[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-edgartools-sec-data":3,"mdc--bcwo0z-key":36,"related-repo-anthropic-edgartools-sec-data":600,"related-org-anthropic-edgartools-sec-data":623},{"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},"edgartools-sec-data","pull SEC EDGAR data","How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K\u002F10-Q data, or company financials.",{"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},"Research","research","tag",{"name":18,"slug":19,"type":16},"Finance","finance",{"name":21,"slug":22,"type":16},"SEC Filings","sec-filings",{"name":24,"slug":25,"type":16},"Python","python",1282,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops","2026-06-27T07:17:06.340987",null,394,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Ftree\u002FHEAD\u002Fresearch-desk\u002Fskills\u002Fedgartools","---\nname: edgartools-sec-data\ndescription: How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K\u002F10-Q data, or company financials.\n---\n\n# edgartools: SEC EDGAR data access\n\n`edgartools` is the desk's standard way to read SEC data. It is preinstalled in your environment. Work in Python (a script or `python -c`), not by fetching sec.gov pages by hand.\n\n## Always set your identity first\n\nThe SEC requires a contact identity on automated requests. Do this before any other call, every session:\n\n```python\nfrom edgar import set_identity\nset_identity(\"Research Desk workshop attendee@example.com\")  # use the EDGAR_IDENTITY value you were given\n```\n\n(Equivalently, the `EDGAR_IDENTITY` environment variable, exported before running Python.)\n\n## Companies and filings\n\n```python\nfrom edgar import Company\n\ncompany = Company(\"NVDA\")              # by ticker (or CIK)\ncompany.name, company.cik, company.industry\n\nfilings = company.get_filings(form=\"10-K\")   # also \"10-Q\", \"8-K\", \"DEF 14A\", ...\nlatest_10k = filings.latest()                # most recent of that form\nlatest_10q = company.get_filings(form=\"10-Q\").latest()\n\nlatest_10k.form, latest_10k.filing_date, latest_10k.accession_no\n```\n\nPick whichever of the latest 10-K \u002F 10-Q is more recent when asked for \"the most recent filing\". Foreign private issuers file 20-F instead of 10-K.\n\n## Reading the filing\n\n```python\nfiling = latest_10k\ntenk = filing.obj()        # rich object for 10-K\u002F10-Q: sections, financials\n\n# Sections (10-K item numbers; 10-Q uses Part\u002FItem naming)\nrisk_factors = tenk[\"Item 1A\"]      # Risk Factors text\nmda = tenk[\"Item 7\"]                # Management's Discussion & Analysis\nbusiness = tenk[\"Item 1\"]\n\n# Plain text of the whole filing if you need to search it\ntext = filing.text()\n```\n\nSections are long — extract what you need rather than pasting whole sections into your reply.\n\n## Financial statements (XBRL)\n\n```python\nfinancials = tenk.financials          # also: company.get_financials() for the latest annual figures\n\nincome = financials.income_statement()\nbalance = financials.balance_sheet()\ncashflow = financials.cashflow_statement()\n```\n\nThese return tabular objects (pandas-friendly). Typical fields: total revenue, gross profit, operating income, net income, cash and equivalents, total debt, inventory, R&D expense. The same statement usually carries the prior period's column — use it for year-over-year comparisons instead of fetching another filing.\n\n## Segment and geographic revenue\n\nConsolidated revenue hides the story; the segment note is where concentration and regional shifts show up. Segment data lives in the financial-statement notes (ASC 280), not the primary statements:\n\n```python\n# The segment\u002Fgeography breakdown is a note, not a primary statement.\n# Search the filing text for the segment note and read the tables around it.\ntext = filing.text()\nfor marker in [\"Segment Information\", \"revenue by geographic\", \"Disaggregation of Revenue\"]:\n    idx = text.find(marker)\n    if idx != -1:\n        print(text[idx : idx + 3000])   # the note's tables follow the heading\n        break\n```\n\nReport segment\u002Fgeography revenue alongside the consolidated figure and call out: any region or segment that moved more than ~20% year over year, and any customer-concentration disclosure (usually phrased \"one customer accounted for X% of revenue\").\n\n## Useful patterns\n\n- **Year-over-year risk-factor diff:** pull Item 1A from this year's and last year's 10-K (`company.get_filings(form=\"10-K\")` is sorted; take the first two) and compare.\n- **Insider activity:** `company.get_filings(form=\"4\")` lists Form 4 insider transaction filings.\n- **Be defensive:** the API surface evolves. If an attribute or method isn't there, inspect it (`dir(obj)`, `help(obj)`) or fall back to `filing.text()` and targeted searching, and note the fallback in your output.\n- **Be polite to EDGAR:** keep requests to what you need; everything is cached within the session by the library.\n\n## Units and reporting hygiene\n\n- Statement values are typically raw USD; convert to millions when reporting (`value \u002F 1e6`) and label them.\n- Always state which filing (form, fiscal period, filing date) a number came from.\n- If a figure is missing or ambiguous in XBRL, say so rather than estimating.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,71,78,83,113,126,132,226,231,237,322,327,333,379,384,390,395,465,470,476,562,568,594],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"edgartools-sec-edgar-data-access",[47],{"type":48,"value":49},"text","edgartools: SEC EDGAR data access",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54,61,63,69],{"type":42,"tag":55,"props":56,"children":58},"code",{"className":57},[],[59],{"type":48,"value":60},"edgartools",{"type":48,"value":62}," is the desk's standard way to read SEC data. It is preinstalled in your environment. Work in Python (a script or ",{"type":42,"tag":55,"props":64,"children":66},{"className":65},[],[67],{"type":48,"value":68},"python -c",{"type":48,"value":70},"), not by fetching sec.gov pages by hand.",{"type":42,"tag":72,"props":73,"children":75},"h2",{"id":74},"always-set-your-identity-first",[76],{"type":48,"value":77},"Always set your identity first",{"type":42,"tag":51,"props":79,"children":80},{},[81],{"type":48,"value":82},"The SEC requires a contact identity on automated requests. Do this before any other call, every session:",{"type":42,"tag":84,"props":85,"children":89},"pre",{"className":86,"code":87,"language":25,"meta":88,"style":88},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from edgar import set_identity\nset_identity(\"Research Desk workshop attendee@example.com\")  # use the EDGAR_IDENTITY value you were given\n","",[90],{"type":42,"tag":55,"props":91,"children":92},{"__ignoreMap":88},[93,104],{"type":42,"tag":94,"props":95,"children":98},"span",{"class":96,"line":97},"line",1,[99],{"type":42,"tag":94,"props":100,"children":101},{},[102],{"type":48,"value":103},"from edgar import set_identity\n",{"type":42,"tag":94,"props":105,"children":107},{"class":96,"line":106},2,[108],{"type":42,"tag":94,"props":109,"children":110},{},[111],{"type":48,"value":112},"set_identity(\"Research Desk workshop attendee@example.com\")  # use the EDGAR_IDENTITY value you were given\n",{"type":42,"tag":51,"props":114,"children":115},{},[116,118,124],{"type":48,"value":117},"(Equivalently, the ",{"type":42,"tag":55,"props":119,"children":121},{"className":120},[],[122],{"type":48,"value":123},"EDGAR_IDENTITY",{"type":48,"value":125}," environment variable, exported before running Python.)",{"type":42,"tag":72,"props":127,"children":129},{"id":128},"companies-and-filings",[130],{"type":48,"value":131},"Companies and filings",{"type":42,"tag":84,"props":133,"children":135},{"className":86,"code":134,"language":25,"meta":88,"style":88},"from edgar import Company\n\ncompany = Company(\"NVDA\")              # by ticker (or CIK)\ncompany.name, company.cik, company.industry\n\nfilings = company.get_filings(form=\"10-K\")   # also \"10-Q\", \"8-K\", \"DEF 14A\", ...\nlatest_10k = filings.latest()                # most recent of that form\nlatest_10q = company.get_filings(form=\"10-Q\").latest()\n\nlatest_10k.form, latest_10k.filing_date, latest_10k.accession_no\n",[136],{"type":42,"tag":55,"props":137,"children":138},{"__ignoreMap":88},[139,147,156,165,174,182,191,200,209,217],{"type":42,"tag":94,"props":140,"children":141},{"class":96,"line":97},[142],{"type":42,"tag":94,"props":143,"children":144},{},[145],{"type":48,"value":146},"from edgar import Company\n",{"type":42,"tag":94,"props":148,"children":149},{"class":96,"line":106},[150],{"type":42,"tag":94,"props":151,"children":153},{"emptyLinePlaceholder":152},true,[154],{"type":48,"value":155},"\n",{"type":42,"tag":94,"props":157,"children":159},{"class":96,"line":158},3,[160],{"type":42,"tag":94,"props":161,"children":162},{},[163],{"type":48,"value":164},"company = Company(\"NVDA\")              # by ticker (or CIK)\n",{"type":42,"tag":94,"props":166,"children":168},{"class":96,"line":167},4,[169],{"type":42,"tag":94,"props":170,"children":171},{},[172],{"type":48,"value":173},"company.name, company.cik, company.industry\n",{"type":42,"tag":94,"props":175,"children":177},{"class":96,"line":176},5,[178],{"type":42,"tag":94,"props":179,"children":180},{"emptyLinePlaceholder":152},[181],{"type":48,"value":155},{"type":42,"tag":94,"props":183,"children":185},{"class":96,"line":184},6,[186],{"type":42,"tag":94,"props":187,"children":188},{},[189],{"type":48,"value":190},"filings = company.get_filings(form=\"10-K\")   # also \"10-Q\", \"8-K\", \"DEF 14A\", ...\n",{"type":42,"tag":94,"props":192,"children":194},{"class":96,"line":193},7,[195],{"type":42,"tag":94,"props":196,"children":197},{},[198],{"type":48,"value":199},"latest_10k = filings.latest()                # most recent of that form\n",{"type":42,"tag":94,"props":201,"children":203},{"class":96,"line":202},8,[204],{"type":42,"tag":94,"props":205,"children":206},{},[207],{"type":48,"value":208},"latest_10q = company.get_filings(form=\"10-Q\").latest()\n",{"type":42,"tag":94,"props":210,"children":212},{"class":96,"line":211},9,[213],{"type":42,"tag":94,"props":214,"children":215},{"emptyLinePlaceholder":152},[216],{"type":48,"value":155},{"type":42,"tag":94,"props":218,"children":220},{"class":96,"line":219},10,[221],{"type":42,"tag":94,"props":222,"children":223},{},[224],{"type":48,"value":225},"latest_10k.form, latest_10k.filing_date, latest_10k.accession_no\n",{"type":42,"tag":51,"props":227,"children":228},{},[229],{"type":48,"value":230},"Pick whichever of the latest 10-K \u002F 10-Q is more recent when asked for \"the most recent filing\". Foreign private issuers file 20-F instead of 10-K.",{"type":42,"tag":72,"props":232,"children":234},{"id":233},"reading-the-filing",[235],{"type":48,"value":236},"Reading the filing",{"type":42,"tag":84,"props":238,"children":240},{"className":86,"code":239,"language":25,"meta":88,"style":88},"filing = latest_10k\ntenk = filing.obj()        # rich object for 10-K\u002F10-Q: sections, financials\n\n# Sections (10-K item numbers; 10-Q uses Part\u002FItem naming)\nrisk_factors = tenk[\"Item 1A\"]      # Risk Factors text\nmda = tenk[\"Item 7\"]                # Management's Discussion & Analysis\nbusiness = tenk[\"Item 1\"]\n\n# Plain text of the whole filing if you need to search it\ntext = filing.text()\n",[241],{"type":42,"tag":55,"props":242,"children":243},{"__ignoreMap":88},[244,252,260,267,275,283,291,299,306,314],{"type":42,"tag":94,"props":245,"children":246},{"class":96,"line":97},[247],{"type":42,"tag":94,"props":248,"children":249},{},[250],{"type":48,"value":251},"filing = latest_10k\n",{"type":42,"tag":94,"props":253,"children":254},{"class":96,"line":106},[255],{"type":42,"tag":94,"props":256,"children":257},{},[258],{"type":48,"value":259},"tenk = filing.obj()        # rich object for 10-K\u002F10-Q: sections, financials\n",{"type":42,"tag":94,"props":261,"children":262},{"class":96,"line":158},[263],{"type":42,"tag":94,"props":264,"children":265},{"emptyLinePlaceholder":152},[266],{"type":48,"value":155},{"type":42,"tag":94,"props":268,"children":269},{"class":96,"line":167},[270],{"type":42,"tag":94,"props":271,"children":272},{},[273],{"type":48,"value":274},"# Sections (10-K item numbers; 10-Q uses Part\u002FItem naming)\n",{"type":42,"tag":94,"props":276,"children":277},{"class":96,"line":176},[278],{"type":42,"tag":94,"props":279,"children":280},{},[281],{"type":48,"value":282},"risk_factors = tenk[\"Item 1A\"]      # Risk Factors text\n",{"type":42,"tag":94,"props":284,"children":285},{"class":96,"line":184},[286],{"type":42,"tag":94,"props":287,"children":288},{},[289],{"type":48,"value":290},"mda = tenk[\"Item 7\"]                # Management's Discussion & Analysis\n",{"type":42,"tag":94,"props":292,"children":293},{"class":96,"line":193},[294],{"type":42,"tag":94,"props":295,"children":296},{},[297],{"type":48,"value":298},"business = tenk[\"Item 1\"]\n",{"type":42,"tag":94,"props":300,"children":301},{"class":96,"line":202},[302],{"type":42,"tag":94,"props":303,"children":304},{"emptyLinePlaceholder":152},[305],{"type":48,"value":155},{"type":42,"tag":94,"props":307,"children":308},{"class":96,"line":211},[309],{"type":42,"tag":94,"props":310,"children":311},{},[312],{"type":48,"value":313},"# Plain text of the whole filing if you need to search it\n",{"type":42,"tag":94,"props":315,"children":316},{"class":96,"line":219},[317],{"type":42,"tag":94,"props":318,"children":319},{},[320],{"type":48,"value":321},"text = filing.text()\n",{"type":42,"tag":51,"props":323,"children":324},{},[325],{"type":48,"value":326},"Sections are long — extract what you need rather than pasting whole sections into your reply.",{"type":42,"tag":72,"props":328,"children":330},{"id":329},"financial-statements-xbrl",[331],{"type":48,"value":332},"Financial statements (XBRL)",{"type":42,"tag":84,"props":334,"children":336},{"className":86,"code":335,"language":25,"meta":88,"style":88},"financials = tenk.financials          # also: company.get_financials() for the latest annual figures\n\nincome = financials.income_statement()\nbalance = financials.balance_sheet()\ncashflow = financials.cashflow_statement()\n",[337],{"type":42,"tag":55,"props":338,"children":339},{"__ignoreMap":88},[340,348,355,363,371],{"type":42,"tag":94,"props":341,"children":342},{"class":96,"line":97},[343],{"type":42,"tag":94,"props":344,"children":345},{},[346],{"type":48,"value":347},"financials = tenk.financials          # also: company.get_financials() for the latest annual figures\n",{"type":42,"tag":94,"props":349,"children":350},{"class":96,"line":106},[351],{"type":42,"tag":94,"props":352,"children":353},{"emptyLinePlaceholder":152},[354],{"type":48,"value":155},{"type":42,"tag":94,"props":356,"children":357},{"class":96,"line":158},[358],{"type":42,"tag":94,"props":359,"children":360},{},[361],{"type":48,"value":362},"income = financials.income_statement()\n",{"type":42,"tag":94,"props":364,"children":365},{"class":96,"line":167},[366],{"type":42,"tag":94,"props":367,"children":368},{},[369],{"type":48,"value":370},"balance = financials.balance_sheet()\n",{"type":42,"tag":94,"props":372,"children":373},{"class":96,"line":176},[374],{"type":42,"tag":94,"props":375,"children":376},{},[377],{"type":48,"value":378},"cashflow = financials.cashflow_statement()\n",{"type":42,"tag":51,"props":380,"children":381},{},[382],{"type":48,"value":383},"These return tabular objects (pandas-friendly). Typical fields: total revenue, gross profit, operating income, net income, cash and equivalents, total debt, inventory, R&D expense. The same statement usually carries the prior period's column — use it for year-over-year comparisons instead of fetching another filing.",{"type":42,"tag":72,"props":385,"children":387},{"id":386},"segment-and-geographic-revenue",[388],{"type":48,"value":389},"Segment and geographic revenue",{"type":42,"tag":51,"props":391,"children":392},{},[393],{"type":48,"value":394},"Consolidated revenue hides the story; the segment note is where concentration and regional shifts show up. Segment data lives in the financial-statement notes (ASC 280), not the primary statements:",{"type":42,"tag":84,"props":396,"children":398},{"className":86,"code":397,"language":25,"meta":88,"style":88},"# The segment\u002Fgeography breakdown is a note, not a primary statement.\n# Search the filing text for the segment note and read the tables around it.\ntext = filing.text()\nfor marker in [\"Segment Information\", \"revenue by geographic\", \"Disaggregation of Revenue\"]:\n    idx = text.find(marker)\n    if idx != -1:\n        print(text[idx : idx + 3000])   # the note's tables follow the heading\n        break\n",[399],{"type":42,"tag":55,"props":400,"children":401},{"__ignoreMap":88},[402,410,418,425,433,441,449,457],{"type":42,"tag":94,"props":403,"children":404},{"class":96,"line":97},[405],{"type":42,"tag":94,"props":406,"children":407},{},[408],{"type":48,"value":409},"# The segment\u002Fgeography breakdown is a note, not a primary statement.\n",{"type":42,"tag":94,"props":411,"children":412},{"class":96,"line":106},[413],{"type":42,"tag":94,"props":414,"children":415},{},[416],{"type":48,"value":417},"# Search the filing text for the segment note and read the tables around it.\n",{"type":42,"tag":94,"props":419,"children":420},{"class":96,"line":158},[421],{"type":42,"tag":94,"props":422,"children":423},{},[424],{"type":48,"value":321},{"type":42,"tag":94,"props":426,"children":427},{"class":96,"line":167},[428],{"type":42,"tag":94,"props":429,"children":430},{},[431],{"type":48,"value":432},"for marker in [\"Segment Information\", \"revenue by geographic\", \"Disaggregation of Revenue\"]:\n",{"type":42,"tag":94,"props":434,"children":435},{"class":96,"line":176},[436],{"type":42,"tag":94,"props":437,"children":438},{},[439],{"type":48,"value":440},"    idx = text.find(marker)\n",{"type":42,"tag":94,"props":442,"children":443},{"class":96,"line":184},[444],{"type":42,"tag":94,"props":445,"children":446},{},[447],{"type":48,"value":448},"    if idx != -1:\n",{"type":42,"tag":94,"props":450,"children":451},{"class":96,"line":193},[452],{"type":42,"tag":94,"props":453,"children":454},{},[455],{"type":48,"value":456},"        print(text[idx : idx + 3000])   # the note's tables follow the heading\n",{"type":42,"tag":94,"props":458,"children":459},{"class":96,"line":202},[460],{"type":42,"tag":94,"props":461,"children":462},{},[463],{"type":48,"value":464},"        break\n",{"type":42,"tag":51,"props":466,"children":467},{},[468],{"type":48,"value":469},"Report segment\u002Fgeography revenue alongside the consolidated figure and call out: any region or segment that moved more than ~20% year over year, and any customer-concentration disclosure (usually phrased \"one customer accounted for X% of revenue\").",{"type":42,"tag":72,"props":471,"children":473},{"id":472},"useful-patterns",[474],{"type":48,"value":475},"Useful patterns",{"type":42,"tag":477,"props":478,"children":479},"ul",{},[480,500,518,552],{"type":42,"tag":481,"props":482,"children":483},"li",{},[484,490,492,498],{"type":42,"tag":485,"props":486,"children":487},"strong",{},[488],{"type":48,"value":489},"Year-over-year risk-factor diff:",{"type":48,"value":491}," pull Item 1A from this year's and last year's 10-K (",{"type":42,"tag":55,"props":493,"children":495},{"className":494},[],[496],{"type":48,"value":497},"company.get_filings(form=\"10-K\")",{"type":48,"value":499}," is sorted; take the first two) and compare.",{"type":42,"tag":481,"props":501,"children":502},{},[503,508,510,516],{"type":42,"tag":485,"props":504,"children":505},{},[506],{"type":48,"value":507},"Insider activity:",{"type":48,"value":509}," ",{"type":42,"tag":55,"props":511,"children":513},{"className":512},[],[514],{"type":48,"value":515},"company.get_filings(form=\"4\")",{"type":48,"value":517}," lists Form 4 insider transaction filings.",{"type":42,"tag":481,"props":519,"children":520},{},[521,526,528,534,536,542,544,550],{"type":42,"tag":485,"props":522,"children":523},{},[524],{"type":48,"value":525},"Be defensive:",{"type":48,"value":527}," the API surface evolves. If an attribute or method isn't there, inspect it (",{"type":42,"tag":55,"props":529,"children":531},{"className":530},[],[532],{"type":48,"value":533},"dir(obj)",{"type":48,"value":535},", ",{"type":42,"tag":55,"props":537,"children":539},{"className":538},[],[540],{"type":48,"value":541},"help(obj)",{"type":48,"value":543},") or fall back to ",{"type":42,"tag":55,"props":545,"children":547},{"className":546},[],[548],{"type":48,"value":549},"filing.text()",{"type":48,"value":551}," and targeted searching, and note the fallback in your output.",{"type":42,"tag":481,"props":553,"children":554},{},[555,560],{"type":42,"tag":485,"props":556,"children":557},{},[558],{"type":48,"value":559},"Be polite to EDGAR:",{"type":48,"value":561}," keep requests to what you need; everything is cached within the session by the library.",{"type":42,"tag":72,"props":563,"children":565},{"id":564},"units-and-reporting-hygiene",[566],{"type":48,"value":567},"Units and reporting hygiene",{"type":42,"tag":477,"props":569,"children":570},{},[571,584,589],{"type":42,"tag":481,"props":572,"children":573},{},[574,576,582],{"type":48,"value":575},"Statement values are typically raw USD; convert to millions when reporting (",{"type":42,"tag":55,"props":577,"children":579},{"className":578},[],[580],{"type":48,"value":581},"value \u002F 1e6",{"type":48,"value":583},") and label them.",{"type":42,"tag":481,"props":585,"children":586},{},[587],{"type":48,"value":588},"Always state which filing (form, fiscal period, filing date) a number came from.",{"type":42,"tag":481,"props":590,"children":591},{},[592],{"type":48,"value":593},"If a figure is missing or ambiguous in XBRL, say so rather than estimating.",{"type":42,"tag":595,"props":596,"children":597},"style",{},[598],{"type":48,"value":599},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":601,"total":106},[602,609],{"slug":4,"name":4,"fn":5,"description":6,"org":603,"tags":604,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[605,606,607,608],{"name":18,"slug":19,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},{"slug":610,"name":610,"fn":611,"description":612,"org":613,"tags":614,"stars":26,"repoUrl":27,"updatedAt":622},"mining","locate diamond spawns in Minecraft","Where diamonds spawn in Minecraft 1.20.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[615,618,621],{"name":616,"slug":617,"type":16},"Game Development","game-development",{"name":619,"slug":620,"type":16},"Reference","reference",{"name":14,"slug":15,"type":16},"2026-05-07T05:41:16.745365",{"items":624,"total":811},[625,646,660,672,691,704,725,745,759,774,782,795],{"slug":626,"name":626,"fn":627,"description":628,"org":629,"tags":630,"stars":643,"repoUrl":644,"updatedAt":645},"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},[631,634,637,640],{"name":632,"slug":633,"type":16},"Creative","creative",{"name":635,"slug":636,"type":16},"Design","design",{"name":638,"slug":639,"type":16},"Generative Art","generative-art",{"name":641,"slug":642,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":647,"name":647,"fn":648,"description":649,"org":650,"tags":651,"stars":643,"repoUrl":644,"updatedAt":659},"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},[652,655,656],{"name":653,"slug":654,"type":16},"Branding","branding",{"name":635,"slug":636,"type":16},{"name":657,"slug":658,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":661,"name":661,"fn":662,"description":663,"org":664,"tags":665,"stars":643,"repoUrl":644,"updatedAt":671},"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},[666,667,668],{"name":632,"slug":633,"type":16},{"name":635,"slug":636,"type":16},{"name":669,"slug":670,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":673,"name":673,"fn":674,"description":675,"org":676,"tags":677,"stars":643,"repoUrl":644,"updatedAt":690},"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},[678,681,682,685,687],{"name":679,"slug":680,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":683,"slug":684,"type":16},"Anthropic SDK","anthropic-sdk",{"name":686,"slug":673,"type":16},"Claude API",{"name":688,"slug":689,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":643,"repoUrl":644,"updatedAt":703},"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},[697,700],{"name":698,"slug":699,"type":16},"Documentation","documentation",{"name":701,"slug":702,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":705,"name":705,"fn":706,"description":707,"org":708,"tags":709,"stars":643,"repoUrl":644,"updatedAt":724},"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},[710,713,715,718,721],{"name":711,"slug":712,"type":16},"Documents","documents",{"name":714,"slug":705,"type":16},"DOCX",{"name":716,"slug":717,"type":16},"Office","office",{"name":719,"slug":720,"type":16},"Templates","templates",{"name":722,"slug":723,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":726,"name":726,"fn":727,"description":728,"org":729,"tags":730,"stars":643,"repoUrl":644,"updatedAt":744},"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},[731,732,735,738,741],{"name":635,"slug":636,"type":16},{"name":733,"slug":734,"type":16},"Frontend","frontend",{"name":736,"slug":737,"type":16},"React","react",{"name":739,"slug":740,"type":16},"Tailwind CSS","tailwind-css",{"name":742,"slug":743,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":746,"name":746,"fn":747,"description":748,"org":749,"tags":750,"stars":643,"repoUrl":644,"updatedAt":758},"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},[751,754,755],{"name":752,"slug":753,"type":16},"Communications","communications",{"name":719,"slug":720,"type":16},{"name":756,"slug":757,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":760,"name":760,"fn":761,"description":762,"org":763,"tags":764,"stars":643,"repoUrl":644,"updatedAt":773},"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},[765,766,769,770],{"name":679,"slug":680,"type":16},{"name":767,"slug":768,"type":16},"API Development","api-development",{"name":688,"slug":689,"type":16},{"name":771,"slug":772,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":670,"name":670,"fn":775,"description":776,"org":777,"tags":778,"stars":643,"repoUrl":644,"updatedAt":781},"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},[779,780],{"name":711,"slug":712,"type":16},{"name":669,"slug":670,"type":16},"2026-04-06T17:56:02.483316",{"slug":783,"name":783,"fn":784,"description":785,"org":786,"tags":787,"stars":643,"repoUrl":644,"updatedAt":794},"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},[788,791],{"name":789,"slug":790,"type":16},"PowerPoint","powerpoint",{"name":792,"slug":793,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":796,"name":796,"fn":797,"description":798,"org":799,"tags":800,"stars":643,"repoUrl":644,"updatedAt":810},"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},[801,802,803,806,809],{"name":679,"slug":680,"type":16},{"name":698,"slug":699,"type":16},{"name":804,"slug":805,"type":16},"Evals","evals",{"name":807,"slug":808,"type":16},"Performance","performance",{"name":701,"slug":702,"type":16},"2026-04-19T06:45:40.804",490]