[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-cash-flow-snapshot":3,"mdc--dy99nf-key":40,"related-org-anthropic-cash-flow-snapshot":632,"related-repo-anthropic-cash-flow-snapshot":821},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":38,"mdContent":39},"cash-flow-snapshot","generate cash flow forecasts","Reads AR\u002FAP, historical cash timing, and known fixed costs from QuickBooks, PayPal, Stripe, or Square — or a CSV upload — and produces a 30\u002F60\u002F90-day cash flow forecast with percentage-variance confidence bands and named risk flags. Delivers a chat summary and a downloadable XLSX. Use when the user asks \"forecast my cash flow,\" \"will I make payroll,\" mentions \"runway,\" or says \"cash crunch.\" Falls back to CSV upload when no connector is live.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Finance","finance","tag",{"name":18,"slug":19,"type":16},"Accounting","accounting",{"name":21,"slug":22,"type":16},"Forecasting","forecasting",{"name":24,"slug":25,"type":16},"PayPal","paypal",{"name":27,"slug":28,"type":16},"Stripe","stripe",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-05-14T06:02:59.06788",null,2736,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":37},[],"Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002FHEAD\u002Fsmall-business\u002Fskills\u002Fcash-flow-snapshot","---\nname: cash-flow-snapshot\ndescription: >\n  Reads AR\u002FAP, historical cash timing, and known fixed costs from QuickBooks,\n  PayPal, Stripe, or Square — or a CSV upload — and produces a 30\u002F60\u002F90-day\n  cash flow forecast with percentage-variance confidence bands and named risk\n  flags. Delivers a chat summary and a downloadable XLSX. Use when the user\n  asks \"forecast my cash flow,\" \"will I make payroll,\" mentions \"runway,\" or\n  says \"cash crunch.\" Falls back to CSV upload when no connector is live.\ncompatibility: \"Requires one or more of: QuickBooks MCP, PayPal MCP, Stripe MCP, Square MCP, file upload (CSV fallback). Output uses xlsx skill.\"\n---\n\n# Cash Flow Snapshot\n\nProduces a 30\u002F60\u002F90-day cash flow forecast with percentage-variance confidence\nbands and named risk flags. Delivers a two-part output: a concise chat summary\nand a downloadable XLSX workbook.\n\n**Quick start**\n\n> \"Will I make payroll next month?\"\n\nClaude pulls AR\u002FAP and fixed costs from connected sources, calculates expected\ninflows and outflows across 30, 60, and 90-day windows, applies confidence\nbands based on each customer's historical payment variance, and flags specific\nrisks by name.\n\n---\n\n## Workflow\n\n### Step 1 — Identify available data sources\n\nCheck which connectors are live. Try in this order:\n\n1. QuickBooks — primary source for AR aging, AP, and fixed costs\n2. PayPal — transaction history and settlement timing\n3. Stripe — charge and payout history\n4. Square — sales and payout history\n5. CSV upload — fallback if no connector is connected\n\nIf no connector is live and no file is attached, ask the user to either connect\na source or upload a CSV (income\u002Fexpense tabular data, any reasonable format).\nNote which sources were used in the output — this affects confidence band width.\n\n### Step 2 — Pull the data\n\n**From QuickBooks:**\n- AR aging report: customer name, invoice amount, invoice date, due date, days outstanding\n- AP: vendor name, amount due, due date\n- Recurring fixed costs: rent, payroll, subscriptions (look for recurring transactions)\n\n**From PayPal \u002F Stripe \u002F Square:**\n- Settlement history: transaction date, amount, settlement date\n- Use settlement lag (transaction date → payout date) to compute each source's\n  average and variance payment delay\n\n**From CSV upload:**\n- Parse as income\u002Fexpense tabular data\n- Required columns (flexible naming): date, amount, type (income or expense), description\n- If columns are ambiguous, show the header row and ask the user to confirm mapping\n\n### Step 3 — Compute historical payment timing\n\nFor each AR customer (or income source from CSV), calculate:\n- **Mean payment lag** — average days from invoice\u002Ftransaction date to receipt\n- **Payment variance** — standard deviation of payment lag across last 6–12 payments\n- Use variance to set confidence band width (see Step 4)\n\nIf fewer than 3 payments exist for a customer, use the population mean as the\npoint estimate and apply a ±30% variance band as the default. When running on\nCSV data with sufficient history (≥3 payments per source), compute the band\nfrom the actual payment variance — do not assume ±30%.\n\n### Step 4 — Build the 30\u002F60\u002F90-day forecast\n\nProduce three time windows: 0–30 days, 31–60 days, 61–90 days.\n\nFor each window, compute:\n\n| Line | Method |\n|---|---|\n| Expected inflows | AR due in window, adjusted for mean payment lag |\n| Expected outflows | AP due in window + fixed costs falling in window |\n| Net cash position | Inflows − Outflows |\n| Confidence band | ± weighted average payment variance as a % of expected inflows |\n\nConfidence band formula:\n```\nband_pct = weighted_avg_stddev_days \u002F avg_payment_lag_days\nlow  = net_cash × (1 − band_pct)\nhigh = net_cash × (1 + band_pct)\n```\n\nRound band_pct to one decimal place. Cap at ±50% — higher variance means the\ndata is too thin to model; flag it instead (see Step 5).\n\n### Step 5 — Flag named risks\n\nScan for conditions that push the low-band estimate negative or create a\nliquidity crunch. For each risk found, produce a one-line flag:\n\n- **Late-payer risk:** \"Customer X historically pays 18 days late; that shifts\n  their $8,400 invoice out of the 30-day window into day 48.\"\n- **Payroll crunch:** \"Payroll ($22,000) hits April 15. Low-band cash on hand\n  April 14: $19,200. Shortfall risk: $2,800.\"\n- **Thin data warning:** \"Only 2 payments on record for Customer Y — confidence\n  band set to default ±30%.\"\n- **No-connector warning:** \"Running on CSV data only — no real-time AP or\n  recurring cost data. Confidence bands are wider than normal.\"\n\nLimit to the top 5 risks by severity (largest dollar impact first).\n\n### Step 6 — Deliver outputs\n\n**Chat summary** (always):\n```\nCash Flow Snapshot — [date range]\nSource(s): [connectors used]\n\n            Expected    Low       High\n30-day net: $X,XXX     $X,XXX    $X,XXX\n60-day net: $X,XXX     $X,XXX    $X,XXX\n90-day net: $X,XXX     $X,XXX    $X,XXX\n\n⚠ Risks flagged: [count]\n  • [risk 1]\n  • [risk 2]\n  ...\n```\n\n**XLSX workbook** (always):\nRead `xlsx\u002FSKILL.md` before generating. Produce a workbook with three sheets:\n\n1. **Summary** — the 30\u002F60\u002F90 forecast table with confidence bands. Beneath\n   each window row, expand inline sub-rows showing the individual transactions\n   that make up its inflows (green) and outflows (red). This makes the estimates\n   auditable without leaving the Summary sheet.\n\n2. **Detail** — all transactions grouped by window, sorted by date within each\n   group. Include a running net column (cumulative inflows minus outflows within\n   the window) and a subtotal row at the bottom of each window showing total\n   inflows, total outflows, and net. Grey out past transactions in a separate\n   section at the bottom for reference. Ensure all three windows have rows even\n   if one is empty — show a \"No transactions in this window\" placeholder row.\n\n3. **Risks** — the flagged risks with dollar impact and affected window.\n\nSave as `cash-flow-snapshot-[YYYY-MM-DD].xlsx`.\n\n---\n\n## Approval gates\n\nNo destructive actions — this skill is read-only. No approval gate required\nbefore generating the forecast.\n\nRemind the user after delivery:\n> \"This forecast is based on [sources listed]. It is not a substitute for\n> accounting advice — verify with your bookkeeper before making financing decisions.\"\n\n---\n\n## Reference files\n\n| File | Load when |\n|---|---|\n| `reference\u002Fgotchas.md` | When a connector returns unexpected data or variance is extreme |\n| `reference\u002Fexamples\u002Fworked-example.md` | When modeling the output format for a new data shape |\n",{"data":41,"body":43},{"name":4,"description":6,"compatibility":42},"Requires one or more of: QuickBooks MCP, PayPal MCP, Stripe MCP, Square MCP, file upload (CSV fallback). Output uses xlsx skill.",{"type":44,"children":45},"root",[46,54,60,69,78,83,87,94,101,106,136,141,147,155,174,182,195,203,221,227,232,260,265,271,276,281,361,366,379,384,390,395,438,443,449,459,468,486,519,532,535,541,546,551,567,570,576],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Cash Flow Snapshot",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Produces a 30\u002F60\u002F90-day cash flow forecast with percentage-variance confidence\nbands and named risk flags. Delivers a two-part output: a concise chat summary\nand a downloadable XLSX workbook.",{"type":47,"tag":55,"props":61,"children":62},{},[63],{"type":47,"tag":64,"props":65,"children":66},"strong",{},[67],{"type":52,"value":68},"Quick start",{"type":47,"tag":70,"props":71,"children":72},"blockquote",{},[73],{"type":47,"tag":55,"props":74,"children":75},{},[76],{"type":52,"value":77},"\"Will I make payroll next month?\"",{"type":47,"tag":55,"props":79,"children":80},{},[81],{"type":52,"value":82},"Claude pulls AR\u002FAP and fixed costs from connected sources, calculates expected\ninflows and outflows across 30, 60, and 90-day windows, applies confidence\nbands based on each customer's historical payment variance, and flags specific\nrisks by name.",{"type":47,"tag":84,"props":85,"children":86},"hr",{},[],{"type":47,"tag":88,"props":89,"children":91},"h2",{"id":90},"workflow",[92],{"type":52,"value":93},"Workflow",{"type":47,"tag":95,"props":96,"children":98},"h3",{"id":97},"step-1-identify-available-data-sources",[99],{"type":52,"value":100},"Step 1 — Identify available data sources",{"type":47,"tag":55,"props":102,"children":103},{},[104],{"type":52,"value":105},"Check which connectors are live. Try in this order:",{"type":47,"tag":107,"props":108,"children":109},"ol",{},[110,116,121,126,131],{"type":47,"tag":111,"props":112,"children":113},"li",{},[114],{"type":52,"value":115},"QuickBooks — primary source for AR aging, AP, and fixed costs",{"type":47,"tag":111,"props":117,"children":118},{},[119],{"type":52,"value":120},"PayPal — transaction history and settlement timing",{"type":47,"tag":111,"props":122,"children":123},{},[124],{"type":52,"value":125},"Stripe — charge and payout history",{"type":47,"tag":111,"props":127,"children":128},{},[129],{"type":52,"value":130},"Square — sales and payout history",{"type":47,"tag":111,"props":132,"children":133},{},[134],{"type":52,"value":135},"CSV upload — fallback if no connector is connected",{"type":47,"tag":55,"props":137,"children":138},{},[139],{"type":52,"value":140},"If no connector is live and no file is attached, ask the user to either connect\na source or upload a CSV (income\u002Fexpense tabular data, any reasonable format).\nNote which sources were used in the output — this affects confidence band width.",{"type":47,"tag":95,"props":142,"children":144},{"id":143},"step-2-pull-the-data",[145],{"type":52,"value":146},"Step 2 — Pull the data",{"type":47,"tag":55,"props":148,"children":149},{},[150],{"type":47,"tag":64,"props":151,"children":152},{},[153],{"type":52,"value":154},"From QuickBooks:",{"type":47,"tag":156,"props":157,"children":158},"ul",{},[159,164,169],{"type":47,"tag":111,"props":160,"children":161},{},[162],{"type":52,"value":163},"AR aging report: customer name, invoice amount, invoice date, due date, days outstanding",{"type":47,"tag":111,"props":165,"children":166},{},[167],{"type":52,"value":168},"AP: vendor name, amount due, due date",{"type":47,"tag":111,"props":170,"children":171},{},[172],{"type":52,"value":173},"Recurring fixed costs: rent, payroll, subscriptions (look for recurring transactions)",{"type":47,"tag":55,"props":175,"children":176},{},[177],{"type":47,"tag":64,"props":178,"children":179},{},[180],{"type":52,"value":181},"From PayPal \u002F Stripe \u002F Square:",{"type":47,"tag":156,"props":183,"children":184},{},[185,190],{"type":47,"tag":111,"props":186,"children":187},{},[188],{"type":52,"value":189},"Settlement history: transaction date, amount, settlement date",{"type":47,"tag":111,"props":191,"children":192},{},[193],{"type":52,"value":194},"Use settlement lag (transaction date → payout date) to compute each source's\naverage and variance payment delay",{"type":47,"tag":55,"props":196,"children":197},{},[198],{"type":47,"tag":64,"props":199,"children":200},{},[201],{"type":52,"value":202},"From CSV upload:",{"type":47,"tag":156,"props":204,"children":205},{},[206,211,216],{"type":47,"tag":111,"props":207,"children":208},{},[209],{"type":52,"value":210},"Parse as income\u002Fexpense tabular data",{"type":47,"tag":111,"props":212,"children":213},{},[214],{"type":52,"value":215},"Required columns (flexible naming): date, amount, type (income or expense), description",{"type":47,"tag":111,"props":217,"children":218},{},[219],{"type":52,"value":220},"If columns are ambiguous, show the header row and ask the user to confirm mapping",{"type":47,"tag":95,"props":222,"children":224},{"id":223},"step-3-compute-historical-payment-timing",[225],{"type":52,"value":226},"Step 3 — Compute historical payment timing",{"type":47,"tag":55,"props":228,"children":229},{},[230],{"type":52,"value":231},"For each AR customer (or income source from CSV), calculate:",{"type":47,"tag":156,"props":233,"children":234},{},[235,245,255],{"type":47,"tag":111,"props":236,"children":237},{},[238,243],{"type":47,"tag":64,"props":239,"children":240},{},[241],{"type":52,"value":242},"Mean payment lag",{"type":52,"value":244}," — average days from invoice\u002Ftransaction date to receipt",{"type":47,"tag":111,"props":246,"children":247},{},[248,253],{"type":47,"tag":64,"props":249,"children":250},{},[251],{"type":52,"value":252},"Payment variance",{"type":52,"value":254}," — standard deviation of payment lag across last 6–12 payments",{"type":47,"tag":111,"props":256,"children":257},{},[258],{"type":52,"value":259},"Use variance to set confidence band width (see Step 4)",{"type":47,"tag":55,"props":261,"children":262},{},[263],{"type":52,"value":264},"If fewer than 3 payments exist for a customer, use the population mean as the\npoint estimate and apply a ±30% variance band as the default. When running on\nCSV data with sufficient history (≥3 payments per source), compute the band\nfrom the actual payment variance — do not assume ±30%.",{"type":47,"tag":95,"props":266,"children":268},{"id":267},"step-4-build-the-306090-day-forecast",[269],{"type":52,"value":270},"Step 4 — Build the 30\u002F60\u002F90-day forecast",{"type":47,"tag":55,"props":272,"children":273},{},[274],{"type":52,"value":275},"Produce three time windows: 0–30 days, 31–60 days, 61–90 days.",{"type":47,"tag":55,"props":277,"children":278},{},[279],{"type":52,"value":280},"For each window, compute:",{"type":47,"tag":282,"props":283,"children":284},"table",{},[285,304],{"type":47,"tag":286,"props":287,"children":288},"thead",{},[289],{"type":47,"tag":290,"props":291,"children":292},"tr",{},[293,299],{"type":47,"tag":294,"props":295,"children":296},"th",{},[297],{"type":52,"value":298},"Line",{"type":47,"tag":294,"props":300,"children":301},{},[302],{"type":52,"value":303},"Method",{"type":47,"tag":305,"props":306,"children":307},"tbody",{},[308,322,335,348],{"type":47,"tag":290,"props":309,"children":310},{},[311,317],{"type":47,"tag":312,"props":313,"children":314},"td",{},[315],{"type":52,"value":316},"Expected inflows",{"type":47,"tag":312,"props":318,"children":319},{},[320],{"type":52,"value":321},"AR due in window, adjusted for mean payment lag",{"type":47,"tag":290,"props":323,"children":324},{},[325,330],{"type":47,"tag":312,"props":326,"children":327},{},[328],{"type":52,"value":329},"Expected outflows",{"type":47,"tag":312,"props":331,"children":332},{},[333],{"type":52,"value":334},"AP due in window + fixed costs falling in window",{"type":47,"tag":290,"props":336,"children":337},{},[338,343],{"type":47,"tag":312,"props":339,"children":340},{},[341],{"type":52,"value":342},"Net cash position",{"type":47,"tag":312,"props":344,"children":345},{},[346],{"type":52,"value":347},"Inflows − Outflows",{"type":47,"tag":290,"props":349,"children":350},{},[351,356],{"type":47,"tag":312,"props":352,"children":353},{},[354],{"type":52,"value":355},"Confidence band",{"type":47,"tag":312,"props":357,"children":358},{},[359],{"type":52,"value":360},"± weighted average payment variance as a % of expected inflows",{"type":47,"tag":55,"props":362,"children":363},{},[364],{"type":52,"value":365},"Confidence band formula:",{"type":47,"tag":367,"props":368,"children":372},"pre",{"className":369,"code":371,"language":52},[370],"language-text","band_pct = weighted_avg_stddev_days \u002F avg_payment_lag_days\nlow  = net_cash × (1 − band_pct)\nhigh = net_cash × (1 + band_pct)\n",[373],{"type":47,"tag":374,"props":375,"children":377},"code",{"__ignoreMap":376},"",[378],{"type":52,"value":371},{"type":47,"tag":55,"props":380,"children":381},{},[382],{"type":52,"value":383},"Round band_pct to one decimal place. Cap at ±50% — higher variance means the\ndata is too thin to model; flag it instead (see Step 5).",{"type":47,"tag":95,"props":385,"children":387},{"id":386},"step-5-flag-named-risks",[388],{"type":52,"value":389},"Step 5 — Flag named risks",{"type":47,"tag":55,"props":391,"children":392},{},[393],{"type":52,"value":394},"Scan for conditions that push the low-band estimate negative or create a\nliquidity crunch. For each risk found, produce a one-line flag:",{"type":47,"tag":156,"props":396,"children":397},{},[398,408,418,428],{"type":47,"tag":111,"props":399,"children":400},{},[401,406],{"type":47,"tag":64,"props":402,"children":403},{},[404],{"type":52,"value":405},"Late-payer risk:",{"type":52,"value":407}," \"Customer X historically pays 18 days late; that shifts\ntheir $8,400 invoice out of the 30-day window into day 48.\"",{"type":47,"tag":111,"props":409,"children":410},{},[411,416],{"type":47,"tag":64,"props":412,"children":413},{},[414],{"type":52,"value":415},"Payroll crunch:",{"type":52,"value":417}," \"Payroll ($22,000) hits April 15. Low-band cash on hand\nApril 14: $19,200. Shortfall risk: $2,800.\"",{"type":47,"tag":111,"props":419,"children":420},{},[421,426],{"type":47,"tag":64,"props":422,"children":423},{},[424],{"type":52,"value":425},"Thin data warning:",{"type":52,"value":427}," \"Only 2 payments on record for Customer Y — confidence\nband set to default ±30%.\"",{"type":47,"tag":111,"props":429,"children":430},{},[431,436],{"type":47,"tag":64,"props":432,"children":433},{},[434],{"type":52,"value":435},"No-connector warning:",{"type":52,"value":437}," \"Running on CSV data only — no real-time AP or\nrecurring cost data. Confidence bands are wider than normal.\"",{"type":47,"tag":55,"props":439,"children":440},{},[441],{"type":52,"value":442},"Limit to the top 5 risks by severity (largest dollar impact first).",{"type":47,"tag":95,"props":444,"children":446},{"id":445},"step-6-deliver-outputs",[447],{"type":52,"value":448},"Step 6 — Deliver outputs",{"type":47,"tag":55,"props":450,"children":451},{},[452,457],{"type":47,"tag":64,"props":453,"children":454},{},[455],{"type":52,"value":456},"Chat summary",{"type":52,"value":458}," (always):",{"type":47,"tag":367,"props":460,"children":463},{"className":461,"code":462,"language":52},[370],"Cash Flow Snapshot — [date range]\nSource(s): [connectors used]\n\n            Expected    Low       High\n30-day net: $X,XXX     $X,XXX    $X,XXX\n60-day net: $X,XXX     $X,XXX    $X,XXX\n90-day net: $X,XXX     $X,XXX    $X,XXX\n\n⚠ Risks flagged: [count]\n  • [risk 1]\n  • [risk 2]\n  ...\n",[464],{"type":47,"tag":374,"props":465,"children":466},{"__ignoreMap":376},[467],{"type":52,"value":462},{"type":47,"tag":55,"props":469,"children":470},{},[471,476,478,484],{"type":47,"tag":64,"props":472,"children":473},{},[474],{"type":52,"value":475},"XLSX workbook",{"type":52,"value":477}," (always):\nRead ",{"type":47,"tag":374,"props":479,"children":481},{"className":480},[],[482],{"type":52,"value":483},"xlsx\u002FSKILL.md",{"type":52,"value":485}," before generating. Produce a workbook with three sheets:",{"type":47,"tag":107,"props":487,"children":488},{},[489,499,509],{"type":47,"tag":111,"props":490,"children":491},{},[492,497],{"type":47,"tag":64,"props":493,"children":494},{},[495],{"type":52,"value":496},"Summary",{"type":52,"value":498}," — the 30\u002F60\u002F90 forecast table with confidence bands. Beneath\neach window row, expand inline sub-rows showing the individual transactions\nthat make up its inflows (green) and outflows (red). This makes the estimates\nauditable without leaving the Summary sheet.",{"type":47,"tag":111,"props":500,"children":501},{},[502,507],{"type":47,"tag":64,"props":503,"children":504},{},[505],{"type":52,"value":506},"Detail",{"type":52,"value":508}," — all transactions grouped by window, sorted by date within each\ngroup. Include a running net column (cumulative inflows minus outflows within\nthe window) and a subtotal row at the bottom of each window showing total\ninflows, total outflows, and net. Grey out past transactions in a separate\nsection at the bottom for reference. Ensure all three windows have rows even\nif one is empty — show a \"No transactions in this window\" placeholder row.",{"type":47,"tag":111,"props":510,"children":511},{},[512,517],{"type":47,"tag":64,"props":513,"children":514},{},[515],{"type":52,"value":516},"Risks",{"type":52,"value":518}," — the flagged risks with dollar impact and affected window.",{"type":47,"tag":55,"props":520,"children":521},{},[522,524,530],{"type":52,"value":523},"Save as ",{"type":47,"tag":374,"props":525,"children":527},{"className":526},[],[528],{"type":52,"value":529},"cash-flow-snapshot-[YYYY-MM-DD].xlsx",{"type":52,"value":531},".",{"type":47,"tag":84,"props":533,"children":534},{},[],{"type":47,"tag":88,"props":536,"children":538},{"id":537},"approval-gates",[539],{"type":52,"value":540},"Approval gates",{"type":47,"tag":55,"props":542,"children":543},{},[544],{"type":52,"value":545},"No destructive actions — this skill is read-only. No approval gate required\nbefore generating the forecast.",{"type":47,"tag":55,"props":547,"children":548},{},[549],{"type":52,"value":550},"Remind the user after delivery:",{"type":47,"tag":70,"props":552,"children":553},{},[554],{"type":47,"tag":55,"props":555,"children":556},{},[557,559,565],{"type":52,"value":558},"\"This forecast is based on ",{"type":47,"tag":560,"props":561,"children":562},"span",{},[563],{"type":52,"value":564},"sources listed",{"type":52,"value":566},". It is not a substitute for\naccounting advice — verify with your bookkeeper before making financing decisions.\"",{"type":47,"tag":84,"props":568,"children":569},{},[],{"type":47,"tag":88,"props":571,"children":573},{"id":572},"reference-files",[574],{"type":52,"value":575},"Reference files",{"type":47,"tag":282,"props":577,"children":578},{},[579,595],{"type":47,"tag":286,"props":580,"children":581},{},[582],{"type":47,"tag":290,"props":583,"children":584},{},[585,590],{"type":47,"tag":294,"props":586,"children":587},{},[588],{"type":52,"value":589},"File",{"type":47,"tag":294,"props":591,"children":592},{},[593],{"type":52,"value":594},"Load when",{"type":47,"tag":305,"props":596,"children":597},{},[598,615],{"type":47,"tag":290,"props":599,"children":600},{},[601,610],{"type":47,"tag":312,"props":602,"children":603},{},[604],{"type":47,"tag":374,"props":605,"children":607},{"className":606},[],[608],{"type":52,"value":609},"reference\u002Fgotchas.md",{"type":47,"tag":312,"props":611,"children":612},{},[613],{"type":52,"value":614},"When a connector returns unexpected data or variance is extreme",{"type":47,"tag":290,"props":616,"children":617},{},[618,627],{"type":47,"tag":312,"props":619,"children":620},{},[621],{"type":47,"tag":374,"props":622,"children":624},{"className":623},[],[625],{"type":52,"value":626},"reference\u002Fexamples\u002Fworked-example.md",{"type":47,"tag":312,"props":628,"children":629},{},[630],{"type":52,"value":631},"When modeling the output format for a new data shape",{"items":633,"total":820},[634,655,669,681,700,713,734,754,768,783,791,804],{"slug":635,"name":635,"fn":636,"description":637,"org":638,"tags":639,"stars":652,"repoUrl":653,"updatedAt":654},"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},[640,643,646,649],{"name":641,"slug":642,"type":16},"Creative","creative",{"name":644,"slug":645,"type":16},"Design","design",{"name":647,"slug":648,"type":16},"Generative Art","generative-art",{"name":650,"slug":651,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":652,"repoUrl":653,"updatedAt":668},"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},[661,664,665],{"name":662,"slug":663,"type":16},"Branding","branding",{"name":644,"slug":645,"type":16},{"name":666,"slug":667,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":670,"name":670,"fn":671,"description":672,"org":673,"tags":674,"stars":652,"repoUrl":653,"updatedAt":680},"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},[675,676,677],{"name":641,"slug":642,"type":16},{"name":644,"slug":645,"type":16},{"name":678,"slug":679,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":682,"name":682,"fn":683,"description":684,"org":685,"tags":686,"stars":652,"repoUrl":653,"updatedAt":699},"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},[687,690,691,694,696],{"name":688,"slug":689,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":692,"slug":693,"type":16},"Anthropic SDK","anthropic-sdk",{"name":695,"slug":682,"type":16},"Claude API",{"name":697,"slug":698,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":701,"name":701,"fn":702,"description":703,"org":704,"tags":705,"stars":652,"repoUrl":653,"updatedAt":712},"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},[706,709],{"name":707,"slug":708,"type":16},"Documentation","documentation",{"name":710,"slug":711,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":652,"repoUrl":653,"updatedAt":733},"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},[719,722,724,727,730],{"name":720,"slug":721,"type":16},"Documents","documents",{"name":723,"slug":714,"type":16},"DOCX",{"name":725,"slug":726,"type":16},"Office","office",{"name":728,"slug":729,"type":16},"Templates","templates",{"name":731,"slug":732,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":735,"name":735,"fn":736,"description":737,"org":738,"tags":739,"stars":652,"repoUrl":653,"updatedAt":753},"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},[740,741,744,747,750],{"name":644,"slug":645,"type":16},{"name":742,"slug":743,"type":16},"Frontend","frontend",{"name":745,"slug":746,"type":16},"React","react",{"name":748,"slug":749,"type":16},"Tailwind CSS","tailwind-css",{"name":751,"slug":752,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":755,"name":755,"fn":756,"description":757,"org":758,"tags":759,"stars":652,"repoUrl":653,"updatedAt":767},"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},[760,763,764],{"name":761,"slug":762,"type":16},"Communications","communications",{"name":728,"slug":729,"type":16},{"name":765,"slug":766,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":769,"name":769,"fn":770,"description":771,"org":772,"tags":773,"stars":652,"repoUrl":653,"updatedAt":782},"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},[774,775,778,779],{"name":688,"slug":689,"type":16},{"name":776,"slug":777,"type":16},"API Development","api-development",{"name":697,"slug":698,"type":16},{"name":780,"slug":781,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":679,"name":679,"fn":784,"description":785,"org":786,"tags":787,"stars":652,"repoUrl":653,"updatedAt":790},"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},[788,789],{"name":720,"slug":721,"type":16},{"name":678,"slug":679,"type":16},"2026-04-06T17:56:02.483316",{"slug":792,"name":792,"fn":793,"description":794,"org":795,"tags":796,"stars":652,"repoUrl":653,"updatedAt":803},"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},[797,800],{"name":798,"slug":799,"type":16},"PowerPoint","powerpoint",{"name":801,"slug":802,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":805,"name":805,"fn":806,"description":807,"org":808,"tags":809,"stars":652,"repoUrl":653,"updatedAt":819},"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},[810,811,812,815,818],{"name":688,"slug":689,"type":16},{"name":707,"slug":708,"type":16},{"name":813,"slug":814,"type":16},"Evals","evals",{"name":816,"slug":817,"type":16},"Performance","performance",{"name":710,"slug":711,"type":16},"2026-04-19T06:45:40.804",490,{"items":822,"total":927},[823,837,853,869,885,902,914],{"slug":824,"name":824,"fn":825,"description":826,"org":827,"tags":828,"stars":29,"repoUrl":30,"updatedAt":836},"accessibility-review","run WCAG accessibility audits","Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with \"audit accessibility\", \"check a11y\", \"is this accessible?\", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[829,832,833],{"name":830,"slug":831,"type":16},"Accessibility","accessibility",{"name":644,"slug":645,"type":16},{"name":834,"slug":835,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":838,"name":838,"fn":839,"description":840,"org":841,"tags":842,"stars":29,"repoUrl":30,"updatedAt":852},"account-research","research accounts for sales intel","Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM. Trigger with \"research [company]\", \"look up [person]\", \"intel on [prospect]\", \"who is [name] at [company]\", or \"tell me about [company]\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[843,846,849],{"name":844,"slug":845,"type":16},"CRM","crm",{"name":847,"slug":848,"type":16},"Research","research",{"name":850,"slug":851,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":854,"name":854,"fn":855,"description":856,"org":857,"tags":858,"stars":29,"repoUrl":30,"updatedAt":868},"analyze","answer data questions and run analyses","Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[859,862,865],{"name":860,"slug":861,"type":16},"Analytics","analytics",{"name":863,"slug":864,"type":16},"Data Analysis","data-analysis",{"name":866,"slug":867,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":870,"name":870,"fn":871,"description":872,"org":873,"tags":874,"stars":29,"repoUrl":30,"updatedAt":884},"architecture","create and evaluate architecture decision records","Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[875,878,880,881],{"name":876,"slug":877,"type":16},"ADR","adr",{"name":879,"slug":870,"type":16},"Architecture",{"name":707,"slug":708,"type":16},{"name":882,"slug":883,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":886,"name":886,"fn":887,"description":888,"org":889,"tags":890,"stars":29,"repoUrl":30,"updatedAt":901},"audit-support","support SOX 404 control testing","Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[891,894,895,898],{"name":892,"slug":893,"type":16},"Audit","audit",{"name":14,"slug":15,"type":16},{"name":896,"slug":897,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":899,"slug":900,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":903,"name":903,"fn":904,"description":905,"org":906,"tags":907,"stars":29,"repoUrl":30,"updatedAt":913},"brand-review","review content against brand voice","Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before\u002Fafter fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[908,909,912],{"name":662,"slug":663,"type":16},{"name":910,"slug":911,"type":16},"Marketing","marketing",{"name":765,"slug":766,"type":16},"2026-04-06T17:58:19.548331",{"slug":915,"name":915,"fn":916,"description":917,"org":918,"tags":919,"stars":29,"repoUrl":30,"updatedAt":926},"brand-voice-enforcement","enforce brand voice in content","This skill applies brand guidelines to content creation. It should be used when the user asks to \"write an email\", \"draft a proposal\", \"create a pitch deck\", \"write a LinkedIn post\", \"draft a presentation\", \"write a Slack message\", \"draft sales content\", or any content creation request where brand voice should be applied. Also triggers on \"on-brand\", \"brand voice\", \"enforce voice\", \"apply brand guidelines\", \"brand-aligned content\", \"write in our voice\", \"use our brand tone\", \"make this sound like us\", \"rewrite this in our tone\", or \"this doesn't sound on-brand\". Not for generating guidelines from scratch (use guideline-generation) or discovering brand materials (use discover-brand).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[920,921,922,925],{"name":662,"slug":663,"type":16},{"name":761,"slug":762,"type":16},{"name":923,"slug":924,"type":16},"Content Creation","content-creation",{"name":765,"slug":766,"type":16},"2026-04-06T18:00:23.528956",200]