[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-ai-readiness":3,"mdc-yh2bid-key":36,"related-repo-anthropic-ai-readiness":663,"related-org-anthropic-ai-readiness":767},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":34,"mdContent":35},"ai-readiness","identify AI opportunities in portfolio companies","Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual planning, or when deciding which companies get AI investment first. Triggers on \"AI readiness\", \"AI opportunity scan\", \"where should we deploy AI\", \"AI across the portfolio\", \"AI quick wins\", or \"which portcos are ready for AI\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20,23],{"name":14,"slug":15,"type":16},"Operations","operations","tag",{"name":18,"slug":19,"type":16},"Strategy","strategy",{"name":21,"slug":22,"type":16},"AI Infrastructure","ai-infrastructure",{"name":24,"slug":25,"type":16},"Private Equity","private-equity",33636,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services","2026-05-21T06:50:36.056814",null,4964,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services\u002Ftree\u002FHEAD\u002Fplugins\u002Fvertical-plugins\u002Fprivate-equity\u002Fskills\u002Fai-readiness","---\nname: ai-readiness\ndescription: Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual planning, or when deciding which companies get AI investment first. Triggers on \"AI readiness\", \"AI opportunity scan\", \"where should we deploy AI\", \"AI across the portfolio\", \"AI quick wins\", or \"which portcos are ready for AI\".\n---\n\n# Portfolio AI Readiness\n\n## Workflow\n\n### Step 1: Connect to Portfolio Data\n\nFirst, ask the user where the portfolio materials live. Don't assume — offer the options:\n\n- **MCP servers** — data room, SharePoint, Google Drive, or a portfolio-ops database if one is connected\n- **Local files** — a folder path on disk with quarterly decks, financials, board packs\n- **File uploads** — drag PDFs, PowerPoint, or Excel directly into the conversation\n\nOnce connected, pull quarterly updates, board decks, and financials for the portfolio (or a subset). For each company, extract: sector, revenue, headcount by function, tech stack mentioned, and any AI\u002Fautomation initiatives already in flight.\n\nIf the user provides a single company, still run the scan but skip the cross-portfolio ranking.\n\nAsk up front if not obvious from materials:\n- Hold period remaining per company (AI payback matters less 12 months from exit)\n- Whether any portco has already deployed something that worked\n\n### Step 2: Per-Company Scan\n\nFor each company, answer three gate questions. All three yes → **Go**. Any no → **Wait** with a note on what unblocks it.\n\n1. **Is the data there?** Can they produce a clean input for the use case — customer list, invoice feed, contract repository — without a 6-month data project first?\n2. **Is there an owner?** Someone on the management team who will drive this, not a sponsor who will \"support\" it.\n3. **Can we pilot in 30 days?** One team, one workflow, off-the-shelf tooling. If the answer starts with \"first we'd need to...\", it's not a quick win.\n\nThen identify the top 2-3 leverage points. Look for these patterns in the cost structure and operations:\n\n**Back Office (usually fastest to pilot)**\n- Invoice processing, AP\u002FAR matching, expense categorization\n- Contract abstraction — vendor agreements, leases, customer MSAs\n- Month-end close: reconciliations, flux commentary, lender reporting first drafts\n\n**Revenue \u002F Front Office**\n- RFP and proposal first drafts — big lever if revenue is project-based\n- Sales call summaries and CRM hygiene\n- Customer support ticket triage and first-response drafting\n- Quoting for configured \u002F complex products\n\n**Operations (sector-dependent)**\n- SOP and quality documentation generation\n- Scheduling and dispatch (field services, logistics)\n- Code generation and review (software portcos)\n\nFor each leverage point, capture in one line: what it replaces, FTE-hours\u002Fweek saved (assume 30-50%, not 100%), and whether it's buy-off-the-shelf or needs a light build.\n\n### Step 3: Rank Across the Portfolio\n\nStack every leverage point from every company into one list. Rank by:\n\n1. **Dollar impact** — annualized EBITDA contribution (cost out + revenue lift, net of tool cost)\n2. **Speed to value** — months to first measurable result\n3. **Probability** — discount for data quality, change management risk, management team capability\n\nTiebreaker: favor opportunities with \u003C18 months of hold period remaining — those need to move now or not at all.\n\nOutput the stack:\n\n| Rank | Company | Opportunity | Est. EBITDA ($) | Months to Value | Gate | First Step |\n|---|---|---|---|---|---|---|\n| 1 | | | | | Go | |\n| 2 | | | | | Go | |\n| 3 | | | | | Wait — [blocker] | |\n\n### Step 4: Find the Replays\n\nThe highest-leverage move in a portfolio is running one successful play at multiple companies. Scan for:\n\n- **Same sector, same function** — two healthcare services portcos with manual prior-auth? One implementation, two deployments.\n- **Same tool, different company** — if one portco already has a working invoice-processing setup, flag every other portco with >$Xm in AP volume as a fast follower.\n- **Shared vendor leverage** — three portcos buying the same tool is a pricing conversation.\n\nList each replay with the lead company (who proves it) and follower companies (who copy it).\n\n### Step 5: Output\n\nOne page for the operating partner, structured for a portfolio review:\n\n1. **Top 5 across the portfolio** — the ranked table from Step 3, with owner and 30-day first step\n2. **Replays** — 2-3 playbooks that hit multiple companies at once\n3. **Go \u002F Wait by company** — one line each; for Waits, what unblocks them\n4. **What we're NOT doing** — the opportunities that looked good on paper but failed a gate; saves the operating partner from relitigating them every quarter\n5. **Aggregate EBITDA contribution** — total portfolio-wide AI opportunity, split Year 1 quick wins vs. Years 2-3 scale\n\n## Important Notes\n\n- **Rank by dollars, not excitement.** A boring AP automation that saves $400k at a $40m revenue company beats a flashy customer-facing chatbot every time.\n- **The binding constraint is almost always data, not models.** If a company can't produce a clean customer list, AI isn't the first project — a data cleanup is. Say so plainly.\n- **Off-the-shelf first.** Custom builds are slow, expensive, and fragile for companies without engineering depth. Favor tools they can buy and deploy.\n- **Ownership is the real gate.** A quick win with no internal owner dies in 90 days. If no one on the management team wants it, mark it Wait regardless of the dollar size.\n- **Hold period drives urgency.** A company 3 years from exit can afford a foundational data project. A company 12 months out needs something that shows up in the LTM EBITDA for the CIM — or skip it.\n- **Failed pilots are signal.** If management already tried something and it didn't stick, find out why before proposing the same thing again.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,57,64,70,106,111,116,121,134,140,159,193,198,206,224,232,255,263,281,286,292,297,330,335,340,481,487,492,525,530,536,541,594,600],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"portfolio-ai-readiness",[47],{"type":48,"value":49},"text","Portfolio AI Readiness",{"type":42,"tag":51,"props":52,"children":54},"h2",{"id":53},"workflow",[55],{"type":48,"value":56},"Workflow",{"type":42,"tag":58,"props":59,"children":61},"h3",{"id":60},"step-1-connect-to-portfolio-data",[62],{"type":48,"value":63},"Step 1: Connect to Portfolio Data",{"type":42,"tag":65,"props":66,"children":67},"p",{},[68],{"type":48,"value":69},"First, ask the user where the portfolio materials live. Don't assume — offer the options:",{"type":42,"tag":71,"props":72,"children":73},"ul",{},[74,86,96],{"type":42,"tag":75,"props":76,"children":77},"li",{},[78,84],{"type":42,"tag":79,"props":80,"children":81},"strong",{},[82],{"type":48,"value":83},"MCP servers",{"type":48,"value":85}," — data room, SharePoint, Google Drive, or a portfolio-ops database if one is connected",{"type":42,"tag":75,"props":87,"children":88},{},[89,94],{"type":42,"tag":79,"props":90,"children":91},{},[92],{"type":48,"value":93},"Local files",{"type":48,"value":95}," — a folder path on disk with quarterly decks, financials, board packs",{"type":42,"tag":75,"props":97,"children":98},{},[99,104],{"type":42,"tag":79,"props":100,"children":101},{},[102],{"type":48,"value":103},"File uploads",{"type":48,"value":105}," — drag PDFs, PowerPoint, or Excel directly into the conversation",{"type":42,"tag":65,"props":107,"children":108},{},[109],{"type":48,"value":110},"Once connected, pull quarterly updates, board decks, and financials for the portfolio (or a subset). For each company, extract: sector, revenue, headcount by function, tech stack mentioned, and any AI\u002Fautomation initiatives already in flight.",{"type":42,"tag":65,"props":112,"children":113},{},[114],{"type":48,"value":115},"If the user provides a single company, still run the scan but skip the cross-portfolio ranking.",{"type":42,"tag":65,"props":117,"children":118},{},[119],{"type":48,"value":120},"Ask up front if not obvious from materials:",{"type":42,"tag":71,"props":122,"children":123},{},[124,129],{"type":42,"tag":75,"props":125,"children":126},{},[127],{"type":48,"value":128},"Hold period remaining per company (AI payback matters less 12 months from exit)",{"type":42,"tag":75,"props":130,"children":131},{},[132],{"type":48,"value":133},"Whether any portco has already deployed something that worked",{"type":42,"tag":58,"props":135,"children":137},{"id":136},"step-2-per-company-scan",[138],{"type":48,"value":139},"Step 2: Per-Company Scan",{"type":42,"tag":65,"props":141,"children":142},{},[143,145,150,152,157],{"type":48,"value":144},"For each company, answer three gate questions. All three yes → ",{"type":42,"tag":79,"props":146,"children":147},{},[148],{"type":48,"value":149},"Go",{"type":48,"value":151},". Any no → ",{"type":42,"tag":79,"props":153,"children":154},{},[155],{"type":48,"value":156},"Wait",{"type":48,"value":158}," with a note on what unblocks it.",{"type":42,"tag":160,"props":161,"children":162},"ol",{},[163,173,183],{"type":42,"tag":75,"props":164,"children":165},{},[166,171],{"type":42,"tag":79,"props":167,"children":168},{},[169],{"type":48,"value":170},"Is the data there?",{"type":48,"value":172}," Can they produce a clean input for the use case — customer list, invoice feed, contract repository — without a 6-month data project first?",{"type":42,"tag":75,"props":174,"children":175},{},[176,181],{"type":42,"tag":79,"props":177,"children":178},{},[179],{"type":48,"value":180},"Is there an owner?",{"type":48,"value":182}," Someone on the management team who will drive this, not a sponsor who will \"support\" it.",{"type":42,"tag":75,"props":184,"children":185},{},[186,191],{"type":42,"tag":79,"props":187,"children":188},{},[189],{"type":48,"value":190},"Can we pilot in 30 days?",{"type":48,"value":192}," One team, one workflow, off-the-shelf tooling. If the answer starts with \"first we'd need to...\", it's not a quick win.",{"type":42,"tag":65,"props":194,"children":195},{},[196],{"type":48,"value":197},"Then identify the top 2-3 leverage points. Look for these patterns in the cost structure and operations:",{"type":42,"tag":65,"props":199,"children":200},{},[201],{"type":42,"tag":79,"props":202,"children":203},{},[204],{"type":48,"value":205},"Back Office (usually fastest to pilot)",{"type":42,"tag":71,"props":207,"children":208},{},[209,214,219],{"type":42,"tag":75,"props":210,"children":211},{},[212],{"type":48,"value":213},"Invoice processing, AP\u002FAR matching, expense categorization",{"type":42,"tag":75,"props":215,"children":216},{},[217],{"type":48,"value":218},"Contract abstraction — vendor agreements, leases, customer MSAs",{"type":42,"tag":75,"props":220,"children":221},{},[222],{"type":48,"value":223},"Month-end close: reconciliations, flux commentary, lender reporting first drafts",{"type":42,"tag":65,"props":225,"children":226},{},[227],{"type":42,"tag":79,"props":228,"children":229},{},[230],{"type":48,"value":231},"Revenue \u002F Front Office",{"type":42,"tag":71,"props":233,"children":234},{},[235,240,245,250],{"type":42,"tag":75,"props":236,"children":237},{},[238],{"type":48,"value":239},"RFP and proposal first drafts — big lever if revenue is project-based",{"type":42,"tag":75,"props":241,"children":242},{},[243],{"type":48,"value":244},"Sales call summaries and CRM hygiene",{"type":42,"tag":75,"props":246,"children":247},{},[248],{"type":48,"value":249},"Customer support ticket triage and first-response drafting",{"type":42,"tag":75,"props":251,"children":252},{},[253],{"type":48,"value":254},"Quoting for configured \u002F complex products",{"type":42,"tag":65,"props":256,"children":257},{},[258],{"type":42,"tag":79,"props":259,"children":260},{},[261],{"type":48,"value":262},"Operations (sector-dependent)",{"type":42,"tag":71,"props":264,"children":265},{},[266,271,276],{"type":42,"tag":75,"props":267,"children":268},{},[269],{"type":48,"value":270},"SOP and quality documentation generation",{"type":42,"tag":75,"props":272,"children":273},{},[274],{"type":48,"value":275},"Scheduling and dispatch (field services, logistics)",{"type":42,"tag":75,"props":277,"children":278},{},[279],{"type":48,"value":280},"Code generation and review (software portcos)",{"type":42,"tag":65,"props":282,"children":283},{},[284],{"type":48,"value":285},"For each leverage point, capture in one line: what it replaces, FTE-hours\u002Fweek saved (assume 30-50%, not 100%), and whether it's buy-off-the-shelf or needs a light build.",{"type":42,"tag":58,"props":287,"children":289},{"id":288},"step-3-rank-across-the-portfolio",[290],{"type":48,"value":291},"Step 3: Rank Across the Portfolio",{"type":42,"tag":65,"props":293,"children":294},{},[295],{"type":48,"value":296},"Stack every leverage point from every company into one list. Rank by:",{"type":42,"tag":160,"props":298,"children":299},{},[300,310,320],{"type":42,"tag":75,"props":301,"children":302},{},[303,308],{"type":42,"tag":79,"props":304,"children":305},{},[306],{"type":48,"value":307},"Dollar impact",{"type":48,"value":309}," — annualized EBITDA contribution (cost out + revenue lift, net of tool cost)",{"type":42,"tag":75,"props":311,"children":312},{},[313,318],{"type":42,"tag":79,"props":314,"children":315},{},[316],{"type":48,"value":317},"Speed to value",{"type":48,"value":319}," — months to first measurable result",{"type":42,"tag":75,"props":321,"children":322},{},[323,328],{"type":42,"tag":79,"props":324,"children":325},{},[326],{"type":48,"value":327},"Probability",{"type":48,"value":329}," — discount for data quality, change management risk, management team capability",{"type":42,"tag":65,"props":331,"children":332},{},[333],{"type":48,"value":334},"Tiebreaker: favor opportunities with \u003C18 months of hold period remaining — those need to move now or not at all.",{"type":42,"tag":65,"props":336,"children":337},{},[338],{"type":48,"value":339},"Output the stack:",{"type":42,"tag":341,"props":342,"children":343},"table",{},[344,388],{"type":42,"tag":345,"props":346,"children":347},"thead",{},[348],{"type":42,"tag":349,"props":350,"children":351},"tr",{},[352,358,363,368,373,378,383],{"type":42,"tag":353,"props":354,"children":355},"th",{},[356],{"type":48,"value":357},"Rank",{"type":42,"tag":353,"props":359,"children":360},{},[361],{"type":48,"value":362},"Company",{"type":42,"tag":353,"props":364,"children":365},{},[366],{"type":48,"value":367},"Opportunity",{"type":42,"tag":353,"props":369,"children":370},{},[371],{"type":48,"value":372},"Est. EBITDA ($)",{"type":42,"tag":353,"props":374,"children":375},{},[376],{"type":48,"value":377},"Months to Value",{"type":42,"tag":353,"props":379,"children":380},{},[381],{"type":48,"value":382},"Gate",{"type":42,"tag":353,"props":384,"children":385},{},[386],{"type":48,"value":387},"First Step",{"type":42,"tag":389,"props":390,"children":391},"tbody",{},[392,420,447],{"type":42,"tag":349,"props":393,"children":394},{},[395,401,404,407,410,413,417],{"type":42,"tag":396,"props":397,"children":398},"td",{},[399],{"type":48,"value":400},"1",{"type":42,"tag":396,"props":402,"children":403},{},[],{"type":42,"tag":396,"props":405,"children":406},{},[],{"type":42,"tag":396,"props":408,"children":409},{},[],{"type":42,"tag":396,"props":411,"children":412},{},[],{"type":42,"tag":396,"props":414,"children":415},{},[416],{"type":48,"value":149},{"type":42,"tag":396,"props":418,"children":419},{},[],{"type":42,"tag":349,"props":421,"children":422},{},[423,428,431,434,437,440,444],{"type":42,"tag":396,"props":424,"children":425},{},[426],{"type":48,"value":427},"2",{"type":42,"tag":396,"props":429,"children":430},{},[],{"type":42,"tag":396,"props":432,"children":433},{},[],{"type":42,"tag":396,"props":435,"children":436},{},[],{"type":42,"tag":396,"props":438,"children":439},{},[],{"type":42,"tag":396,"props":441,"children":442},{},[443],{"type":48,"value":149},{"type":42,"tag":396,"props":445,"children":446},{},[],{"type":42,"tag":349,"props":448,"children":449},{},[450,455,458,461,464,467,478],{"type":42,"tag":396,"props":451,"children":452},{},[453],{"type":48,"value":454},"3",{"type":42,"tag":396,"props":456,"children":457},{},[],{"type":42,"tag":396,"props":459,"children":460},{},[],{"type":42,"tag":396,"props":462,"children":463},{},[],{"type":42,"tag":396,"props":465,"children":466},{},[],{"type":42,"tag":396,"props":468,"children":469},{},[470,472],{"type":48,"value":471},"Wait — ",{"type":42,"tag":473,"props":474,"children":475},"span",{},[476],{"type":48,"value":477},"blocker",{"type":42,"tag":396,"props":479,"children":480},{},[],{"type":42,"tag":58,"props":482,"children":484},{"id":483},"step-4-find-the-replays",[485],{"type":48,"value":486},"Step 4: Find the Replays",{"type":42,"tag":65,"props":488,"children":489},{},[490],{"type":48,"value":491},"The highest-leverage move in a portfolio is running one successful play at multiple companies. Scan for:",{"type":42,"tag":71,"props":493,"children":494},{},[495,505,515],{"type":42,"tag":75,"props":496,"children":497},{},[498,503],{"type":42,"tag":79,"props":499,"children":500},{},[501],{"type":48,"value":502},"Same sector, same function",{"type":48,"value":504}," — two healthcare services portcos with manual prior-auth? One implementation, two deployments.",{"type":42,"tag":75,"props":506,"children":507},{},[508,513],{"type":42,"tag":79,"props":509,"children":510},{},[511],{"type":48,"value":512},"Same tool, different company",{"type":48,"value":514}," — if one portco already has a working invoice-processing setup, flag every other portco with >$Xm in AP volume as a fast follower.",{"type":42,"tag":75,"props":516,"children":517},{},[518,523],{"type":42,"tag":79,"props":519,"children":520},{},[521],{"type":48,"value":522},"Shared vendor leverage",{"type":48,"value":524}," — three portcos buying the same tool is a pricing conversation.",{"type":42,"tag":65,"props":526,"children":527},{},[528],{"type":48,"value":529},"List each replay with the lead company (who proves it) and follower companies (who copy it).",{"type":42,"tag":58,"props":531,"children":533},{"id":532},"step-5-output",[534],{"type":48,"value":535},"Step 5: Output",{"type":42,"tag":65,"props":537,"children":538},{},[539],{"type":48,"value":540},"One page for the operating partner, structured for a portfolio review:",{"type":42,"tag":160,"props":542,"children":543},{},[544,554,564,574,584],{"type":42,"tag":75,"props":545,"children":546},{},[547,552],{"type":42,"tag":79,"props":548,"children":549},{},[550],{"type":48,"value":551},"Top 5 across the portfolio",{"type":48,"value":553}," — the ranked table from Step 3, with owner and 30-day first step",{"type":42,"tag":75,"props":555,"children":556},{},[557,562],{"type":42,"tag":79,"props":558,"children":559},{},[560],{"type":48,"value":561},"Replays",{"type":48,"value":563}," — 2-3 playbooks that hit multiple companies at once",{"type":42,"tag":75,"props":565,"children":566},{},[567,572],{"type":42,"tag":79,"props":568,"children":569},{},[570],{"type":48,"value":571},"Go \u002F Wait by company",{"type":48,"value":573}," — one line each; for Waits, what unblocks them",{"type":42,"tag":75,"props":575,"children":576},{},[577,582],{"type":42,"tag":79,"props":578,"children":579},{},[580],{"type":48,"value":581},"What we're NOT doing",{"type":48,"value":583}," — the opportunities that looked good on paper but failed a gate; saves the operating partner from relitigating them every quarter",{"type":42,"tag":75,"props":585,"children":586},{},[587,592],{"type":42,"tag":79,"props":588,"children":589},{},[590],{"type":48,"value":591},"Aggregate EBITDA contribution",{"type":48,"value":593}," — total portfolio-wide AI opportunity, split Year 1 quick wins vs. Years 2-3 scale",{"type":42,"tag":51,"props":595,"children":597},{"id":596},"important-notes",[598],{"type":48,"value":599},"Important Notes",{"type":42,"tag":71,"props":601,"children":602},{},[603,613,623,633,643,653],{"type":42,"tag":75,"props":604,"children":605},{},[606,611],{"type":42,"tag":79,"props":607,"children":608},{},[609],{"type":48,"value":610},"Rank by dollars, not excitement.",{"type":48,"value":612}," A boring AP automation that saves $400k at a $40m revenue company beats a flashy customer-facing chatbot every time.",{"type":42,"tag":75,"props":614,"children":615},{},[616,621],{"type":42,"tag":79,"props":617,"children":618},{},[619],{"type":48,"value":620},"The binding constraint is almost always data, not models.",{"type":48,"value":622}," If a company can't produce a clean customer list, AI isn't the first project — a data cleanup is. Say so plainly.",{"type":42,"tag":75,"props":624,"children":625},{},[626,631],{"type":42,"tag":79,"props":627,"children":628},{},[629],{"type":48,"value":630},"Off-the-shelf first.",{"type":48,"value":632}," Custom builds are slow, expensive, and fragile for companies without engineering depth. Favor tools they can buy and deploy.",{"type":42,"tag":75,"props":634,"children":635},{},[636,641],{"type":42,"tag":79,"props":637,"children":638},{},[639],{"type":48,"value":640},"Ownership is the real gate.",{"type":48,"value":642}," A quick win with no internal owner dies in 90 days. If no one on the management team wants it, mark it Wait regardless of the dollar size.",{"type":42,"tag":75,"props":644,"children":645},{},[646,651],{"type":42,"tag":79,"props":647,"children":648},{},[649],{"type":48,"value":650},"Hold period drives urgency.",{"type":48,"value":652}," A company 3 years from exit can afford a foundational data project. A company 12 months out needs something that shows up in the LTM EBITDA for the CIM — or skip it.",{"type":42,"tag":75,"props":654,"children":655},{},[656,661],{"type":42,"tag":79,"props":657,"children":658},{},[659],{"type":48,"value":660},"Failed pilots are signal.",{"type":48,"value":662}," If management already tried something and it didn't stick, find out why before proposing the same thing again.",{"items":664,"total":766},[665,684,701,708,723,740,750],{"slug":666,"name":666,"fn":667,"description":668,"org":669,"tags":670,"stars":26,"repoUrl":27,"updatedAt":683},"3-statement-model","fill out 3-statement financial models","Complete, populate and fill out 3-statement financial model templates (Income Statement, Balance Sheet, Cash Flow Statement) . Use when asked to fill out model templates, complete existing model frameworks, populate financial models with data, complete a partially filled IS\u002FBS\u002FCF framework, or link integrated financial statements within an existing template structure. Triggers include requests to fill in, complete, or populate a 3-statement model template",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[671,674,677,680],{"name":672,"slug":673,"type":16},"Excel","excel",{"name":675,"slug":676,"type":16},"Finance","finance",{"name":678,"slug":679,"type":16},"Financial Modeling","financial-modeling",{"name":681,"slug":682,"type":16},"Financial Statements","financial-statements","2026-05-15T06:08:35.416766",{"slug":685,"name":685,"fn":686,"description":687,"org":688,"tags":689,"stars":26,"repoUrl":27,"updatedAt":700},"accrual-schedule","build period-end accrual schedules","Build the period-end accrual schedule — for each accrual, compute the entry, cite the support, and draft the JE. Use during month-end close; the JE is a draft for controller approval, not a posting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[690,693,694,697],{"name":691,"slug":692,"type":16},"Accounting","accounting",{"name":675,"slug":676,"type":16},{"name":695,"slug":696,"type":16},"Journal Entry","journal-entry",{"name":698,"slug":699,"type":16},"Month-End Close","month-end-close","2026-05-06T05:38:41.445686",{"slug":4,"name":4,"fn":5,"description":6,"org":702,"tags":703,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[704,705,706,707],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"slug":709,"name":709,"fn":710,"description":711,"org":712,"tags":713,"stars":26,"repoUrl":27,"updatedAt":722},"audit-xls","audit spreadsheets for formula accuracy","Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on \"audit this sheet\", \"check my formulas\", \"find formula errors\", \"QA this spreadsheet\", \"sanity check this\", \"debug model\", \"model check\", \"model won't balance\", \"something's off in my model\", \"model review\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[714,717,718,719],{"name":715,"slug":716,"type":16},"Audit","audit",{"name":672,"slug":673,"type":16},{"name":675,"slug":676,"type":16},{"name":720,"slug":721,"type":16},"Spreadsheets","spreadsheets","2026-05-15T06:07:23.536125",{"slug":724,"name":724,"fn":725,"description":726,"org":727,"tags":728,"stars":26,"repoUrl":27,"updatedAt":739},"bond-futures-basis","analyze bond futures basis","Analyze the bond futures basis by pricing futures, identifying the cheapest-to-deliver, and comparing with yield curves to assess delivery option value and basis trading opportunities. Use when analyzing bond futures, computing the basis, identifying CTD bonds, calculating implied repo rates, or evaluating basis trades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[729,732,733,736],{"name":730,"slug":731,"type":16},"Derivatives","derivatives",{"name":675,"slug":676,"type":16},{"name":734,"slug":735,"type":16},"Fixed Income","fixed-income",{"name":737,"slug":738,"type":16},"Trading","trading","2026-05-15T06:08:13.647174",{"slug":741,"name":741,"fn":742,"description":743,"org":744,"tags":745,"stars":26,"repoUrl":27,"updatedAt":749},"bond-relative-value","perform bond relative value analysis","Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing. Use when analyzing bond richness\u002Fcheapness, computing spread decomposition, comparing bonds, assessing bond value vs curves, or running rate shock scenarios.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[746,747,748],{"name":675,"slug":676,"type":16},{"name":734,"slug":735,"type":16},{"name":737,"slug":738,"type":16},"2026-05-15T06:08:11.151011",{"slug":751,"name":751,"fn":752,"description":753,"org":754,"tags":755,"stars":26,"repoUrl":27,"updatedAt":765},"break-trace","trace reconciliation breaks to source transactions","Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what differs and why. Use after gl-recon has classified a break.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[756,757,758,761,762],{"name":691,"slug":692,"type":16},{"name":715,"slug":716,"type":16},{"name":759,"slug":760,"type":16},"Debugging","debugging",{"name":675,"slug":676,"type":16},{"name":763,"slug":764,"type":16},"Reconciliation","reconciliation","2026-05-06T05:37:42.364074",62,{"items":768,"total":955},[769,790,804,816,835,848,869,889,903,918,926,939],{"slug":770,"name":770,"fn":771,"description":772,"org":773,"tags":774,"stars":787,"repoUrl":788,"updatedAt":789},"algorithmic-art","create algorithmic art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[775,778,781,784],{"name":776,"slug":777,"type":16},"Creative","creative",{"name":779,"slug":780,"type":16},"Design","design",{"name":782,"slug":783,"type":16},"Generative Art","generative-art",{"name":785,"slug":786,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":787,"repoUrl":788,"updatedAt":803},"brand-guidelines","apply Anthropic brand colors and typography","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[796,799,800],{"name":797,"slug":798,"type":16},"Branding","branding",{"name":779,"slug":780,"type":16},{"name":801,"slug":802,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":805,"name":805,"fn":806,"description":807,"org":808,"tags":809,"stars":787,"repoUrl":788,"updatedAt":815},"canvas-design","create posters and visual art as PNG or PDF","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[810,811,812],{"name":776,"slug":777,"type":16},{"name":779,"slug":780,"type":16},{"name":813,"slug":814,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":817,"name":817,"fn":818,"description":819,"org":820,"tags":821,"stars":787,"repoUrl":788,"updatedAt":834},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[822,825,826,829,831],{"name":823,"slug":824,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":827,"slug":828,"type":16},"Anthropic SDK","anthropic-sdk",{"name":830,"slug":817,"type":16},"Claude API",{"name":832,"slug":833,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":836,"name":836,"fn":837,"description":838,"org":839,"tags":840,"stars":787,"repoUrl":788,"updatedAt":847},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[841,844],{"name":842,"slug":843,"type":16},"Documentation","documentation",{"name":845,"slug":846,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":849,"name":849,"fn":850,"description":851,"org":852,"tags":853,"stars":787,"repoUrl":788,"updatedAt":868},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[854,857,859,862,865],{"name":855,"slug":856,"type":16},"Documents","documents",{"name":858,"slug":849,"type":16},"DOCX",{"name":860,"slug":861,"type":16},"Office","office",{"name":863,"slug":864,"type":16},"Templates","templates",{"name":866,"slug":867,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":870,"name":870,"fn":871,"description":872,"org":873,"tags":874,"stars":787,"repoUrl":788,"updatedAt":888},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[875,876,879,882,885],{"name":779,"slug":780,"type":16},{"name":877,"slug":878,"type":16},"Frontend","frontend",{"name":880,"slug":881,"type":16},"React","react",{"name":883,"slug":884,"type":16},"Tailwind CSS","tailwind-css",{"name":886,"slug":887,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":787,"repoUrl":788,"updatedAt":902},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[895,898,899],{"name":896,"slug":897,"type":16},"Communications","communications",{"name":863,"slug":864,"type":16},{"name":900,"slug":901,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":904,"name":904,"fn":905,"description":906,"org":907,"tags":908,"stars":787,"repoUrl":788,"updatedAt":917},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[909,910,913,914],{"name":823,"slug":824,"type":16},{"name":911,"slug":912,"type":16},"API Development","api-development",{"name":832,"slug":833,"type":16},{"name":915,"slug":916,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":814,"name":814,"fn":919,"description":920,"org":921,"tags":922,"stars":787,"repoUrl":788,"updatedAt":925},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[923,924],{"name":855,"slug":856,"type":16},{"name":813,"slug":814,"type":16},"2026-04-06T17:56:02.483316",{"slug":927,"name":927,"fn":928,"description":929,"org":930,"tags":931,"stars":787,"repoUrl":788,"updatedAt":938},"pptx","create and edit PowerPoint presentations","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[932,935],{"name":933,"slug":934,"type":16},"PowerPoint","powerpoint",{"name":936,"slug":937,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":940,"name":940,"fn":941,"description":942,"org":943,"tags":944,"stars":787,"repoUrl":788,"updatedAt":954},"skill-creator","create and optimize agent skills","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[945,946,947,950,953],{"name":823,"slug":824,"type":16},{"name":842,"slug":843,"type":16},{"name":948,"slug":949,"type":16},"Evals","evals",{"name":951,"slug":952,"type":16},"Performance","performance",{"name":845,"slug":846,"type":16},"2026-04-19T06:45:40.804",490]