{"kind":"Skill","metadata":{"namespace":"community","name":"tear-sheet","version":"0.1.0"},"spec":{"description":"Generate professional company tear sheets using S\u0026P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M\u0026A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M\u0026A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.","files":{"LICENSE":"\n                                 Apache License\n                           Version 2.0, January 2004\n                        http://www.apache.org/licenses/\n\n   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n   1. Definitions.\n\n      \"License\" shall mean the terms and conditions for use, reproduction,\n      and distribution as defined by Sections 1 through 9 of this document.\n\n      \"Licensor\" shall mean the copyright owner or entity authorized by\n      the copyright owner that is granting the License.\n\n      \"Legal Entity\" shall mean the union of the acting entity and all\n      other entities that control, are controlled by, or are under common\n      control with that entity. For the purposes of this definition,\n      \"control\" means (i) the power, direct or indirect, to cause the\n      direction or management of such entity, whether by contract or\n      otherwise, or (ii) ownership of fifty percent (50%) or more of the\n      outstanding shares, or (iii) beneficial ownership of such entity.\n\n      \"You\" (or \"Your\") shall mean an individual or Legal Entity\n      exercising permissions granted by this License.\n\n      \"Source\" form shall mean the preferred form for making modifications,\n      including but not limited to software source code, documentation\n      source, and configuration files.\n\n      \"Object\" form shall mean any form resulting from mechanical\n      transformation or translation of a Source form, including but\n      not limited to compiled object code, generated documentation,\n      and conversions to other media types.\n\n      \"Work\" shall mean the work of authorship, whether in Source or\n      Object form, made available under the License, as indicated by a\n      copyright notice that is included in or attached to the work\n      (an example is provided in the Appendix below).\n\n      \"Derivative Works\" shall mean any work, whether in Source or Object\n      form, that is based on (or derived from) the Work and for which the\n      editorial revisions, annotations, elaborations, or other modifications\n      represent, as a whole, an original work of authorship. For the purposes\n      of this License, Derivative Works shall not include works that remain\n      separable from, or merely link (or bind by name) to the interfaces of,\n      the Work and Derivative Works thereof.\n\n      \"Contribution\" shall mean any work of authorship, including\n      the original version of the Work and any modifications or additions\n      to that Work or Derivative Works thereof, that is intentionally\n      submitted to Licensor for inclusion in the Work by the copyright owner\n      or by an individual or Legal Entity authorized to submit on behalf of\n      the copyright owner. For the purposes of this definition, \"submitted\"\n      means any form of electronic, verbal, or written communication sent\n      to the Licensor or its representatives, including but not limited to\n      communication on electronic mailing lists, source code control systems,\n      and issue tracking systems that are managed by, or on behalf of, the\n      Licensor for the purpose of discussing and improving the Work, but\n      excluding communication that is conspicuously marked or otherwise\n      designated in writing by the copyright owner as \"Not a Contribution.\"\n\n      \"Contributor\" shall mean Licensor and any individual or Legal Entity\n      on behalf of whom a Contribution has been received by Licensor and\n      subsequently incorporated within the Work.\n\n   2. Grant of Copyright License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n      copyright license to reproduce, prepare Derivative Works of,\n      publicly display, publicly perform, sublicense, and distribute the\n      Work and such Derivative Works in Source or Object form.\n\n   3. Grant of Patent License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n      (except as stated in this section) patent license to make, have made,\n      use, offer to sell, sell, import, and otherwise transfer the Work,\n      where such license applies only to those patent claims licensable\n      by such Contributor that are necessarily infringed by their\n      Contribution(s) alone or by combination of their Contribution(s)\n      with the Work to which such Contribution(s) was submitted. If You\n      institute patent litigation against any entity (including a\n      cross-claim or counterclaim in a lawsuit) alleging that the Work\n      or a Contribution incorporated within the Work constitutes direct\n      or contributory patent infringement, then any patent licenses\n      granted to You under this License for that Work shall terminate\n      as of the date such litigation is filed.\n\n   4. Redistribution. You may reproduce and distribute copies of the\n      Work or Derivative Works thereof in any medium, with or without\n      modifications, and in Source or Object form, provided that You\n      meet the following conditions:\n\n      (a) You must give any other recipients of the Work or\n          Derivative Works a copy of this License; and\n\n      (b) You must cause any modified files to carry prominent notices\n          stating that You changed the files; and\n\n      (c) You must retain, in the Source form of any Derivative Works\n          that You distribute, all copyright, patent, trademark, and\n          attribution notices from the Source form of the Work,\n          excluding those notices that do not pertain to any part of\n          the Derivative Works; and\n\n      (d) If the Work includes a \"NOTICE\" text file as part of its\n          distribution, then any Derivative Works that You distribute must\n          include a readable copy of the attribution notices contained\n          within such NOTICE file, excluding those notices that do not\n          pertain to any part of the Derivative Works, in at least one\n          of the following places: within a NOTICE text file distributed\n          as part of the Derivative Works; within the Source form or\n          documentation, if provided along with the Derivative Works; or,\n          within a display generated by the Derivative Works, if and\n          wherever such third-party notices normally appear. The contents\n          of the NOTICE file are for informational purposes only and\n          do not modify the License. You may add Your own attribution\n          notices within Derivative Works that You distribute, alongside\n          or as an addendum to the NOTICE text from the Work, provided\n          that such additional attribution notices cannot be construed\n          as modifying the License.\n\n      You may add Your own copyright statement to Your modifications and\n      may provide additional or different license terms and conditions\n      for use, reproduction, or distribution of Your modifications, or\n      for any such Derivative Works as a whole, provided Your use,\n      reproduction, and distribution of the Work otherwise complies with\n      the conditions stated in this License.\n\n   5. Submission of Contributions. Unless You explicitly state otherwise,\n      any Contribution intentionally submitted for inclusion in the Work\n      by You to the Licensor shall be under the terms and conditions of\n      this License, without any additional terms or conditions.\n      Notwithstanding the above, nothing herein shall supersede or modify\n      the terms of any separate license agreement you may have executed\n      with Licensor regarding such Contributions.\n\n   6. Trademarks. This License does not grant permission to use the trade\n      names, trademarks, service marks, or product names of the Licensor,\n      except as required for reasonable and customary use in describing the\n      origin of the Work and reproducing the content of the NOTICE file.\n\n   7. Disclaimer of Warranty. Unless required by applicable law or\n      agreed to in writing, Licensor provides the Work (and each\n      Contributor provides its Contributions) on an \"AS IS\" BASIS,\n      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n      implied, including, without limitation, any warranties or conditions\n      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n      PARTICULAR PURPOSE. You are solely responsible for determining the\n      appropriateness of using or redistributing the Work and assume any\n      risks associated with Your exercise of permissions under this License.\n\n   8. Limitation of Liability. In no event and under no legal theory,\n      whether in tort (including negligence), contract, or otherwise,\n      unless required by applicable law (such as deliberate and grossly\n      negligent acts) or agreed to in writing, shall any Contributor be\n      liable to You for damages, including any direct, indirect, special,\n      incidental, or consequential damages of any character arising as a\n      result of this License or out of the use or inability to use the\n      Work (including but not limited to damages for loss of goodwill,\n      work stoppage, computer failure or malfunction, or any and all\n      other commercial damages or losses), even if such Contributor\n      has been advised of the possibility of such damages.\n\n   9. Accepting Warranty or Additional Liability. While redistributing\n      the Work or Derivative Works thereof, You may choose to offer,\n      and charge a fee for, acceptance of support, warranty, indemnity,\n      or other liability obligations and/or rights consistent with this\n      License. However, in accepting such obligations, You may act only\n      on Your own behalf and on Your sole responsibility, not on behalf\n      of any other Contributor, and only if You agree to indemnify,\n      defend, and hold each Contributor harmless for any liability\n      incurred by, or claims asserted against, such Contributor by reason\n      of your accepting any such warranty or additional liability.\n\n   END OF TERMS AND CONDITIONS\n\n   APPENDIX: How to apply the Apache License to your work.\n\n      To apply the Apache License to your work, attach the following\n      boilerplate notice, with the fields enclosed by brackets \"[]\"\n      replaced with your own identifying information. (Don't include\n      the brackets!)  The text should be enclosed in the appropriate\n      comment syntax for the file format. We also recommend that a\n      file or class name and description of purpose be included on the\n      same \"printed page\" as the copyright notice for easier\n      identification within third-party archives.\n\n   Copyright 2026-present Kensho Technologies, LLC.\n\n   Licensed under the Apache License, Version 2.0 (the \"License\");\n   you may not use this file except in compliance with the License.\n   You may obtain a copy of the License at\n\n       http://www.apache.org/licenses/LICENSE-2.0\n\n   Unless required by applicable law or agreed to in writing, software\n   distributed under the License is distributed on an \"AS IS\" BASIS,\n   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n   See the License for the specific language governing permissions and\n   limitations under the License.","SKILL.md":"---\nname: tear-sheet\ndescription: \"Generate professional company tear sheets using S\u0026P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M\u0026A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M\u0026A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.\"\n---\n\n# Financial Tear Sheet Generator\n\nGenerate audience-specific company tear sheets by pulling live data from S\u0026P Capital IQ via the S\u0026P Global MCP tools and formatting the result as a professional Word document.\n\n## Style Configuration\n\nThese are sensible defaults. To customize for your firm's brand, modify this section — common changes include swapping the color palette, changing the font (Calibri is standard at many banks), and updating the disclaimer text.\n\n**Colors:**\n- Primary (header banner background, section header text): #1F3864\n- Accent (signature section highlights): #2E75B6\n- Table header row fill: #D6E4F0\n- Table alternating row fill: #F2F2F2\n- Table borders: #CCCCCC\n- Header banner text: #FFFFFF\n\n**Typography (sizes in half-points for docx-js):**\n- Font family: Arial\n- Company name: 18pt bold (size: 36)\n- Section headers: 11pt bold (size: 22), Primary color\n- Body text: 9pt (size: 18)\n- Table text: 8.5pt (size: 17)\n- Footer/disclaimer: 7pt italic (size: 14)\n- Per-template overrides are specified in each reference file's Formatting Notes.\n\n**Company Header Banner:**\n- The header is a navy (#1F3864) banner spanning the full page width with company name in white.\n- **Below the banner, key-value pairs MUST be rendered in a two-column borderless table spanning the full page width.** Left column: company identifiers (ticker, HQ, founded, employees, sector). Right column: financial identifiers (market cap, EV, stock price, shares outstanding). Each cell contains a bold label and regular-weight value on the same line (e.g., \"**Market Cap** $124.7B\"). Do not left-justify all fields in a single column — this wastes horizontal space and looks unprofessional. The two-column spread is the single most important visual signal that distinguishes a professional tear sheet from a default document.\n  - **Implementation:** Create a 2-column table with `borders: none` and `shading: none` on all cells. Set column widths to 50% each. Place left-column fields (ticker, HQ, founded, employees) as separate paragraphs in the left cell. Place right-column fields (market cap, EV, stock price, shares outstanding) in the right cell. Each field is a single paragraph: bold run for the label, regular run for the value.\n  - The specific fields in each column vary by audience — see the reference file's header spec. The principle is always: spread across the page, not clumped left.\n- **Do not use a bordered table for the header key-value block.** Bordered tables are reserved for financial data only.\n- Key metrics in the header (market cap, EV, stock price) should be displayed as inline key-value pairs, not in a separate bordered table.\n\n**Section Headers:**\n- Each section header gets a horizontal rule (thin line, #CCCCCC, 0.5pt) directly beneath it to create clean visual separation between sections.\n- **Render the rule as a bottom border on the header paragraph itself** — do not insert a separate paragraph element for the rule. A separate paragraph adds its own before/after spacing and causes excessive whitespace below section titles.\n- **Implementation:** In docx-js, apply a bottom border to the section header paragraph via `paragraph.borders.bottom = { style: BorderStyle.SINGLE, size: 1, color: \"CCCCCC\" }`. Do not use `doc.addParagraph()` with a separate horizontal rule element. Do not use `thematicBreak`. The border must be on the heading paragraph itself with 0pt spacing after, so the rule sits tight against the header text.\n- Spacing: 12pt before the header paragraph, 0pt after the header paragraph, 4pt before the next content element.\n\n**Bullet Formatting:**\n- Use a single bullet character (•) for all bulleted content across all tear sheet types. Do not mix •, -, ▸, or numbered lists within or across tear sheets.\n- **Synthesis/analysis bullets** (Earnings Highlights, Strategic Fit, Integration Considerations, Conversation Starters): indented block-style formatting with left indent 360 DXA (0.25\") and a hanging indent for the bullet character. These should be visually offset from body text — they're interpretive content and should look distinct from data tables and prose paragraphs.\n- **Informational bullets** within relationship sections: standard body indent (180 DXA), no hanging indent.\n- **Do not apply left-border accents to any bullet sections.** Left-border styling renders inconsistently in docx-js and creates visual artifacts. Use indentation and text size differentiation to distinguish signature sections instead.\n\n**Tables (financial data only):**\n- Header row: Table Header Fill (#D6E4F0) with bold dark text\n- Body rows: alternating white / Table Alternating Fill (#F2F2F2)\n- Borders: Table Border color (#CCCCCC), thin (BorderStyle.SINGLE, size 1)\n- Cell padding: top/bottom 40 DXA, left/right 80 DXA\n- Right-align all numeric columns\n- Always use ShadingType.CLEAR (never SOLID — SOLID causes black backgrounds)\n\n**Layout:**\n- US Letter portrait, 0.75\" margins (1080 DXA all sides)\n\n**Number formatting:**\n- Currency: USD. Use millions unless company revenue \u003e $50B (then billions, one decimal). Label units in column headers (e.g., \"Revenue ($M)\"), not in individual cells.\n- **Table cells: plain numbers with commas, no dollar signs.** Example: a revenue cell shows \"4,916\" not \"$4,916\". The column header carries the unit.\n- Fiscal years: actual years (FY2022, FY2023, FY2024), never relative labels (FY-2, FY-1).\n- Negatives: parentheses, e.g., (2.3%)\n- Percentages: one decimal place\n- Large numbers: commas as thousands separators\n\n**Footer (document footer, not inline):**\nPlace the source attribution and disclaimer in the actual document footer (repeated on every page), not as inline body text at the bottom. The footer is exactly two lines, centered, on every page:\n- Line 1: \"Data: S\u0026P Capital IQ via Kensho | Analysis: AI-generated | [Month Day, Year]\"\n- Line 2: \"For informational purposes only. Not investment advice.\"\n- Style: 7pt italic, centered, #666666 text color\n- This footer text must be identical across all tear sheet types for the same company. Do not vary the wording by audience.\n- **This footer is required on every tear sheet, every audience type, every page.** Do not omit it.\n\n## Component Functions\n\n**You MUST use these exact functions to create document elements. Do NOT write custom docx-js styling code.** Copy these functions into your generated Node script and call them. The Style Configuration prose above remains as documentation; these functions are the enforcement mechanism.\n\n```javascript\nconst docx = require(\"docx\");\nconst {\n  Document, Paragraph, TextRun, Table, TableRow, TableCell,\n  WidthType, AlignmentType, BorderStyle, ShadingType,\n  Header, Footer, PageNumber, HeadingLevel, TableLayoutType,\n  convertInchesToTwip\n} = docx;\n\n// ── Color constants ──\nconst COLORS = {\n  PRIMARY: \"1F3864\",\n  ACCENT: \"2E75B6\",\n  TABLE_HEADER_FILL: \"D6E4F0\",\n  TABLE_ALT_ROW: \"F2F2F2\",\n  TABLE_BORDER: \"CCCCCC\",\n  HEADER_TEXT: \"FFFFFF\",\n  FOOTER_TEXT: \"666666\",\n};\n\nconst FONT = \"Arial\";\n\n// ── 1. createHeaderBanner ──\n// Returns an array of docx elements: [banner paragraph, key-value table]\nfunction createHeaderBanner(companyName, leftFields, rightFields) {\n  // leftFields / rightFields: arrays of { label: string, value: string }\n  const banner = new Paragraph({\n    children: [\n      new TextRun({\n        text: companyName,\n        bold: true,\n        size: 36, // 18pt\n        color: COLORS.HEADER_TEXT,\n        font: FONT,\n      }),\n    ],\n    shading: { type: ShadingType.CLEAR, color: \"auto\", fill: COLORS.PRIMARY },\n    spacing: { after: 0 },\n    alignment: AlignmentType.LEFT,\n  });\n\n  function buildCellParagraphs(fields) {\n    return fields.map(\n      (f) =\u003e\n        new Paragraph({\n          children: [\n            new TextRun({ text: f.label + \"  \", bold: true, size: 18, font: FONT }),\n            new TextRun({ text: f.value, size: 18, font: FONT }),\n          ],\n          spacing: { after: 40 },\n        })\n    );\n  }\n\n  const noBorder = { style: BorderStyle.NONE, size: 0, color: \"FFFFFF\" };\n  const noBorders = { top: noBorder, bottom: noBorder, left: noBorder, right: noBorder };\n  const noShading = { type: ShadingType.CLEAR, color: \"auto\", fill: \"FFFFFF\" };\n\n  const kvTable = new Table({\n    rows: [\n      new TableRow({\n        children: [\n          new TableCell({\n            children: buildCellParagraphs(leftFields),\n            width: { size: 50, type: WidthType.PERCENTAGE },\n            borders: noBorders,\n            shading: noShading,\n          }),\n          new TableCell({\n            children: buildCellParagraphs(rightFields),\n            width: { size: 50, type: WidthType.PERCENTAGE },\n            borders: noBorders,\n            shading: noShading,\n          }),\n        ],\n      }),\n    ],\n    width: { size: 100, type: WidthType.PERCENTAGE },\n  });\n\n  return [banner, kvTable];\n}\n\n// ── 2. createSectionHeader ──\n// Returns a single Paragraph with bottom border rule\nfunction createSectionHeader(text) {\n  return new Paragraph({\n    children: [\n      new TextRun({\n        text: text,\n        bold: true,\n        size: 22, // 11pt\n        color: COLORS.PRIMARY,\n        font: FONT,\n      }),\n    ],\n    spacing: { before: 240, after: 0 }, // 12pt before, 0pt after\n    border: {\n      bottom: { style: BorderStyle.SINGLE, size: 1, color: COLORS.TABLE_BORDER },\n    },\n  });\n}\n\n// ── 3. createTable ──\n// headers: string[], rows: string[][], options: { accentHeader?, fontSize? }\nfunction createTable(headers, rows, options = {}) {\n  const fontSize = options.fontSize || 17; // 8.5pt default\n  const headerFill = options.accentHeader ? COLORS.ACCENT : COLORS.TABLE_HEADER_FILL;\n  const headerTextColor = options.accentHeader ? COLORS.HEADER_TEXT : \"000000\";\n\n  const cellBorders = {\n    top: { style: BorderStyle.SINGLE, size: 1, color: COLORS.TABLE_BORDER },\n    bottom: { style: BorderStyle.SINGLE, size: 1, color: COLORS.TABLE_BORDER },\n    left: { style: BorderStyle.SINGLE, size: 1, color: COLORS.TABLE_BORDER },\n    right: { style: BorderStyle.SINGLE, size: 1, color: COLORS.TABLE_BORDER },\n  };\n\n  const cellMargins = { top: 40, bottom: 40, left: 80, right: 80 };\n\n  function isNumeric(val) {\n    if (typeof val !== \"string\") return false;\n    const cleaned = val.replace(/[,$%()]/g, \"\").trim();\n    return cleaned !== \"\" \u0026\u0026 !isNaN(cleaned);\n  }\n\n  // Header row\n  const headerRow = new TableRow({\n    children: headers.map(\n      (h) =\u003e\n        new TableCell({\n          children: [\n            new Paragraph({\n              children: [\n                new TextRun({\n                  text: h,\n                  bold: true,\n                  size: fontSize,\n                  color: headerTextColor,\n                  font: FONT,\n                }),\n              ],\n            }),\n          ],\n          shading: { type: ShadingType.CLEAR, color: \"auto\", fill: headerFill },\n          borders: cellBorders,\n          margins: cellMargins,\n        })\n    ),\n  });\n\n  // Data rows with alternating shading\n  const dataRows = rows.map((row, rowIdx) =\u003e {\n    const fill = rowIdx % 2 === 1 ? COLORS.TABLE_ALT_ROW : \"FFFFFF\";\n    return new TableRow({\n      children: row.map((cell, colIdx) =\u003e {\n        const align = colIdx \u003e 0 \u0026\u0026 isNumeric(cell)\n          ? AlignmentType.RIGHT\n          : AlignmentType.LEFT;\n        return new TableCell({\n          children: [\n            new Paragraph({\n              children: [\n                new TextRun({ text: cell, size: fontSize, font: FONT }),\n              ],\n              alignment: align,\n            }),\n          ],\n          shading: { type: ShadingType.CLEAR, color: \"auto\", fill: fill },\n          borders: cellBorders,\n          margins: cellMargins,\n        });\n      }),\n    });\n  });\n\n  return new Table({\n    rows: [headerRow, ...dataRows],\n    width: { size: 100, type: WidthType.PERCENTAGE },\n  });\n}\n\n// ── 4. createBulletList ──\n// items: string[], style: \"synthesis\" | \"informational\"\nfunction createBulletList(items, style = \"synthesis\") {\n  const indent =\n    style === \"synthesis\"\n      ? { left: 360, hanging: 180 }   // 360 DXA left, hanging indent for bullet\n      : { left: 180 };                 // 180 DXA, no hanging\n\n  return items.map(\n    (item) =\u003e\n      new Paragraph({\n        children: [\n          new TextRun({ text: \"•  \", font: FONT, size: 18 }),\n          new TextRun({ text: item, font: FONT, size: 18 }),\n        ],\n        indent: indent,\n        spacing: { after: 60 },\n      })\n  );\n}\n\n// ── 5. createFooter ──\n// date: string (e.g., \"February 23, 2026\")\nfunction createFooter(date) {\n  return new Footer({\n    children: [\n      new Paragraph({\n        children: [\n          new TextRun({\n            text: `Data: S\u0026P Capital IQ via Kensho | Analysis: AI-generated | ${date}`,\n            italics: true,\n            size: 14, // 7pt\n            color: COLORS.FOOTER_TEXT,\n            font: FONT,\n          }),\n        ],\n        alignment: AlignmentType.CENTER,\n      }),\n      new Paragraph({\n        children: [\n          new TextRun({\n            text: \"For informational purposes only. Not investment advice.\",\n            italics: true,\n            size: 14,\n            color: COLORS.FOOTER_TEXT,\n            font: FONT,\n          }),\n        ],\n        alignment: AlignmentType.CENTER,\n      }),\n    ],\n  });\n}\n```\n\n**Usage in generated scripts:**\n1. Copy all functions and constants above into the generated Node.js script\n2. Call `createHeaderBanner(...)` instead of manually building banner paragraphs and tables\n3. Call `createSectionHeader(...)` for every section title — never manually set paragraph borders\n4. Call `createTable(...)` for **all** tabular data — financial summaries, trading comps, M\u0026A activity, relationship tables, funding history, etc. Pass `{ accentHeader: true }` for M\u0026A activity tables (IB/M\u0026A template). For non-numeric tables (e.g., relationships, ownership), the function still works correctly — it only right-aligns cells that contain numeric values.\n5. Call `createBulletList(items, \"synthesis\")` for earnings highlights, strategic fit, integration considerations, and conversation starters\n6. Call `createBulletList(items, \"informational\")` for relationship entries\n7. Pass `createFooter(date)` to the Document constructor's `footers.default` property\n\n**What these functions eliminate:**\n- Black background tables (enforces `ShadingType.CLEAR` everywhere)\n- Separate horizontal rule paragraphs under section headers (enforces `border.bottom` on the paragraph itself)\n- Bordered key-value tables in headers (enforces `borders: none`)\n- Inconsistent bullet styles (enforces `•` character only)\n- Missing footers (provides the exact footer structure)\n\n## Workflow\n\n### Step 1: Identify Inputs\n\nGather up to four things before proceeding:\n\n1. **Company** — name or ticker. If only a ticker, resolve the full company name with an initial query (e.g., use the company info tool).\n2. **Audience** — one of four types:\n   - **Equity Research** — for buy-side/sell-side analysts evaluating an investment\n   - **IB / M\u0026A** — for bankers profiling a company in transaction context\n   - **Corp Dev** — for internal strategic teams evaluating an acquisition target\n   - **Sales / BD** — for commercial teams preparing for a client meeting\n3. **Comparable companies** (optional) — if the user has specific comps in mind, note them. Otherwise the skill will identify peers from S\u0026P Global data. This matters for Equity Research, IB/M\u0026A, and Corp Dev tear sheets.\n4. **Page length preference** (optional) — defaults vary by audience (see below), but the user can override.\n\nIf the user doesn't specify an audience, ask.\n\n### Step 2: Read the Audience-Specific Reference\n\nRead the corresponding reference file from this skill's directory:\n\n- Equity Research → `references/equity-research.md`\n- IB / M\u0026A → `references/ib-ma.md`\n- Corp Dev → `references/corp-dev.md`\n- Sales / BD → `references/sales-bd.md`\n\nEach reference defines sections, a query plan, formatting guidance, and page length defaults.\n\n### Step 3: Pull Data via S\u0026P Global MCP\n\n**First:** Create the intermediate file directory:\n```bash\nmkdir -p /tmp/tear-sheet/\n```\n\nUse the **S\u0026P Global** MCP tools (also known as the Kensho LLM-ready API). Claude will have access to structured tools for financial data, company information, market data, consensus estimates, earnings transcripts, M\u0026A transactions, and business relationships. The query plans in each reference file describe what data to retrieve for each section — map these to the appropriate S\u0026P Global tools available in the conversation.\n\n**After each query step, immediately write the retrieved data to the intermediate file(s) specified in the reference file's query plan.** Do not defer writes — data written to disk is protected from context degradation in long conversations.\n\n**Query strategy:**\nEach reference file includes a query plan with 4-6 data retrieval steps. These are starting points, not rigid constraints. Prioritize data completeness over minimizing calls:\n\n- **Always pull 4 fiscal years of financial data**, even though only 3 years are displayed. The fourth (earliest) year is needed to compute YoY revenue growth for the first displayed year. Without it, the earliest year's growth rate will show \"N/A\" — which looks like missing data, not a design choice.\n- Execute the query plan as written, using whichever S\u0026P Global tools match the data needed.\n- If a tool call returns incomplete results, try alternative tools or narrower queries. For example, if company summary doesn't include segment detail, try the segments tool directly.\n- If a data point isn't returned after a targeted retry, move on — label it \"N/A\" or \"Not disclosed.\"\n- Never fabricate data. If the tools don't return a number, do not estimate from training knowledge.\n\n**User-specified comps:** If the user provided comparable companies, query financials and multiples for each comp explicitly. If no comps were provided, use whatever peer data the tools return, or identify peers from the company's sector using the competitors tool.\n\n**Optional context from the user:** Listen for additional context the user provides naturally. If they mention who the acquirer is (\"we're looking at this for our platform\"), what they sell (\"we sell data analytics to banks\"), or who the likely buyers are (\"this would be interesting to Salesforce or Microsoft\"), incorporate that context into the relevant synthesis sections (Strategic Fit, Conversation Starters, Deal Angle). Don't prompt for this information — just use it if offered.\n\n**Private company handling:**\nCIQ includes private company data, so query the same way. However, expect sparser results. When generating for a private company:\n- Skip: stock price, 52-week range, beta, stock performance, consensus estimates, trading comps\n- Lean into: business overview, relationships, ownership structure, whatever financials are available\n- Note \"Private Company\" prominently in the header\n\n### Step 3b: Calculate Derived Metrics\n\nAfter all data collection is complete and intermediate files are written, compute all derived metrics in a single dedicated pass. This is a calculation-only step — no new MCP queries.\n\n**Read all intermediate files back into context**, then compute:\n\n- **Margins:** Gross Margin %, EBITDA Margin %, FCF Margin %, Operating Margin %\n- **Growth rates:** YoY revenue growth, YoY segment revenue growth, YoY EPS growth\n- **Efficiency ratios:** FCF Conversion (FCF/EBITDA), R\u0026D as % of Revenue, Capex as % of Revenue\n- **Capital structure:** Net Debt (Total Debt − Cash \u0026 Equivalents), Net Debt / EBITDA\n- **Segment mix:** Each segment's revenue as % of consolidated total revenue (use consolidated revenue as denominator per Data Integrity Rule 8)\n\n**Validation (moved from Arithmetic Validation):** During this calculation pass, enforce all arithmetic checks:\n\n- **Margin calculations:** Verify EBITDA Margin = EBITDA / Revenue, Gross Margin = Gross Profit / Revenue, etc. If the computed margin doesn't match the raw numbers, use the computation from raw components.\n- **Growth rates:** Verify YoY growth = (Current − Prior) / Prior. Don't rely on pre-computed growth rates if you have the underlying values.\n- **Segment totals:** If showing revenue by segment, verify segments sum to total revenue (within rounding tolerance). If they don't, omit the total row rather than publishing inconsistent math.\n- **Percentage columns:** Verify \"% of Total\" columns sum to ~100%.\n- **Valuation cross-checks:** If you show both EV and EV/Revenue, verify EV / Revenue ≈ the stated multiple.\n\nIf a validation fails: attempt recalculation from raw data. If still inconsistent, flag the metric as \"N/A\" rather than publishing incorrect numbers. Quiet math errors in a tear sheet destroy credibility.\n\n**Write results** to `/tmp/tear-sheet/calculations.csv` with columns: `metric,value,formula,components`\n\nExample rows:\n```\nmetric,value,formula,components\ngross_margin_fy2024,72.4%,gross_profit/revenue,\"9524/13159\"\nrevenue_growth_fy2024,12.3%,(current-prior)/prior,\"13159/11716\"\nnet_debt_fy2024,2150,total_debt-cash,\"4200-2050\"\n```\n\n### Step 3c: Verify Data Files\n\nBefore generating the document, verify that all intermediate files are present and populated.\n\n**Read each intermediate file** via separate read operations and print a verification summary:\n\n```\n=== Tear Sheet Data Verification ===\ncompany-profile.txt: ✓ (12 fields)\nfinancials.csv:      ✓ (36 rows)\nsegments.csv:        ✓ (8 rows)\nvaluation.csv:       ✓ (5 rows)\ncalculations.csv:    ✓ (18 rows)\nearnings.txt:        ✓ (populated)\nrelationships.txt:   ⚠ MISSING\npeer-comps.csv:      ✓ (12 rows)\n================================\n```\n\n**Soft gate:** If any file expected for the current audience type is missing or empty, print a warning but continue. The tear sheet handles missing data gracefully with \"N/A\" and section skipping. However, the warning ensures visibility into what data was lost.\n\n**Critical rule: The files — not your memory of earlier conversation — are the single source of truth for every number in the document.** When generating the DOCX in Step 4, read values from the intermediate files. Do not rely on conversation context for financial data.\n\n### Step 4: Format as DOCX\n\nRead `/mnt/skills/public/docx/SKILL.md` for docx creation mechanics (docx-js via Node). Apply the Style Configuration above plus the section-specific formatting in the reference file.\n\n**Page length defaults (user can override):**\n- Equity Research: 1 page (density is the convention)\n- IB / M\u0026A: 1-2 pages\n- Corp Dev: 1-2 pages\n- Sales / BD: 1-2 pages\n\nIf content exceeds the target, each reference file specifies which sections to cut first.\n\n**Output filename:** `[CompanyName]_TearSheet_[Audience]_[YYYYMMDD].docx`\nExample: `Nvidia_TearSheet_CorpDev_20260220.docx`\n\nSave to `/mnt/user-data/outputs/` and present to the user.\n\n## Data Integrity Rules\n\nThese override everything else:\n1. **S\u0026P Global tools are the only source for financial data.** Do not fill gaps with training knowledge — it may be stale or wrong.\n2. **Label what you can't find.** Use \"N/A\" or \"Not disclosed\" rather than omitting a row silently.\n3. **Dates matter.** Note the fiscal year end or reporting period. Don't assume calendar year = fiscal year. Market data (stock prices, market cap) should include an \"as of\" date.\n4. **Don't mix reporting periods.** If you have FY2023 revenue and LTM EBITDA, label them distinctly.\n5. **Prefer MCP-returned fields over manual computation.** If the S\u0026P Global tools return a pre-computed field (e.g., net debt, EBITDA, FCF), use that value directly rather than computing it from components. Only compute derived metrics manually when the tools do not return the field. This reduces discrepancies.\n6. **Ensure consistency across tear sheet types.** If generating multiple tear sheets for the same company (e.g., equity research and IB/M\u0026A in the same session), the same underlying data points must produce identical values across all outputs. Net debt, revenue, EBITDA, margins, and growth rates must match exactly. Do not re-query or re-compute independently per report — reuse the same retrieved values.\n7. **Never downgrade known transaction values.** If the M\u0026A tools return a deal value for a transaction, that value must appear in the output. Do not replace a known deal value with \"Undisclosed.\" Use \"Undisclosed\" only when the tools genuinely return no value for a transaction.\n8. **Use consolidated revenue as the denominator for segment percentages.** When computing \"% of Total\" for segment tables, divide each segment's revenue by consolidated total revenue (as reported on the income statement), not by the sum of segment revenues. The sum of segments often exceeds consolidated revenue due to intersegment eliminations. Using consolidated revenue ensures percentages align with the total revenue figure shown elsewhere in the document.\n9. **Always include forward (NTM) multiples when available.** If the tools return both trailing and forward valuation multiples, both must appear in the output. Forward multiples are the primary valuation reference for equity research, IB/M\u0026A, and corp dev audiences. Never show only trailing multiples when forward data is available.\n10. **No S\u0026P Global tool returns executive or management data.** Do not populate management names, titles, or biographical details from training data — this violates Rule 1 and produces stale information. If a management section appears in a template, omit it entirely. Ownership structure (institutional holders, insider %, PE sponsor) may be included only if returned by the tools — gate with \"data permitting.\"\n\n## Intermediate File Rule\n\nAll data retrieved from MCP tools must be persisted to structured intermediate files before document generation. These files — not conversation context — are the single source of truth for every number in the document.\n\n**Setup:** At the start of Step 3, create the working directory:\n```\nmkdir -p /tmp/tear-sheet/\n```\n\n**Write-after-query mandate:** After each MCP query step completes, immediately write the retrieved data to the appropriate intermediate file(s). Do not wait until all queries finish. Each reference file's query plan specifies which file(s) to write after each step.\n\n**File schemas:**\n\n| File | Format | Columns / Structure | Used By |\n|---|---|---|---|\n| `/tmp/tear-sheet/company-profile.txt` | Key-value text | name, ticker, exchange, HQ, sector, industry, founded, employees, market_cap, enterprise_value, stock_price, 52wk_high, 52wk_low, shares_outstanding, beta, ownership | All |\n| `/tmp/tear-sheet/financials.csv` | CSV | `period,line_item,value,source` | All |\n| `/tmp/tear-sheet/segments.csv` | CSV | `period,segment_name,revenue,source` | ER, IB, CD |\n| `/tmp/tear-sheet/valuation.csv` | CSV | `metric,trailing,forward,source` | ER, IB, CD |\n| `/tmp/tear-sheet/consensus.csv` | CSV | `metric,fy_year,value,source` | ER |\n| `/tmp/tear-sheet/earnings.txt` | Structured text | Quarter, date, key quotes, guidance, key drivers | ER, IB, Sales |\n| `/tmp/tear-sheet/relationships.txt` | Structured text | Customers, suppliers, partners, competitors — each with descriptors | IB, CD, Sales |\n| `/tmp/tear-sheet/peer-comps.csv` | CSV | `ticker,metric,value,source` | ER, IB, CD |\n| `/tmp/tear-sheet/ma-activity.csv` | CSV | `date,target,deal_value,type,rationale,source` | IB, CD |\n| `/tmp/tear-sheet/calculations.csv` | CSV | `metric,value,formula,components` | All (written in Step 3b) |\n\n**Abbreviations:** ER = Equity Research, IB = IB/M\u0026A, CD = Corp Dev, Sales = Sales/BD.\n\nNot every audience type uses every file — the reference files define which query steps apply. Files not relevant to the current audience type need not be created.\n\n**Raw values only.** Intermediate files store raw values as returned by the tools. Do not pre-compute margins, growth rates, or other derived metrics in these files — that happens in Step 3b.\n\n**Page budget enforcement:** Each reference file specifies a default page length and a numbered cut order. If the rendered document exceeds the target, apply cuts in the order specified — do not attempt to shrink font sizes or margins below the template minimums. The cut order is a strict priority stack: cut section 1 completely before touching section 2.\n\n## Content Quality Rules\n\n11. **Rewrite every narrative section for the audience.** The CIQ company summary is an input, not an output. Each audience type needs a different description: concise and thesis-oriented for equity research, pitchbook prose for IB, product-focused for Corp Dev, plain language for Sales/BD. Never paste the CIQ summary verbatim into any tear sheet.\n12. **Differentiate earnings highlights by audience.** The same earnings call produces different takeaways for different readers. Equity research wants segment-level performance and consensus beat/miss. IB wants margin trajectory and strategic commentary. Sales/BD wants strategic themes that create conversation angles. Do not reuse the same bullets across tear sheet types.\n13. **Synthesis sections are the differentiator.** Strategic Fit Analysis, Integration Considerations, Conversation Starters, and Business Overview paragraphs are where the tear sheet earns its value. These sections require analytical reasoning that connects data points into a narrative — listing company names without context is not synthesis.\n14. **Flag pending divestitures in segment tables.** If a company has announced a pending divestiture of a segment or business unit, add a footnote or parenthetical to the segment table noting the pending transaction (e.g., \"Mobility* — *Pending divestiture, expected mid-2026\"). For Corp Dev and IB/M\u0026A tear sheets, include a one-line note below the segment table showing pro-forma revenue and revenue mix excluding the divested segment. This helps the reader evaluate the \"go-forward\" business without doing the math themselves.\n\n### Arithmetic Validation\n\n**→ Arithmetic validation is now enforced in Step 3b (Calculate Derived Metrics).** All margin calculations, growth rates, segment totals, percentage columns, and valuation cross-checks are validated during the dedicated calculation pass, before document generation begins. See Step 3b for the full validation checklist.\n","references/corp-dev.md":"# Corporate Development Tear Sheet\n\n## Purpose\nA target evaluation profile for an internal Corp Dev team assessing a potential acquisition. Unlike the IB/M\u0026A profile (which tells a strategic *story* for a pitch), this is an analytical document focused on strategic fit: how the target's products, customers, technology, and operations overlap with or complement the acquirer's. The Corp Dev audience already knows their own company — they need to understand the target through the lens of \"should we buy this, and what would integration look like?\"\n\n**Default page length:** 1-2 pages. Corp Dev teams are comfortable with denser profiles and won't penalize a second page if the content is substantive.\n\n## Query Plan\n\nStart with these queries. Break apart and follow up if results are incomplete.\n\n**Query 1 — Target profile:**\n\"[Company] business description products services technology platform headquarters founded employees sector industry\"\n→ Header, Business \u0026 Product Overview\n→ **Immediately write** to `/tmp/tear-sheet/company-profile.txt`\n\n**Query 2 — Financials:**\n\"[Company] annual income statement revenue gross profit EBITDA operating income net income capex free cash flow R\u0026D expense total debt cash and equivalents last 4 fiscal years\"\n→ Financial Summary (pull 4 years; display 3; use the earliest year only for YoY growth computation. R\u0026D is especially important for Corp Dev — they want to understand the target's investment in IP)\n→ **Immediately write** raw values to `/tmp/tear-sheet/financials.csv`\n\n**Query 3 — Segments + customers:**\n\"[Company] revenue by segment business unit last 2 fiscal years key customers end markets customer concentration\"\n→ Revenue Mix (need 2 years for YoY growth), Customer Analysis\n→ **Immediately write** segment data to `/tmp/tear-sheet/segments.csv` (skip if no segment data returned)\n\n**Query 4 — Relationships + competitive landscape:**\n\"[Company] key customers suppliers partners competitors business relationships technology vendors\"\n→ Strategic Fit Analysis, Ecosystem Map\n→ **Immediately write** to `/tmp/tear-sheet/relationships.txt`\n\n**Query 5 — Valuation + peers:**\nIf user provided specific comps:\n\"[Comp company] enterprise value EV/Revenue EV/EBITDA revenue growth EBITDA margin\"\nOtherwise:\nUse the competitors tool to identify 3-5 public peers, then pull EV/Revenue (NTM), EV/EBITDA (NTM), revenue growth %, and EBITDA margin % for each.\nAlso: \"[Company] enterprise value market capitalization valuation multiples\"\n→ Valuation Context\n→ **Immediately write** company multiples to `/tmp/tear-sheet/valuation.csv`\n→ **Immediately write** peer data to `/tmp/tear-sheet/peer-comps.csv`\n\n**Query 6 — Ownership (data permitting):**\n\"[Company] ownership structure investors institutional ownership insider ownership\"\n→ Ownership snapshot (no intermediate file — included in company-profile.txt if available)\n\n## Sections\n\nListed in priority order. See \"Page Budget \u0026 Cut Order\" below for explicit cut guidance.\n\n### 1. Company Header\nSimilar to IB/M\u0026A but adds a \"Strategic Relevance\" tagline.\n\n| Field | Notes |\n|---|---|\n| Company name | Large, bold |\n| Ticker \u0026 Exchange | If public; omit for private |\n| HQ Location | |\n| Founded / Employees | |\n| Enterprise Value | Market cap for public; latest valuation for private |\n| Ownership | Public / PE-backed / Founder-led / etc. |\n| **Strategic Relevance** | One sentence: why this target is attractive to an acquirer (synthesized from data) |\n\nThe \"Strategic Relevance\" line is unique to Corp Dev. Write from a neutral analytical perspective, not from the target's marketing language. Frame what an acquirer *gets* — not what the target *is*. Good: \"Dominant position in commodity price benchmarks with regulatory moat and 70%+ gross margins — a capital-light, high-barrier data asset.\" Bad: \"The world's leading provider of financial data and analytics.\" The former tells a corp dev team why this is attractive; the latter is a press release.\n\n### 2. Business \u0026 Product Overview\n**Do not paste the CIQ company summary.** Rewrite in 4-6 sentences (one paragraph, not two) with a product and technology focus — this audience evaluates acquisitions, not investments:\n- Core products/services and what problem they solve\n- Technology or platform architecture (at a high level)\n- Key differentiators and competitive moat\n- Customer segments — who buys this and why\n- Current strategic direction\n\nWrite with an acquirer's lens. The reader is thinking: \"How would this fit with what we already have?\" The description should make it easy to spot overlaps and complements.\n\n### 3. Revenue Mix \u0026 Customer Profile\nTwo sub-sections:\n\n**a) Revenue by Segment** (if available):\n\n| Segment | Revenue ($M) | % of Total | YoY Growth |\n|---|---|---|---|\n\n**b) Customer Analysis:**\nBelow the segment table (or in place of it if segments aren't available), write a qualitative paragraph covering:\n- Customer concentration: are the top 5 customers \u003e30% of revenue? (Critical for acquisition risk)\n- Customer type: enterprise vs. SMB vs. consumer\n- Contract structure: subscription vs. transactional vs. license (if known)\n- Geographic mix\n\nCustomer concentration is the single most important signal here — if the tools return any data on top customers or revenue concentration, highlight it prominently. If data is sparse, write what you can infer from the business description and relationships. Keep this to 2-3 sentences — it's context for the segment table, not a standalone analysis.\n\n### 4. Strategic Fit Analysis\n**This is the signature section of the Corp Dev tear sheet.** It is required — do not skip or compress it. It uses the Business Relationships data from S\u0026P Capital IQ to map overlaps and complements.\n\nOrganize as three buckets. **Each bucket must be 2-3 sentences of analytical reasoning, not a list of company names.** Listing \"Customers: Microsoft, JPMorgan, Google\" without context is useless. Instead, explain *what the overlap or complement means* for an acquisition.\n\n**Customer Overlap:** Do the target's customers also buy from the acquirer (or the acquirer's industry)? Shared customers = easier cross-sell, but also risk of channel conflict. Name shared relationships and explain the implications.\n\n**Technology / Product Complement:** Does the target fill a gap in the acquirer's portfolio? What does their tech stack look like? Who are their technology vendors? If they're already using the acquirer's technology, explain why that's a strong integration signal.\n\n**Competitive Displacement:** Is the target a competitor, or does acquiring them remove a competitor from the market? Name the target's key competitors and explain how the competitive landscape would change post-acquisition.\n\nThis section requires synthesis — combine relationship data with the business overview to draw connections. If the user has told you who the acquirer is, tailor to that acquirer. If not, write it generically but still analytically.\n\n**Length discipline:** The 2-3 sentence target per bucket above is a hard constraint, not a suggestion. Each bullet should front-load the insight, then support with one specific data point. The actual outputs frequently balloon to 5-7 sentences per bullet — this is the primary driver of page 3 spillover. If you find yourself writing more than 3 sentences, move the excess detail to Integration Considerations.\n\n### 5. Financial Summary (3-Year)\nSimilar to IB/M\u0026A but with added emphasis on R\u0026D and capital efficiency.\n\n| Metric ($M) | FY20XX | FY20XX | FY20XX |\n|---|---|---|---|\n| Revenue | | | |\n| Revenue Growth % | | | |\n| Gross Margin % | | | |\n| EBITDA | | | |\n| EBITDA Margin % | | | |\n| R\u0026D Expense | | | |\n| R\u0026D as % of Revenue | | | |\n| Capex | | | |\n| Free Cash Flow | | | |\n| FCF Conversion (FCF/EBITDA) | | | |\n\nR\u0026D intensity signals how much of the target's value is in IP vs. services. FCF conversion signals integration complexity — high-capex businesses are harder to integrate. If R\u0026D expense isn't separately reported, note \"Not separately disclosed\" in the row rather than \"N/A\" — this itself is informative (suggests R\u0026D may be embedded in COGS or SG\u0026A).\n\n**Capital Structure** (compact sub-table below the financial summary):\n\n| Metric | Value |\n|---|---|\n| Total Debt | $XXM |\n| Cash \u0026 Equivalents | $XXM |\n| Net Debt | $XXM |\n| Net Debt / EBITDA | X.Xx |\n\nFrame for acquisition context: below the table, include one sentence interpreting leverage (e.g., \"Net debt of $X represents Y.Yx EBITDA leverage, which is manageable for an investment-grade acquirer but would compound leverage in an LBO scenario.\"). Pull from the balance sheet data already retrieved.\n\n### 6. Valuation Context\n**This section is required for public companies.** Corp Dev teams need market context to frame a potential bid. If the tools return valuation multiples, this section must appear. Do not cut it for space — cut Ownership Snapshot (Section 7) first.\n\nNot a formal valuation — Corp Dev teams do their own DCFs. This provides market context.\n\n**a) Trading multiples** (if public):\n\n**Peer context is essential, not optional.** If the user provided comps, show each in its own column. If no comps were provided, use the competitors tool to identify 3-5 public peers, then pull EV/Revenue (NTM), EV/EBITDA (NTM), revenue growth %, and EBITDA margin % for each.\n\n| Metric | [Company] | [Peer 1] | [Peer 2] | [Peer 3] | Peer Median |\n|---|---|---|---|---|---|\n| EV/Revenue (NTM) | | | | | |\n| EV/EBITDA (NTM) | | | | | |\n| Revenue Growth % | | | | | |\n| EBITDA Margin % | | | | | |\n\nA company's multiples in isolation tell a corp dev team nothing — they need relative context to assess whether the target is cheap or rich vs. the peer set. This is the minimum viable valuation context for a target profile.\n\nIf peer multiples are unavailable from the tools, show the company's own multiples and list selected peer names below the table for the reader's reference.\n\n**b) Precedent transactions (data permitting):**\nIf the M\u0026A tools return recent transactions involving the company's peers or within the same sub-sector, display them:\n\n| Date | Target | Acquirer | EV ($M) | EV/Rev | EV/EBITDA |\n|---|---|---|---|---|---|\n\nFrame as context: \"Recent transactions in [sub-sector] have valued targets at X–Yx revenue.\"\n\nIf precedent transaction data is not available from the tools, note \"Precedent transaction data not available from data source\" rather than omitting silently. Do not fabricate precedent multiples.\n\nFor private companies, skip trading multiples. Precedent transactions (data permitting) are still useful.\n\n### 7. Ownership Snapshot (data permitting — omit if tools return nothing)\nIf the tools return ownership data, include a compact block: founder/family control %, PE sponsor details, institutional concentration. Ownership structure directly impacts deal complexity and is relevant for integration considerations.\n\n**Do not include a Management Team table.** No S\u0026P Global tool returns executive data — see Data Integrity Rule 10. Management names from training data will be stale.\n\n### 8. Integration Considerations\n**Required section — do not cut.** This is the analytical capstone of the Corp Dev tear sheet. Synthesized observations drawn from everything above. 3-4 substantive bullets:\n- **Key risks:** Customer concentration, key-person dependency, technology debt indicators\n- **Integration complexity:** Geography (multi-country = harder), employee count, number of products\n- **Synergy signals:** Shared customers, complementary products, overlapping technology vendors\n- **Open questions:** What would a corp dev team need to diligence before making a bid? Focus on concrete, actionable diligence items — not open-ended strategic questions. Good examples: regulatory approval timeline and jurisdictions, change-of-control provisions in key contracts, key-person retention risk (especially founders/CTOs), customer contract transferability, IP ownership structure, outstanding litigation. Bad examples: \"How defensible is X?\" or \"What is the long-term market opportunity?\" — these are analyst questions, not diligence items.\n\nLabel clearly as analytical observations, not facts from the data source.\n\n## Page Budget \u0026 Cut Order\n\n**Target: 2 pages.** Corp Dev profiles can fill both pages with substantive content, but must not spill to a third unless the user explicitly requests a longer format. If content exceeds 2 pages, cut in this order (cut each completely before moving to the next):\n\n1. Ownership Snapshot (section 7) — omit entirely\n2. Customer Analysis prose under Revenue Mix (section 3) — reduce to 2 sentences max\n3. Valuation Context prose (section 6) — keep peer comp table, cut interpretive paragraph below it\n4. Precedent Transactions (section 6b) — keep the \"not available\" note, remove if space-critical\n5. Capital Structure prose — keep table, cut interpretive paragraph below it\n6. Strategic Fit Analysis (section 4) — compress each bullet to 2-3 sentences max (do not remove the section)\n\nNever cut: Business \u0026 Product Overview (2), Financial Summary (5 core table), Integration Considerations (8).\n\n## Formatting Notes\n- **Strategic Fit Analysis is the centerpiece.** Give it distinctive formatting:\n  - Bump text to 9.5pt (size: 19) — slightly larger than standard body text. This section should look like the most important content on the page.\n  - Use the standard indented block-style bullets from the global style config (360 DXA left indent).\n  - Do not apply left-border accents — they render inconsistently in docx-js.\n- Financial Summary should include R\u0026D and FCF conversion prominently.\n- Valuation Context with peer comps is required for public companies — do not cut before Ownership Snapshot.\n- For private targets, the profile leans heavily on qualitative sections (Business Overview, Strategic Fit, Relationships) — this is expected and still highly valuable.\n- Tone: analytical and evaluative, not promotional. This isn't a pitch — it's an assessment.\n- **Two-page discipline:** Before rendering, mentally estimate page count. The combination of Strategic Fit (3 long bullets) + Integration Considerations (4 bullets) alone can consume a full page — if so, compress Strategic Fit bullets first.\n","references/equity-research.md":"# Equity Research Tear Sheet\n\n## Purpose\nA dense snapshot for buy-side or sell-side analysts evaluating an investment. Emphasis on valuation, forward estimates, financial trajectory, and analyst consensus. Everything supports or challenges an investment thesis.\n\n**Default page length:** 1 page. Equity research tear sheets are conventionally single-page — density is the point. If the user requests more space, extend to 2 pages.\n\n## Query Plan\n\nStart with these queries. If results are incomplete, break into narrower follow-ups.\n\n**Query 1 — Profile + market data:**\n\"[Company] company overview sector industry market capitalization enterprise value stock price 52-week high low shares outstanding beta\"\n→ Header, Business Description\n→ **Immediately write** to `/tmp/tear-sheet/company-profile.txt`\n\n**Query 2 — Historical financials:**\n\"[Company] annual income statement revenue gross profit EBITDA net income EPS free cash flow total debt cash and equivalents last 4 fiscal years\"\n→ Financial Summary (pull 4 years; display 3; use the earliest year only for YoY growth computation)\n→ **Immediately write** raw values to `/tmp/tear-sheet/financials.csv`\n\n**Query 2b — Segments (if available):**\n\"[Company] revenue by segment business unit last 2 fiscal years\"\n→ Revenue \u0026 Segment Breakdown (need 2 years for YoY growth). If segment data is unavailable, skip this section — do not leave a blank table.\n→ **Immediately write** to `/tmp/tear-sheet/segments.csv` (skip if no segment data returned)\n\n**Query 3 — Valuation + consensus:**\n\"[Company] P/E EV/EBITDA EV/Revenue valuation multiples consensus revenue EPS estimates analyst recommendations price target\"\n→ Valuation Snapshot, Consensus Estimates\n→ **Immediately write** multiples to `/tmp/tear-sheet/valuation.csv`\n→ **Immediately write** estimates to `/tmp/tear-sheet/consensus.csv`\n\n**Query 4 — Earnings:**\n\"[Company] most recent earnings call key takeaways guidance\"\n→ Earnings Highlights\n→ **Immediately write** to `/tmp/tear-sheet/earnings.txt`\n\n**Query 5 — Stock performance:**\n\"[Company] stock price return 1 month 3 month 6 month 1 year YTD performance\"\n→ Stock Performance (no intermediate file — data goes directly into document)\n\n**Query 6 (if user provided comps):**\n\"[Comp company] market cap EV/Revenue EV/EBITDA revenue growth\" — repeat for each comp\n→ Peer context for Valuation Snapshot\n→ **Immediately write** to `/tmp/tear-sheet/peer-comps.csv`\n\n## Sections\n\nListed in priority order. If constrained to one page, cut from the bottom.\n\n### 1. Company Header\nCompact key-value block rendered as a two-column borderless table per the global style config.\n\nLeft column: Ticker (exchange), sector / industry, HQ\nRight column: Stock price, 52-week range, market cap, EV, shares outstanding, beta\n\n### 2. Business Description\n2-3 tight sentences. **Rewrite in your own words for an analyst audience** — do not paste the CIQ company summary verbatim. The CIQ summary is an input; the output should be concise and thesis-oriented.\n\nFor well-known, widely covered companies, assume the analyst already knows the basic business. Lead with what's *changing* — strategic pivots, portfolio reshaping, new growth vectors — not a Wikipedia-style overview. For example, for a Fortune 500 company, don't spend a sentence on \"provides financial data to institutions.\" Instead: \"Reshaping its portfolio toward higher-margin data and analytics businesses, with a pending Mobility spin-off and aggressive AI investment through its Kensho subsidiary.\"\n\nFor lesser-known companies, a brief \"what they do\" sentence is appropriate before pivoting to the thesis-relevant dynamics.\n\n### 3. Valuation Snapshot\nCenterpiece of the equity tear sheet.\n\n| Metric | Trailing | Forward (NTM) |\n|---|---|---|\n| P/E | | |\n| EV/EBITDA | | |\n| EV/Revenue | | |\n| P/FCF | | |\n| Dividend Yield | | |\n\n**Forward multiples are mandatory when available from the tools.** Showing only trailing multiples when forward data exists is a significant gap — analysts value companies on forward earnings. If forward multiples aren't available, show trailing only and note \"Fwd estimates N/A.\"\n\nIf the user provided comparable companies, add columns for each comp (or a \"Peer Median\" column if 3+ comps). If no user comps, and the tools return peer data, include a Peer Median column. If neither, show the company's multiples only.\n\n### 4. Consensus Estimates\nWhat the Street expects — a key differentiator for this tear sheet type.\n\n**Data availability note:** The depth of consensus data varies by company and coverage. Include whatever the tools return — analyst count, price target, Buy/Hold/Sell distribution — but do not fabricate or estimate any consensus figure. For thinly covered companies, this section may contain only revenue and EPS estimates, which is still valuable.\n\n| Metric | FY[year] Est. | FY[year+1] Est. |\n|---|---|---|\n| Revenue | | |\n| EPS (normalized) | | |\n| EBITDA | | |\n\nUse normalized/adjusted EPS where available — GAAP EPS can be distorted by one-time items and is less useful for forward estimates.\n\nBelow the main estimates table, include a compact analyst consensus block (if data is available from the tools):\n\n| Analyst Consensus | |\n|---|---|\n| Mean Price Target | $XXX |\n| # of Estimates | XX |\n| Buy / Hold / Sell | XX / XX / XX |\n\nIf price target or recommendation data is unavailable, omit the analyst consensus block rather than showing empty rows. Do not fabricate these figures.\n\nIf consensus data isn't available at all, skip this entire section and note \"Consensus estimates not available.\" Do not estimate.\n\n### 5. Financial Summary (3-Year)\nDense single table using actual fiscal year labels.\n\n| Metric ($M) | FY20XX | FY20XX | FY20XX |\n|---|---|---|---|\n| Revenue | | | |\n| Revenue Growth % | | | |\n| Gross Margin % | | | |\n| EBITDA | | | |\n| EBITDA Margin % | | | |\n| Net Income | | | |\n| EPS (Diluted) | | | |\n| Free Cash Flow | | | |\n| Net Debt | | | |\n\nCompute derived metrics (growth %, margins) from raw data rather than querying separately.\n\n**Capital Structure (separate compact sub-table below the Financial Summary):**\nDo NOT append these rows to the 3-year Financial Summary table — blank cells in prior-year columns look like missing data. Instead, render as a separate 2-column sub-table (Metric | Value) directly below, showing only the most recent fiscal year:\n\n| Metric | FY[latest] |\n|---|---|\n| Total Debt | $XXM |\n| Cash \u0026 Equivalents | $XXM |\n| Net Debt | $XXM |\n\nThis matches the capital structure format used in Corp Dev and IB/M\u0026A tear sheets. Keep it tight — no extra spacing between the Financial Summary and this sub-table.\n\n### 6. Revenue \u0026 Segment Breakdown\nIf segment data is available from the tools, include a compact segment revenue table. This is essential context for equity research — analysts need to see which business lines are driving growth.\n\n| Segment | Revenue ($M) | % of Total | YoY Growth |\n|---|---|---|---|\n| [Segment A] | | | |\n| [Segment B] | | | |\n\nKeep this compact for the one-pager: table only, no qualitative paragraph. If segment data is unavailable, skip this section entirely — do not include a blank or placeholder table.\n\n### 7. Recent Earnings Highlights\nInclude the quarter and date (e.g., \"Q3 FY2025 — October 2025\"). 3-4 bullets with an **investment lens** — this audience wants segment-level specifics, not strategic themes:\n\n**Lead with guidance if provided.** If management issued forward guidance, make it the first bullet with a bold **Guidance:** prefix (e.g., \"**Guidance:** FY2026 EPS of $19.40–$19.65, implying 9–10% growth; organic revenue growth of 6–8%.\"). Guidance is the single most actionable forward-looking data point for an analyst — do not bury it among operating highlights.\n\n**Beat/miss context (data permitting):** If consensus estimate data is available for the reported period, frame the headline result bullet as a beat/miss: \"Revenue of $X beat/missed consensus of $Y by Z%.\" If consensus data for the reported period is not available from the tools, describe results in absolute terms and growth rates only — do not fabricate consensus figures.\n\nThen:\n- Segment-level performance: which business lines accelerated or decelerated\n- Margin trajectory: any commentary on cost structure or profitability trends\n\nAttribute to management: \"Management highlighted…\" or \"CFO noted…\" rather than declarative claims. This section should feel like an earnings recap, not a press release summary.\n\n### 8. Key Operating Metrics\n2-3 sector-relevant KPIs if available from the data (subscriber count, same-store sales, NIM, etc.). If nothing sector-specific, compute ROE and ROIC from the financials already retrieved. Optional — drop if space is tight.\n\n### 9. Stock Performance (cut first)\nPeriod return table. Low analytical value for this audience — cut this before anything else.\n\n| Period | Return |\n|---|---|\n| 1 Month | |\n| 3 Month | |\n| YTD | |\n| 1 Year | |\n\n## Formatting Notes\n- **This is the densest tear sheet type.** It should feel noticeably more compressed than the other templates.\n- Financial Summary table: 8pt text (size: 16), row height 240 DXA. Tightest spacing of any template.\n- Valuation Snapshot and Consensus Estimates: 8.5pt text, occupy the visual center — analysts scan these first.\n- Body text: 8.5pt (size: 17) — smaller than the global 9pt default. Every half-point matters on a one-pager.\n- Section spacing: minimize. 6pt before section headers (not the global 12pt), 2pt after rules.\n- Bold any metric showing a notable inflection (growth turning positive, margin expansion/compression).\n- Prioritize information over whitespace at every turn.\n","references/ib-ma.md":"# Investment Banking / M\u0026A Tear Sheet\n\n## Purpose\nA company profile for transaction context — potential target, acquirer, or pitchbook inclusion. Emphasis on strategic positioning, segment detail, business relationships, and M\u0026A activity. Valuation framed in transaction multiples, not investment thesis.\n\n**Default page length:** 1-2 pages. IB company profiles routinely spill to a second page, especially when segment and M\u0026A data is rich.\n\n## Query Plan\n\nStart with these queries. Break apart and follow up if results are incomplete.\n\n**Query 1 — Profile + identification:**\n\"[Company] business description headquarters founded employees sector industry ownership structure major shareholders\"\n→ Header, Business Overview\n→ **Immediately write** to `/tmp/tear-sheet/company-profile.txt`\n\n**Query 2 — Segments + financials:**\n\"[Company] revenue by segment business unit last 2 fiscal years AND annual income statement revenue gross profit EBITDA operating income net income capex free cash flow total debt cash and equivalents last 4 fiscal years\"\n→ Segment Breakdown (need 2 years to compute YoY growth), Financial Summary (pull 4 years; display 3; use the earliest year only for YoY growth computation)\n→ **Immediately write** raw financials to `/tmp/tear-sheet/financials.csv`\n→ **Immediately write** segment data to `/tmp/tear-sheet/segments.csv` (skip if no segment data returned)\n\n**Query 3 — Valuation + comps:**\nIf the user provided specific comparable companies, query each:\n\"[Comp company] enterprise value EV/Revenue EV/EBITDA revenue growth EBITDA margin\"\nOtherwise:\nUse the competitors tool to identify 3-5 public peers, then pull EV/Revenue (NTM), EV/EBITDA (NTM), revenue growth %, and EBITDA margin % for each.\nAlso: \"[Company] enterprise value market capitalization EV/Revenue EV/EBITDA valuation multiples\"\n→ Header (EV/market cap), Trading Comps\n→ **Immediately write** company multiples to `/tmp/tear-sheet/valuation.csv`\n→ **Immediately write** peer data to `/tmp/tear-sheet/peer-comps.csv`\n\n**Query 4 — M\u0026A activity:**\n\"[Company] acquisitions divestitures completed transactions last 5 years deal value\"\n→ Company's own deals\n→ **Immediately write** to `/tmp/tear-sheet/ma-activity.csv`\n\n**Query 5 — Comparable transactions (data permitting):**\nUse the specific industry from Query 1 results (e.g., \"cloud observability software M\u0026A transactions\" not \"technology M\u0026A\"). If the user specified comps, also try: \"[comp company] acquisition deal multiples.\"\n→ Comparable Transactions\n→ **Append** comparable transactions to `/tmp/tear-sheet/ma-activity.csv` (add `type=precedent` to distinguish from company's own deals)\n\n**Query 6 — Relationships + ownership:**\n\"[Company] key customers suppliers partners business relationships institutional ownership insider ownership\"\n→ Business Relationships, Ownership (data permitting)\n→ **Immediately write** to `/tmp/tear-sheet/relationships.txt`\n\n## Sections\n\nListed in priority order. See \"Page Budget \u0026 Cut Order\" below for explicit cut guidance.\n\n### 1. Company Header\nKey-value block with transaction-relevant identifiers.\n\n| Field | Notes |\n|---|---|\n| Company name | Large, bold |\n| Ticker \u0026 Exchange | If public; omit for private |\n| HQ Location | City, State/Country |\n| Founded | Year |\n| Employees | Approximate headcount |\n| Market Cap / Valuation | Market cap if public; latest known valuation if private |\n| Enterprise Value | |\n| Ownership | Public / PE-backed (name sponsor) / Family / Other |\n\nFor private companies: note \"Private Company\" prominently; skip ticker, exchange.\n\n### 2. Business Overview\n**This is a pitchbook paragraph, not a CIQ summary.** Do not paste the company description from the data tools. Rewrite in 4-6 sentences using pitchbook prose:\n- Characterize the revenue model (recurring vs. transactional, subscription vs. license)\n- Name the customer base at scale (\"serves 80% of Fortune 500 banks\")\n- Identify competitive moats by name (\"proprietary dataset of X\", \"only provider with Y\")\n- Frame growth vectors that would matter to a buyer or seller\n\nThe tone should be confident and specific. A banker reading this paragraph should immediately understand the company's strategic positioning.\n\n### 3. Revenue \u0026 Segment Breakdown\nRevenue by business unit or product line.\n\n| Segment | Revenue ($M) | % of Total | YoY Growth |\n|---|---|---|---|\n| [Segment A] | | | |\n| [Segment B] | | | |\n| **Total** | | **100%** | |\n\n**If segment data isn't available:** Replace the table with 2-3 sentences describing the revenue mix qualitatively (e.g., \"Revenue is primarily derived from subscription licenses (~70%) and professional services (~30%).\"). A blank table looks broken — a qualitative description still conveys useful information.\n\n### 4. Financial Summary (3-Year + LTM)\nActual fiscal years as column headers. **If LTM (last twelve months) data is available, add an LTM column to the right of the most recent fiscal year.** Label it \"LTM [quarter end date]\" (e.g., \"LTM Q3 2025\"). Bankers work off LTM for valuation cross-checks — a fiscal-year-only view can be 6+ months stale.\n\n| Metric ($M) | FY20XX | FY20XX | FY20XX | LTM [date] |\n|---|---|---|---|---|\n| Revenue | | | | |\n| Revenue Growth % | | | | |\n| Gross Profit | | | | |\n| Gross Margin % | | | | |\n| EBITDA | | | | |\n| EBITDA Margin % | | | | |\n| Operating Income | | | | |\n| Net Income | | | | |\n| Capex | | | | |\n| Free Cash Flow | | | | |\n| FCF Margin % | | | | |\n\nIn M\u0026A context, margins and FCF conversion matter as much as absolute scale — a buyer is evaluating efficiency and cash generation potential.\n\n**Capital Structure** (compact sub-table below the financial summary):\n\n| Metric | Value |\n|---|---|\n| Total Debt | $XXM |\n| Cash \u0026 Equivalents | $XXM |\n| Net Debt | $XXM |\n| Net Debt / EBITDA | X.Xx |\n| S\u0026P Credit Rating | XX (if available) |\n\nPull from the balance sheet data already retrieved. This is standard in any banker's company profile — total debt, leverage ratio, and credit rating tell a buyer what the financing picture looks like. If credit rating is unavailable, omit that row.\n\n### 5. Trading Comps\nCompany multiples **and operating metrics** — bankers use these together, not multiples in isolation.\n\n**Forward multiples are mandatory when available.** The table must include NTM multiples if the tools return them. Showing only trailing multiples when forward data exists is a significant gap — bankers price deals on forward earnings.\n\n**Peer columns are expected.** If the user provided comps, each gets its own column. If not, use the competitors tool to identify 3-5 public peers, pull their multiples and operating metrics, and include them. A company-only trading comps table without peer context is incomplete for any banking use case.\n\n| Metric | [Company] | [Comp 1] | [Comp 2] | [Comp 3] | Peer Median |\n|---|---|---|---|---|---|\n| EV/Revenue (NTM) | | | | | |\n| EV/EBITDA (NTM) | | | | | |\n| Revenue Growth % | | | | | |\n| EBITDA Margin % | | | | | |\n\nIf only the company's own multiples are available after attempting peer queries, show those and list selected peer names below the table.\n\nFor private companies, skip this section.\n\n### 6. M\u0026A Activity\nTwo parts. **Deal values are expected in this section** — bankers notice when they're missing.\n\n**Hard rule: If the M\u0026A tools return a transaction value, it must appear in the output.** Never downgrade a known deal value to \"Undisclosed\" — this is a data integrity violation. Use \"Undisclosed\" only when the tools genuinely return no value for a transaction.\n\n**a) Company's Own Transactions:**\n\n**The table must include a dedicated Deal Value column.** Do not merge deal values into a Notes or Rationale column — bankers scan for numbers, and a dedicated column enables that.\n\n| Date | Target / Divested | Deal Value ($M) | Type | Rationale |\n|---|---|---|---|---|\n| | | | Acquisition / Divestiture | |\n\nIf none found: \"No disclosed transactions in the last 5 years.\"\n\n**b) Comparable Sector Transactions (data permitting):**\nUse the specific industry identified earlier (e.g., \"cloud infrastructure software M\u0026A\" not \"technology M\u0026A\"). If the user specified comps, also look for transactions involving those specific companies.\n\n| Date | Target | Acquirer | EV ($M) | EV/Rev | EV/EBITDA |\n|---|---|---|---|---|---|\n\nIf not available from the tools: \"Comparable transaction data not available from data source.\" Do not fabricate precedent multiples.\n\n### 7. Key Business Relationships\nLeverages S\u0026P Capital IQ relationship data. Group by type:\n\n**Customers:** Top 3-5 named clients\n**Suppliers:** Key vendors and technology providers\n**Partners:** Strategic alliances, distribution, JVs\n**Competitors:** Key competitive names\n\nFor each entry, include the relationship type and a parenthetical descriptor explaining the nature of the relationship (e.g., \"AWS — cloud infrastructure (primary hosting provider)\", \"JPMorgan — customer (enterprise analytics platform)\"). A name alone without context isn't useful. Give this section breathing room — it's strategically valuable and most competing tear sheets lack it.\n\n### 8. Ownership Snapshot (data permitting — omit if tools return nothing)\nIf the tools return institutional ownership, insider ownership percentage, or top holders, include a compact block:\n\nTop institutional holders (if available): list top 3-5 by ownership %.\nInsider ownership: aggregate percentage.\n\nFor PE-backed companies, name the sponsor, acquisition year, and ownership stake. Ownership structure directly affects deal complexity — a widely held public company, a founder-controlled company, and a PE-backed company each require fundamentally different deal approaches.\n\nIf ownership data is not returned by the tools, omit this section entirely rather than showing placeholders.\n\n**Do not include a Management Team table.** No S\u0026P Global tool returns executive data — see Data Integrity Rule 10. Management names from training data will be stale.\n\n## Page Budget \u0026 Cut Order\n\n**Target: 2 pages maximum.** IB profiles can use both pages fully, but must not spill to a third. If content exceeds 2 pages, cut in this order (cut each completely before moving to the next):\n\n1. Ownership Snapshot (section 8) — omit entirely\n2. Comparable Sector Transactions (section 6b) — keep company's own M\u0026A, cut precedents\n3. Business Relationships (section 7) — compress to top 3 competitors + top 2 each of suppliers/partners/customers, drop descriptors to parenthetical only\n4. Capital Structure (section 4) — merge Net Debt/EBITDA into Financial Summary as a single row\n5. Trading Comparables (section 5) — reduce to 3 peers\n\nNever cut: Business Overview (2), Revenue \u0026 Segment Breakdown (3), Financial Summary (4 core), M\u0026A Activity company transactions (6a).\n\n## Formatting Notes\n- Business Overview and Segment Breakdown get the most visual weight.\n- **M\u0026A Activity is the signature section:** Use Accent color (#2E75B6) fill with white bold text for M\u0026A table headers — this is the only table that uses a different header color from the standard #D6E4F0. It should catch the eye on a scan.\n- **Business Relationships: give breathing room when space permits.** 6pt between each relationship group, full descriptors on each entry. But if hitting page 3, compress per the cut order above — this section is high-value but also the most compressible.\n- For private companies, the header, business overview, financials, and relationships form the core; other sections may be sparse.\n- **Two-page discipline:** Before rendering, mentally estimate page count. If Business Relationships + M\u0026A Activity together will exceed one full page, start cutting per the cut order.\n","references/sales-bd.md":"# Sales / Business Development Tear Sheet\n\n## Purpose\nA briefing document to prepare a sales or BD team for a client meeting. Emphasis on understanding the prospect's business, what leadership is publicly prioritizing, and identifying angles to connect your product/service to their needs. Financials are simplified to scale and trajectory.\n\nThis is the most narrative-driven tear sheet type. It reads like a briefing memo, not a data sheet.\n\n**Default page length:** 1-2 pages. No strict convention — prioritize readability over compression.\n\n## Query Plan\n\nStart with these queries. Follow up if results are incomplete.\n\n**Query 1 — Company profile + financials:**\n\"[Company] business description overview products services headquarters employees sector industry revenue gross margin last 2 fiscal years\"\n→ Header, Company Overview, Financial Snapshot\n→ **Immediately write** to `/tmp/tear-sheet/company-profile.txt`\n→ **Immediately write** raw financials to `/tmp/tear-sheet/financials.csv`\n\n**Query 2 — Strategy + earnings:**\n\"[Company] most recent earnings call strategic priorities CEO commentary guidance key initiatives\"\n→ Strategic Priorities\n→ **Immediately write** to `/tmp/tear-sheet/earnings.txt`\n\n**Query 3 — Relationships + news:**\n\"[Company] key customers suppliers partners competitors business relationships recent acquisitions partnerships announcements\"\n→ Key Relationships, Recent News\n→ **Immediately write** to `/tmp/tear-sheet/relationships.txt`\n\nThree queries is usually sufficient. For well-known companies, these return rich results. For smaller or private companies, Queries 2 and 3 may be sparse — that's fine. The qualitative sections still deliver value because Claude synthesizes whatever is available into useful framing.\n\n## Sections\n\nListed in priority order. Cut from the bottom if space is constrained.\n\n### 1. Company Header\nStreamlined — identification only, no valuation metrics.\n\n| Field | Notes |\n|---|---|\n| Company name | Large, bold |\n| Ticker \u0026 Exchange | If public; omit for private |\n| HQ | City, State/Country |\n| Industry / Sector | |\n| Employees | |\n| Annual Revenue (latest) | Round to nearest $B or $M |\n| Market Cap | If public; omit for private |\n| FY Revenue Guidance | If available from earnings data; e.g., \"6–8% organic growth\" |\n| FY EPS or EPS Guidance | If public company; pull from `earnings.txt` |\n| Key Financial Metric | Adj. EPS, EBITDA margin, or similar — one headline number |\n\nForward guidance and EPS data come from Query 2 (earnings) — source from `earnings.txt` when populating the header, not just `company-profile.txt`.\n\nOne horizontal band at the top. No enterprise value, no beta — this audience doesn't need them.\n\n### 2. Company Overview\nThe most important section. A sales rep should read this and walk into a meeting with a solid grasp of the prospect.\n\n**Do not paste the CIQ company summary.** It reads like an SEC filing and will lose a non-finance audience. Rewrite in 3-5 sentences of plain language:\n- What the company does (no investor jargon — say \"sells\" not \"monetizes\", say \"yearly revenue\" not \"top-line CAGR\")\n- Who their customers are\n- How they make money\n- Where they operate\n- What makes them distinctive\n\nWrite in prose paragraphs. A non-finance person should understand every sentence.\n\n### 3. Strategic Priorities \u0026 Management Commentary\nWhat is leadership focused on right now? If you know what the CEO is talking about, you can align your pitch.\n\n**This is NOT an earnings recap.** Do not reuse the same bullets as the equity research tear sheet. Extract 3-5 *strategic themes* with thematic labels and supporting data points:\n\n- **AI/Data Monetization:** Management is investing aggressively in AI capabilities, allocating $X to R\u0026D in FY2024 and launching three new AI-powered products.\n- **Margin Expansion:** CEO cited operational efficiency as a top priority, targeting 200bps of operating margin improvement through automation.\n- **International Growth:** Opening new offices in EMEA; Europe now represents 25% of revenue, up from 18%.\n\nEach bullet should answer: \"What does this company care about right now, and what evidence supports it?\" A sales rep should read these and immediately see angles to connect their product.\n\nIf earnings call data isn't available (common for private companies), replace with \"Recent Developments\" pulling from whatever news or announcements the tools return.\n\n### 4. Financial Snapshot\nSimplified. Single compact table — just scale, direction, and one profitability signal. A sales rep needs to know three things: how big is this company, is it growing, and is it healthy.\n\n| Metric | FY[prior year] | FY[latest] | YoY Change |\n|---|---|---|---|\n| Revenue | | | +X% |\n| Gross Margin % | | | +X.Xpp |\n| Employees | | | |\n\nThree rows maximum. No EBITDA, no EV multiples, no balance sheet, no net income. Gross margin (not EBITDA, not net income) is the right single profitability metric for a sales audience — it's intuitive (\"how much they keep after direct costs\") and signals business health without requiring finance literacy. If the rep needs deeper financials, they can request the equity research version.\n\nFor private companies, this table may have only revenue and employees — two data points showing scale and growth are enough for a sales meeting.\n\n### 5. Key Relationships \u0026 Ecosystem\nHelps reps understand the prospect's world and identify angles.\n\nFour labeled lists, 3-5 names each with one-line descriptors:\n\n**Customers:** Who they sell to. Helps understand their go-to-market and shared target customers.\nExample: \"JPMorgan Chase — customer (enterprise analytics platform deployment)\"\n\n**Vendors / Technology:** What they buy. Identifies displacement or integration opportunities.\nExample: \"AWS — vendor (primary cloud infrastructure); Snowflake — vendor (data warehouse)\"\n\n**Partners:** Who they work with. Co-sell angles, mutual connections.\nExample: \"Deloitte — partner (implementation for enterprise clients)\"\n\n**Competitors:** Who they compete against. Positioning context.\nExample: \"Bloomberg — competitor (financial data terminal)\"\n\nEvery entry needs a parenthetical descriptor so the rep understands *what* the relationship means, not just *who*.\n\nIf relationship data isn't available, note \"Relationship data not available\" and move on.\n\n### 6. Recent News \u0026 Developments\n3-5 bullets, each one sentence, most recent first. Include date if available. **Lead with the latest earnings report** — it's the most important recent event for a sales meeting and sets the context for everything else. Then: M\u0026A, product launches, leadership changes, major wins.\n\n**Include upcoming catalysts at the end of the section** with a \"**Coming Up:**\" label. Examples: upcoming earnings dates, pending divestitures, product launches, investor days, regulatory milestones. These create natural engagement windows for sales outreach and are often the best reason to reach out (\"I noticed you have your Investor Day coming up in Q2...\"). Pull from earnings call commentary and M\u0026A data (pending transactions).\n\n### 7. Conversation Starters (cut first)\n2-3 suggested talking points synthesized from the data above. **Each starter must reference a specific strategic priority from Section 3** — generic questions are useless. Frame as questions.\n\n**Tag each starter with a suggested persona** — e.g., (CTO), (CFO), (CDO), (Head of Data), (VP Engineering), (Head of Procurement). A rep meeting with a CTO needs a different opener than one meeting with a CFO. If the user specified who they're meeting with, generate starters for that persona only.\n\nExamples:\n- *(CTO/CDO)* \"You mentioned [specific AI initiative from Section 3] on your last earnings call — how is that impacting your [relevant need]?\"\n- *(CFO/COO)* \"With your [margin expansion target from Section 3], are you evaluating tools that could accelerate that timeline?\"\n- *(VP Strategy/Corp Dev)* \"I noticed [Company] recently acquired [target] — does that change your approach to [capability]?\"\n\nIf the user described what product/service they're selling, tailor these to connect the prospect's priorities to that offering. If not, keep them grounded in the prospect's strategic themes but generic in solution framing.\n\n**Validation test:** Before finalizing each conversation starter, verify it contains at least one specific number, date, product name, or initiative name drawn from the tear sheet. A question that could apply to any company in the sector is not a good conversation starter. \"How are you thinking about AI?\" is generic. \"Your CEO mentioned $1B in AI investment since 2018 and 20% adoption of the iLEVEL auto-ingestion feature — how is that changing your analysts' workflows?\" is specific and demonstrates preparation.\n\nThis section is Claude's synthesis, not raw data from the tools. Label it clearly.\n\n## Formatting Notes\n- **This should be the warmest, most readable tear sheet.** Rigorous content, but the formatting should feel like a briefing memo, not a data terminal.\n- Body text: use the full 9pt (size: 18). No compression — readability over density.\n- Line spacing: 1.15x on body paragraphs (slightly more generous than default). This template is the one where whitespace is a feature, not waste.\n- Company Overview and Strategic Priorities should take ~40-50% of the page.\n- Financial Snapshot: visually compact, secondary prominence. Keep it small and clean.\n- Key Relationships: consider two-column layout (Customers + Vendors on left, Partners + Competitors on right) to save vertical space while keeping descriptors visible.\n- Conversation Starters: use the indented block-style bullets. These are the payoff of the document — they should stand out visually.\n"},"import":{"commit_sha":"9affc6e683bbaf66361058117027cf5a50bf1861","imported_at":"2026-05-18T20:09:40Z","license_text":"\n                                 Apache License\n                           Version 2.0, January 2004\n                        http://www.apache.org/licenses/\n\n   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n   1. Definitions.\n\n      \"License\" shall mean the terms and conditions for use, reproduction,\n      and distribution as defined by Sections 1 through 9 of this document.\n\n      \"Licensor\" shall mean the copyright owner or entity authorized by\n      the copyright owner that is granting the License.\n\n      \"Legal Entity\" shall mean the union of the acting entity and all\n      other entities that control, are controlled by, or are under common\n      control with that entity. For the purposes of this definition,\n      \"control\" means (i) the power, direct or indirect, to cause the\n      direction or management of such entity, whether by contract or\n      otherwise, or (ii) ownership of fifty percent (50%) or more of the\n      outstanding shares, or (iii) beneficial ownership of such entity.\n\n      \"You\" (or \"Your\") shall mean an individual or Legal Entity\n      exercising permissions granted by this License.\n\n      \"Source\" form shall mean the preferred form for making modifications,\n      including but not limited to software source code, documentation\n      source, and configuration files.\n\n      \"Object\" form shall mean any form resulting from mechanical\n      transformation or translation of a Source form, including but\n      not limited to compiled object code, generated documentation,\n      and conversions to other media types.\n\n      \"Work\" shall mean the work of authorship, whether in Source or\n      Object form, made available under the License, as indicated by a\n      copyright notice that is included in or attached to the work\n      (an example is provided in the Appendix below).\n\n      \"Derivative Works\" shall mean any work, whether in Source or Object\n      form, that is based on (or derived from) the Work and for which the\n      editorial revisions, annotations, elaborations, or other modifications\n      represent, as a whole, an original work of authorship. For the purposes\n      of this License, Derivative Works shall not include works that remain\n      separable from, or merely link (or bind by name) to the interfaces of,\n      the Work and Derivative Works thereof.\n\n      \"Contribution\" shall mean any work of authorship, including\n      the original version of the Work and any modifications or additions\n      to that Work or Derivative Works thereof, that is intentionally\n      submitted to Licensor for inclusion in the Work by the copyright owner\n      or by an individual or Legal Entity authorized to submit on behalf of\n      the copyright owner. For the purposes of this definition, \"submitted\"\n      means any form of electronic, verbal, or written communication sent\n      to the Licensor or its representatives, including but not limited to\n      communication on electronic mailing lists, source code control systems,\n      and issue tracking systems that are managed by, or on behalf of, the\n      Licensor for the purpose of discussing and improving the Work, but\n      excluding communication that is conspicuously marked or otherwise\n      designated in writing by the copyright owner as \"Not a Contribution.\"\n\n      \"Contributor\" shall mean Licensor and any individual or Legal Entity\n      on behalf of whom a Contribution has been received by Licensor and\n      subsequently incorporated within the Work.\n\n   2. Grant of Copyright License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n      copyright license to reproduce, prepare Derivative Works of,\n      publicly display, publicly perform, sublicense, and distribute the\n      Work and such Derivative Works in Source or Object form.\n\n   3. Grant of Patent License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n      (except as stated in this section) patent license to make, have made,\n      use, offer to sell, sell, import, and otherwise transfer the Work,\n      where such license applies only to those patent claims licensable\n      by such Contributor that are necessarily infringed by their\n      Contribution(s) alone or by combination of their Contribution(s)\n      with the Work to which such Contribution(s) was submitted. If You\n      institute patent litigation against any entity (including a\n      cross-claim or counterclaim in a lawsuit) alleging that the Work\n      or a Contribution incorporated within the Work constitutes direct\n      or contributory patent infringement, then any patent licenses\n      granted to You under this License for that Work shall terminate\n      as of the date such litigation is filed.\n\n   4. Redistribution. You may reproduce and distribute copies of the\n      Work or Derivative Works thereof in any medium, with or without\n      modifications, and in Source or Object form, provided that You\n      meet the following conditions:\n\n      (a) You must give any other recipients of the Work or\n          Derivative Works a copy of this License; and\n\n      (b) You must cause any modified files to carry prominent notices\n          stating that You changed the files; and\n\n      (c) You must retain, in the Source form of any Derivative Works\n          that You distribute, all copyright, patent, trademark, and\n          attribution notices from the Source form of the Work,\n          excluding those notices that do not pertain to any part of\n          the Derivative Works; and\n\n      (d) If the Work includes a \"NOTICE\" text file as part of its\n          distribution, then any Derivative Works that You distribute must\n          include a readable copy of the attribution notices contained\n          within such NOTICE file, excluding those notices that do not\n          pertain to any part of the Derivative Works, in at least one\n          of the following places: within a NOTICE text file distributed\n          as part of the Derivative Works; within the Source form or\n          documentation, if provided along with the Derivative Works; or,\n          within a display generated by the Derivative Works, if and\n          wherever such third-party notices normally appear. The contents\n          of the NOTICE file are for informational purposes only and\n          do not modify the License. You may add Your own attribution\n          notices within Derivative Works that You distribute, alongside\n          or as an addendum to the NOTICE text from the Work, provided\n          that such additional attribution notices cannot be construed\n          as modifying the License.\n\n      You may add Your own copyright statement to Your modifications and\n      may provide additional or different license terms and conditions\n      for use, reproduction, or distribution of Your modifications, or\n      for any such Derivative Works as a whole, provided Your use,\n      reproduction, and distribution of the Work otherwise complies with\n      the conditions stated in this License.\n\n   5. Submission of Contributions. Unless You explicitly state otherwise,\n      any Contribution intentionally submitted for inclusion in the Work\n      by You to the Licensor shall be under the terms and conditions of\n      this License, without any additional terms or conditions.\n      Notwithstanding the above, nothing herein shall supersede or modify\n      the terms of any separate license agreement you may have executed\n      with Licensor regarding such Contributions.\n\n   6. Trademarks. This License does not grant permission to use the trade\n      names, trademarks, service marks, or product names of the Licensor,\n      except as required for reasonable and customary use in describing the\n      origin of the Work and reproducing the content of the NOTICE file.\n\n   7. Disclaimer of Warranty. Unless required by applicable law or\n      agreed to in writing, Licensor provides the Work (and each\n      Contributor provides its Contributions) on an \"AS IS\" BASIS,\n      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n      implied, including, without limitation, any warranties or conditions\n      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n      PARTICULAR PURPOSE. You are solely responsible for determining the\n      appropriateness of using or redistributing the Work and assume any\n      risks associated with Your exercise of permissions under this License.\n\n   8. Limitation of Liability. In no event and under no legal theory,\n      whether in tort (including negligence), contract, or otherwise,\n      unless required by applicable law (such as deliberate and grossly\n      negligent acts) or agreed to in writing, shall any Contributor be\n      liable to You for damages, including any direct, indirect, special,\n      incidental, or consequential damages of any character arising as a\n      result of this License or out of the use or inability to use the\n      Work (including but not limited to damages for loss of goodwill,\n      work stoppage, computer failure or malfunction, or any and all\n      other commercial damages or losses), even if such Contributor\n      has been advised of the possibility of such damages.\n\n   9. Accepting Warranty or Additional Liability. While redistributing\n      the Work or Derivative Works thereof, You may choose to offer,\n      and charge a fee for, acceptance of support, warranty, indemnity,\n      or other liability obligations and/or rights consistent with this\n      License. However, in accepting such obligations, You may act only\n      on Your own behalf and on Your sole responsibility, not on behalf\n      of any other Contributor, and only if You agree to indemnify,\n      defend, and hold each Contributor harmless for any liability\n      incurred by, or claims asserted against, such Contributor by reason\n      of your accepting any such warranty or additional liability.\n\n   END OF TERMS AND CONDITIONS\n\n   APPENDIX: How to apply the Apache License to your work.\n\n      To apply the Apache License to your work, attach the following\n      boilerplate notice, with the fields enclosed by brackets \"[]\"\n      replaced with your own identifying information. (Don't include\n      the brackets!)  The text should be enclosed in the appropriate\n      comment syntax for the file format. We also recommend that a\n      file or class name and description of purpose be included on the\n      same \"printed page\" as the copyright notice for easier\n      identification within third-party archives.\n\n   Copyright 2026-present Kensho Technologies, LLC.\n\n   Licensed under the Apache License, Version 2.0 (the \"License\");\n   you may not use this file except in compliance with the License.\n   You may obtain a copy of the License at\n\n       http://www.apache.org/licenses/LICENSE-2.0\n\n   Unless required by applicable law or agreed to in writing, software\n   distributed under the License is distributed on an \"AS IS\" BASIS,\n   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n   See the License for the specific language governing permissions and\n   limitations under the License.","owner":"anthropics","repo":"anthropics/financial-services","source_url":"https://github.com/anthropics/financial-services/tree/9affc6e683bbaf66361058117027cf5a50bf1861/plugins/partner-built/spglobal/skills/tear-sheet"}},"content_hash":[127,130,72,12,110,106,52,71,130,241,216,174,72,14,135,247,3,138,33,149,54,251,87,239,136,230,96,239,167,160,39,131],"trust_level":"unsigned","yanked":false}