[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-discover-brand":3,"mdc-jw7dl4-key":37,"related-repo-anthropic-discover-brand":658,"related-org-anthropic-discover-brand":773},{"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":35,"mdContent":36},"discover-brand","discover brand materials across platforms","This skill orchestrates autonomous discovery of brand materials across enterprise platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, Slack). It should be used when the user asks to \"discover brand materials\", \"find brand documents\", \"search for brand guidelines\", \"audit brand content\", \"what brand materials do we have\", \"find our style guide\", \"where are our brand docs\", \"do we have a style guide\", \"discover brand voice\", \"brand content audit\", or \"find brand assets\".\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],{"name":14,"slug":15,"type":16},"Marketing","marketing","tag",{"name":18,"slug":19,"type":16},"Enterprise Search","enterprise-search",{"name":21,"slug":22,"type":16},"Knowledge Management","knowledge-management",{"name":24,"slug":25,"type":16},"Branding","branding",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T18:00:20.902029",null,2736,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"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\u002Fpartner-built\u002Fbrand-voice\u002Fskills\u002Fdiscover-brand","---\nname: discover-brand\ndescription: >\n  This skill orchestrates autonomous discovery of brand materials across enterprise\n  platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, Slack).\n  It should be used when the user asks to \"discover brand materials\",\n  \"find brand documents\", \"search for brand guidelines\", \"audit brand content\",\n  \"what brand materials do we have\", \"find our style guide\", \"where are our brand docs\",\n  \"do we have a style guide\", \"discover brand voice\", \"brand content audit\",\n  or \"find brand assets\".\n---\n\n# Brand Discovery\n\nOrchestrate autonomous discovery of brand materials across enterprise platforms. This skill coordinates the discover-brand agent to search connected platforms (Notion, Confluence, Google Drive, Box, Microsoft 365, Figma, Gong, Granola, Slack), triage sources, and produce a structured discovery report with open questions.\n\n## Discovery Workflow\n\n### 0. Orient the User\n\nBefore starting, briefly explain what's about to happen so the user knows what to expect:\n\n\"Here's how brand discovery works:\n\n1. **Search** — I'll search your connected platforms (Notion, Google Drive, Slack, etc.) for brand-related materials: style guides, pitch decks, templates, transcripts, and more.\n2. **Analyze** — I'll categorize and rank what I find, pull the best sources, and produce a discovery report with what I found, any conflicts, and open questions.\n3. **Generate guidelines** — Once you've reviewed the report, I can generate a structured brand voice guideline document from the results.\n4. **Save** — Guidelines are saved to `.claude\u002Fbrand-voice-guidelines.md` in your working folder once you approve them. Nothing is written until that step.\n\nThe search usually takes a few minutes depending on how many platforms are connected. Ready to get started?\"\n\nWait for the user to confirm before proceeding. If they have questions about the process, answer them first.\n\n### 1. Check Settings\n\nRead `.claude\u002Fbrand-voice.local.md` if it exists. Extract:\n- Company name\n- Which platforms are enabled (notion, confluence, google-drive, box, microsoft-365, figma, gong, granola, slack)\n- Search depth preference (standard or deep)\n- Max sources limit\n- Any known brand material locations listed under \"Known Brand Materials\"\n\nIf no settings file exists, proceed with all connected platforms and standard search depth.\n\n### 2. Validate Platform Coverage\n\nBefore confirming scope, check which platforms are actually connected and classify them:\n\n**Document platforms** (where brand guidelines, style guides, templates, and decks live):\n- Notion, Confluence, Google Drive, Box, Microsoft 365 (SharePoint\u002FOneDrive)\n\n**Supplementary platforms** (valuable for patterns, but not where brand docs are stored):\n- Slack, Gong, Granola, Figma\n\nApply these rules:\n\n1. **If zero document platforms are connected**: **Stop.** Tell the user: \"You don't have any document storage platforms connected (Google Drive, SharePoint, Notion, Confluence, or Box). Brand guidelines and style guides almost always live on one of these. Please connect at least one before running discovery. Gong\u002FGranola\u002FSlack transcripts are valuable supplements but unlikely to contain formal brand documents.\"\n\n2. **If no Google Drive AND no Microsoft 365 AND no Box**: **Warn** (but proceed): \"None of your primary file storage platforms (Google Drive, SharePoint, Box) are connected. Brand documents frequently live on these platforms. Discovery will proceed with [connected platforms], but results may have significant gaps. Consider connecting Google Drive or SharePoint.\"\n\n3. **If only one platform total is connected**: **Warn** (but proceed): \"Only [platform] is connected. Discovery works best with 2+ platforms for cross-source validation. Results from a single platform will have lower confidence scores.\"\n\n### 3. Confirm Scope with User\n\nBefore launching discovery, confirm:\n- Which platforms to search (default: all connected)\n- Whether to include conversation transcripts (Gong, Granola) or just documents\n- Any known locations to prioritize\n\nKeep this brief — one question, not a questionnaire.\n\n### 4. Delegate to Discover-Brand Agent\n\nLaunch the discover-brand agent via the Task tool. Provide:\n- Company name (from settings or user input)\n- Enabled platforms\n- Search depth\n- Any known URLs or locations to check first\n\nThe agent executes the 4-phase discovery algorithm autonomously:\n1. **Broad Discovery** — parallel searches across platforms\n2. **Source Triage** — categorize and rank sources\n3. **Deep Fetch** — retrieve and extract from top sources\n4. **Discovery Report** — structured output with open questions\n\n### 5. Present Discovery Report\n\nWhen the agent returns, present the report to the user with a summary:\n- Total sources found and analyzed\n- Key brand elements discovered\n- Any conflicts between sources\n- Open questions requiring team input\n\n### 6. Offer Next Steps\n\nAfter presenting the report, offer:\n1. **Generate guidelines now** — chain to `\u002Fbrand-voice:generate-guidelines` using discovery report as input\n2. **Resolve open questions first** — work through high-priority questions before generating\n3. **Save report** — store the discovery report to Notion or as a local file\n4. **Expand search** — search additional platforms or deeper if coverage is low\n\n## Open Questions\n\nOpen questions arise when the discovery agent encounters ambiguity it cannot resolve:\n- Conflicting documents (e.g., 2023 style guide vs. 2024 brand update)\n- Missing critical sections (e.g., no social media guidelines found)\n- Inconsistent terminology across platforms\n\nEvery open question includes an agent recommendation. Present questions as \"confirm or override\" — not dead ends.\n\n## Integration with Other Skills\n\n- **Guideline Generation**: The discovery report is returned by the discover-brand agent via the Task tool. Pass it directly to the guideline-generation skill as structured input, replacing the need for users to manually gather sources.\n- **Brand Voice Enforcement**: Once guidelines are generated from discovery, enforcement uses them automatically.\n\n## Error Handling\n\n- If zero platforms are connected, inform the user which platforms the plugin supports and how to connect them.\n- If all searches return empty results, flag the discovery as \"low coverage\" and suggest the user provide documents manually or check platform connections.\n- If a platform is connected but returns permission errors, note the gap and continue with other platforms.\n\n## Reference Files\n\nFor detailed discovery patterns and algorithms, consult:\n\n- **`references\u002Fsearch-strategies.md`** — Platform-specific search queries, query patterns by platform, and tips for maximizing discovery coverage\n- **`references\u002Fsource-ranking.md`** — Source category definitions, ranking algorithm weights, and triage decision criteria\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,51,57,64,71,76,81,136,141,146,152,165,194,199,205,210,220,228,238,246,251,317,323,328,346,351,357,362,385,390,433,439,444,467,473,478,529,535,540,558,563,569,592,598,616,622,627],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"brand-discovery",[48],{"type":49,"value":50},"text","Brand Discovery",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"Orchestrate autonomous discovery of brand materials across enterprise platforms. This skill coordinates the discover-brand agent to search connected platforms (Notion, Confluence, Google Drive, Box, Microsoft 365, Figma, Gong, Granola, Slack), triage sources, and produce a structured discovery report with open questions.",{"type":43,"tag":58,"props":59,"children":61},"h2",{"id":60},"discovery-workflow",[62],{"type":49,"value":63},"Discovery Workflow",{"type":43,"tag":65,"props":66,"children":68},"h3",{"id":67},"_0-orient-the-user",[69],{"type":49,"value":70},"0. Orient the User",{"type":43,"tag":52,"props":72,"children":73},{},[74],{"type":49,"value":75},"Before starting, briefly explain what's about to happen so the user knows what to expect:",{"type":43,"tag":52,"props":77,"children":78},{},[79],{"type":49,"value":80},"\"Here's how brand discovery works:",{"type":43,"tag":82,"props":83,"children":84},"ol",{},[85,97,107,117],{"type":43,"tag":86,"props":87,"children":88},"li",{},[89,95],{"type":43,"tag":90,"props":91,"children":92},"strong",{},[93],{"type":49,"value":94},"Search",{"type":49,"value":96}," — I'll search your connected platforms (Notion, Google Drive, Slack, etc.) for brand-related materials: style guides, pitch decks, templates, transcripts, and more.",{"type":43,"tag":86,"props":98,"children":99},{},[100,105],{"type":43,"tag":90,"props":101,"children":102},{},[103],{"type":49,"value":104},"Analyze",{"type":49,"value":106}," — I'll categorize and rank what I find, pull the best sources, and produce a discovery report with what I found, any conflicts, and open questions.",{"type":43,"tag":86,"props":108,"children":109},{},[110,115],{"type":43,"tag":90,"props":111,"children":112},{},[113],{"type":49,"value":114},"Generate guidelines",{"type":49,"value":116}," — Once you've reviewed the report, I can generate a structured brand voice guideline document from the results.",{"type":43,"tag":86,"props":118,"children":119},{},[120,125,127,134],{"type":43,"tag":90,"props":121,"children":122},{},[123],{"type":49,"value":124},"Save",{"type":49,"value":126}," — Guidelines are saved to ",{"type":43,"tag":128,"props":129,"children":131},"code",{"className":130},[],[132],{"type":49,"value":133},".claude\u002Fbrand-voice-guidelines.md",{"type":49,"value":135}," in your working folder once you approve them. Nothing is written until that step.",{"type":43,"tag":52,"props":137,"children":138},{},[139],{"type":49,"value":140},"The search usually takes a few minutes depending on how many platforms are connected. Ready to get started?\"",{"type":43,"tag":52,"props":142,"children":143},{},[144],{"type":49,"value":145},"Wait for the user to confirm before proceeding. If they have questions about the process, answer them first.",{"type":43,"tag":65,"props":147,"children":149},{"id":148},"_1-check-settings",[150],{"type":49,"value":151},"1. Check Settings",{"type":43,"tag":52,"props":153,"children":154},{},[155,157,163],{"type":49,"value":156},"Read ",{"type":43,"tag":128,"props":158,"children":160},{"className":159},[],[161],{"type":49,"value":162},".claude\u002Fbrand-voice.local.md",{"type":49,"value":164}," if it exists. Extract:",{"type":43,"tag":166,"props":167,"children":168},"ul",{},[169,174,179,184,189],{"type":43,"tag":86,"props":170,"children":171},{},[172],{"type":49,"value":173},"Company name",{"type":43,"tag":86,"props":175,"children":176},{},[177],{"type":49,"value":178},"Which platforms are enabled (notion, confluence, google-drive, box, microsoft-365, figma, gong, granola, slack)",{"type":43,"tag":86,"props":180,"children":181},{},[182],{"type":49,"value":183},"Search depth preference (standard or deep)",{"type":43,"tag":86,"props":185,"children":186},{},[187],{"type":49,"value":188},"Max sources limit",{"type":43,"tag":86,"props":190,"children":191},{},[192],{"type":49,"value":193},"Any known brand material locations listed under \"Known Brand Materials\"",{"type":43,"tag":52,"props":195,"children":196},{},[197],{"type":49,"value":198},"If no settings file exists, proceed with all connected platforms and standard search depth.",{"type":43,"tag":65,"props":200,"children":202},{"id":201},"_2-validate-platform-coverage",[203],{"type":49,"value":204},"2. Validate Platform Coverage",{"type":43,"tag":52,"props":206,"children":207},{},[208],{"type":49,"value":209},"Before confirming scope, check which platforms are actually connected and classify them:",{"type":43,"tag":52,"props":211,"children":212},{},[213,218],{"type":43,"tag":90,"props":214,"children":215},{},[216],{"type":49,"value":217},"Document platforms",{"type":49,"value":219}," (where brand guidelines, style guides, templates, and decks live):",{"type":43,"tag":166,"props":221,"children":222},{},[223],{"type":43,"tag":86,"props":224,"children":225},{},[226],{"type":49,"value":227},"Notion, Confluence, Google Drive, Box, Microsoft 365 (SharePoint\u002FOneDrive)",{"type":43,"tag":52,"props":229,"children":230},{},[231,236],{"type":43,"tag":90,"props":232,"children":233},{},[234],{"type":49,"value":235},"Supplementary platforms",{"type":49,"value":237}," (valuable for patterns, but not where brand docs are stored):",{"type":43,"tag":166,"props":239,"children":240},{},[241],{"type":43,"tag":86,"props":242,"children":243},{},[244],{"type":49,"value":245},"Slack, Gong, Granola, Figma",{"type":43,"tag":52,"props":247,"children":248},{},[249],{"type":49,"value":250},"Apply these rules:",{"type":43,"tag":82,"props":252,"children":253},{},[254,271,295],{"type":43,"tag":86,"props":255,"children":256},{},[257,262,264,269],{"type":43,"tag":90,"props":258,"children":259},{},[260],{"type":49,"value":261},"If zero document platforms are connected",{"type":49,"value":263},": ",{"type":43,"tag":90,"props":265,"children":266},{},[267],{"type":49,"value":268},"Stop.",{"type":49,"value":270}," Tell the user: \"You don't have any document storage platforms connected (Google Drive, SharePoint, Notion, Confluence, or Box). Brand guidelines and style guides almost always live on one of these. Please connect at least one before running discovery. Gong\u002FGranola\u002FSlack transcripts are valuable supplements but unlikely to contain formal brand documents.\"",{"type":43,"tag":86,"props":272,"children":273},{},[274,279,280,285,287,293],{"type":43,"tag":90,"props":275,"children":276},{},[277],{"type":49,"value":278},"If no Google Drive AND no Microsoft 365 AND no Box",{"type":49,"value":263},{"type":43,"tag":90,"props":281,"children":282},{},[283],{"type":49,"value":284},"Warn",{"type":49,"value":286}," (but proceed): \"None of your primary file storage platforms (Google Drive, SharePoint, Box) are connected. Brand documents frequently live on these platforms. Discovery will proceed with ",{"type":43,"tag":288,"props":289,"children":290},"span",{},[291],{"type":49,"value":292},"connected platforms",{"type":49,"value":294},", but results may have significant gaps. Consider connecting Google Drive or SharePoint.\"",{"type":43,"tag":86,"props":296,"children":297},{},[298,303,304,308,310,315],{"type":43,"tag":90,"props":299,"children":300},{},[301],{"type":49,"value":302},"If only one platform total is connected",{"type":49,"value":263},{"type":43,"tag":90,"props":305,"children":306},{},[307],{"type":49,"value":284},{"type":49,"value":309}," (but proceed): \"Only ",{"type":43,"tag":288,"props":311,"children":312},{},[313],{"type":49,"value":314},"platform",{"type":49,"value":316}," is connected. Discovery works best with 2+ platforms for cross-source validation. Results from a single platform will have lower confidence scores.\"",{"type":43,"tag":65,"props":318,"children":320},{"id":319},"_3-confirm-scope-with-user",[321],{"type":49,"value":322},"3. Confirm Scope with User",{"type":43,"tag":52,"props":324,"children":325},{},[326],{"type":49,"value":327},"Before launching discovery, confirm:",{"type":43,"tag":166,"props":329,"children":330},{},[331,336,341],{"type":43,"tag":86,"props":332,"children":333},{},[334],{"type":49,"value":335},"Which platforms to search (default: all connected)",{"type":43,"tag":86,"props":337,"children":338},{},[339],{"type":49,"value":340},"Whether to include conversation transcripts (Gong, Granola) or just documents",{"type":43,"tag":86,"props":342,"children":343},{},[344],{"type":49,"value":345},"Any known locations to prioritize",{"type":43,"tag":52,"props":347,"children":348},{},[349],{"type":49,"value":350},"Keep this brief — one question, not a questionnaire.",{"type":43,"tag":65,"props":352,"children":354},{"id":353},"_4-delegate-to-discover-brand-agent",[355],{"type":49,"value":356},"4. Delegate to Discover-Brand Agent",{"type":43,"tag":52,"props":358,"children":359},{},[360],{"type":49,"value":361},"Launch the discover-brand agent via the Task tool. Provide:",{"type":43,"tag":166,"props":363,"children":364},{},[365,370,375,380],{"type":43,"tag":86,"props":366,"children":367},{},[368],{"type":49,"value":369},"Company name (from settings or user input)",{"type":43,"tag":86,"props":371,"children":372},{},[373],{"type":49,"value":374},"Enabled platforms",{"type":43,"tag":86,"props":376,"children":377},{},[378],{"type":49,"value":379},"Search depth",{"type":43,"tag":86,"props":381,"children":382},{},[383],{"type":49,"value":384},"Any known URLs or locations to check first",{"type":43,"tag":52,"props":386,"children":387},{},[388],{"type":49,"value":389},"The agent executes the 4-phase discovery algorithm autonomously:",{"type":43,"tag":82,"props":391,"children":392},{},[393,403,413,423],{"type":43,"tag":86,"props":394,"children":395},{},[396,401],{"type":43,"tag":90,"props":397,"children":398},{},[399],{"type":49,"value":400},"Broad Discovery",{"type":49,"value":402}," — parallel searches across platforms",{"type":43,"tag":86,"props":404,"children":405},{},[406,411],{"type":43,"tag":90,"props":407,"children":408},{},[409],{"type":49,"value":410},"Source Triage",{"type":49,"value":412}," — categorize and rank sources",{"type":43,"tag":86,"props":414,"children":415},{},[416,421],{"type":43,"tag":90,"props":417,"children":418},{},[419],{"type":49,"value":420},"Deep Fetch",{"type":49,"value":422}," — retrieve and extract from top sources",{"type":43,"tag":86,"props":424,"children":425},{},[426,431],{"type":43,"tag":90,"props":427,"children":428},{},[429],{"type":49,"value":430},"Discovery Report",{"type":49,"value":432}," — structured output with open questions",{"type":43,"tag":65,"props":434,"children":436},{"id":435},"_5-present-discovery-report",[437],{"type":49,"value":438},"5. Present Discovery Report",{"type":43,"tag":52,"props":440,"children":441},{},[442],{"type":49,"value":443},"When the agent returns, present the report to the user with a summary:",{"type":43,"tag":166,"props":445,"children":446},{},[447,452,457,462],{"type":43,"tag":86,"props":448,"children":449},{},[450],{"type":49,"value":451},"Total sources found and analyzed",{"type":43,"tag":86,"props":453,"children":454},{},[455],{"type":49,"value":456},"Key brand elements discovered",{"type":43,"tag":86,"props":458,"children":459},{},[460],{"type":49,"value":461},"Any conflicts between sources",{"type":43,"tag":86,"props":463,"children":464},{},[465],{"type":49,"value":466},"Open questions requiring team input",{"type":43,"tag":65,"props":468,"children":470},{"id":469},"_6-offer-next-steps",[471],{"type":49,"value":472},"6. Offer Next Steps",{"type":43,"tag":52,"props":474,"children":475},{},[476],{"type":49,"value":477},"After presenting the report, offer:",{"type":43,"tag":82,"props":479,"children":480},{},[481,499,509,519],{"type":43,"tag":86,"props":482,"children":483},{},[484,489,491,497],{"type":43,"tag":90,"props":485,"children":486},{},[487],{"type":49,"value":488},"Generate guidelines now",{"type":49,"value":490}," — chain to ",{"type":43,"tag":128,"props":492,"children":494},{"className":493},[],[495],{"type":49,"value":496},"\u002Fbrand-voice:generate-guidelines",{"type":49,"value":498}," using discovery report as input",{"type":43,"tag":86,"props":500,"children":501},{},[502,507],{"type":43,"tag":90,"props":503,"children":504},{},[505],{"type":49,"value":506},"Resolve open questions first",{"type":49,"value":508}," — work through high-priority questions before generating",{"type":43,"tag":86,"props":510,"children":511},{},[512,517],{"type":43,"tag":90,"props":513,"children":514},{},[515],{"type":49,"value":516},"Save report",{"type":49,"value":518}," — store the discovery report to Notion or as a local file",{"type":43,"tag":86,"props":520,"children":521},{},[522,527],{"type":43,"tag":90,"props":523,"children":524},{},[525],{"type":49,"value":526},"Expand search",{"type":49,"value":528}," — search additional platforms or deeper if coverage is low",{"type":43,"tag":58,"props":530,"children":532},{"id":531},"open-questions",[533],{"type":49,"value":534},"Open Questions",{"type":43,"tag":52,"props":536,"children":537},{},[538],{"type":49,"value":539},"Open questions arise when the discovery agent encounters ambiguity it cannot resolve:",{"type":43,"tag":166,"props":541,"children":542},{},[543,548,553],{"type":43,"tag":86,"props":544,"children":545},{},[546],{"type":49,"value":547},"Conflicting documents (e.g., 2023 style guide vs. 2024 brand update)",{"type":43,"tag":86,"props":549,"children":550},{},[551],{"type":49,"value":552},"Missing critical sections (e.g., no social media guidelines found)",{"type":43,"tag":86,"props":554,"children":555},{},[556],{"type":49,"value":557},"Inconsistent terminology across platforms",{"type":43,"tag":52,"props":559,"children":560},{},[561],{"type":49,"value":562},"Every open question includes an agent recommendation. Present questions as \"confirm or override\" — not dead ends.",{"type":43,"tag":58,"props":564,"children":566},{"id":565},"integration-with-other-skills",[567],{"type":49,"value":568},"Integration with Other Skills",{"type":43,"tag":166,"props":570,"children":571},{},[572,582],{"type":43,"tag":86,"props":573,"children":574},{},[575,580],{"type":43,"tag":90,"props":576,"children":577},{},[578],{"type":49,"value":579},"Guideline Generation",{"type":49,"value":581},": The discovery report is returned by the discover-brand agent via the Task tool. Pass it directly to the guideline-generation skill as structured input, replacing the need for users to manually gather sources.",{"type":43,"tag":86,"props":583,"children":584},{},[585,590],{"type":43,"tag":90,"props":586,"children":587},{},[588],{"type":49,"value":589},"Brand Voice Enforcement",{"type":49,"value":591},": Once guidelines are generated from discovery, enforcement uses them automatically.",{"type":43,"tag":58,"props":593,"children":595},{"id":594},"error-handling",[596],{"type":49,"value":597},"Error Handling",{"type":43,"tag":166,"props":599,"children":600},{},[601,606,611],{"type":43,"tag":86,"props":602,"children":603},{},[604],{"type":49,"value":605},"If zero platforms are connected, inform the user which platforms the plugin supports and how to connect them.",{"type":43,"tag":86,"props":607,"children":608},{},[609],{"type":49,"value":610},"If all searches return empty results, flag the discovery as \"low coverage\" and suggest the user provide documents manually or check platform connections.",{"type":43,"tag":86,"props":612,"children":613},{},[614],{"type":49,"value":615},"If a platform is connected but returns permission errors, note the gap and continue with other platforms.",{"type":43,"tag":58,"props":617,"children":619},{"id":618},"reference-files",[620],{"type":49,"value":621},"Reference Files",{"type":43,"tag":52,"props":623,"children":624},{},[625],{"type":49,"value":626},"For detailed discovery patterns and algorithms, consult:",{"type":43,"tag":166,"props":628,"children":629},{},[630,644],{"type":43,"tag":86,"props":631,"children":632},{},[633,642],{"type":43,"tag":90,"props":634,"children":635},{},[636],{"type":43,"tag":128,"props":637,"children":639},{"className":638},[],[640],{"type":49,"value":641},"references\u002Fsearch-strategies.md",{"type":49,"value":643}," — Platform-specific search queries, query patterns by platform, and tips for maximizing discovery coverage",{"type":43,"tag":86,"props":645,"children":646},{},[647,656],{"type":43,"tag":90,"props":648,"children":649},{},[650],{"type":43,"tag":128,"props":651,"children":653},{"className":652},[],[654],{"type":49,"value":655},"references\u002Fsource-ranking.md",{"type":49,"value":657}," — Source category definitions, ranking algorithm weights, and triage decision criteria",{"items":659,"total":772},[660,676,692,708,726,745,757],{"slug":661,"name":661,"fn":662,"description":663,"org":664,"tags":665,"stars":26,"repoUrl":27,"updatedAt":675},"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},[666,669,672],{"name":667,"slug":668,"type":16},"Accessibility","accessibility",{"name":670,"slug":671,"type":16},"Design","design",{"name":673,"slug":674,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":677,"name":677,"fn":678,"description":679,"org":680,"tags":681,"stars":26,"repoUrl":27,"updatedAt":691},"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},[682,685,688],{"name":683,"slug":684,"type":16},"CRM","crm",{"name":686,"slug":687,"type":16},"Research","research",{"name":689,"slug":690,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":693,"name":693,"fn":694,"description":695,"org":696,"tags":697,"stars":26,"repoUrl":27,"updatedAt":707},"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},[698,701,704],{"name":699,"slug":700,"type":16},"Analytics","analytics",{"name":702,"slug":703,"type":16},"Data Analysis","data-analysis",{"name":705,"slug":706,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":709,"name":709,"fn":710,"description":711,"org":712,"tags":713,"stars":26,"repoUrl":27,"updatedAt":725},"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},[714,717,719,722],{"name":715,"slug":716,"type":16},"ADR","adr",{"name":718,"slug":709,"type":16},"Architecture",{"name":720,"slug":721,"type":16},"Documentation","documentation",{"name":723,"slug":724,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":727,"name":727,"fn":728,"description":729,"org":730,"tags":731,"stars":26,"repoUrl":27,"updatedAt":744},"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},[732,735,738,741],{"name":733,"slug":734,"type":16},"Audit","audit",{"name":736,"slug":737,"type":16},"Finance","finance",{"name":739,"slug":740,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":742,"slug":743,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":746,"name":746,"fn":747,"description":748,"org":749,"tags":750,"stars":26,"repoUrl":27,"updatedAt":756},"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},[751,752,753],{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":754,"slug":755,"type":16},"Writing","writing","2026-04-06T17:58:19.548331",{"slug":758,"name":758,"fn":759,"description":760,"org":761,"tags":762,"stars":26,"repoUrl":27,"updatedAt":771},"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},[763,764,767,770],{"name":24,"slug":25,"type":16},{"name":765,"slug":766,"type":16},"Communications","communications",{"name":768,"slug":769,"type":16},"Content Creation","content-creation",{"name":754,"slug":755,"type":16},"2026-04-06T18:00:23.528956",200,{"items":774,"total":951},[775,794,806,818,837,848,869,889,899,914,922,935],{"slug":776,"name":776,"fn":777,"description":778,"org":779,"tags":780,"stars":791,"repoUrl":792,"updatedAt":793},"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},[781,784,785,788],{"name":782,"slug":783,"type":16},"Creative","creative",{"name":670,"slug":671,"type":16},{"name":786,"slug":787,"type":16},"Generative Art","generative-art",{"name":789,"slug":790,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":795,"name":795,"fn":796,"description":797,"org":798,"tags":799,"stars":791,"repoUrl":792,"updatedAt":805},"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},[800,801,802],{"name":24,"slug":25,"type":16},{"name":670,"slug":671,"type":16},{"name":803,"slug":804,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":807,"name":807,"fn":808,"description":809,"org":810,"tags":811,"stars":791,"repoUrl":792,"updatedAt":817},"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},[812,813,814],{"name":782,"slug":783,"type":16},{"name":670,"slug":671,"type":16},{"name":815,"slug":816,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":819,"name":819,"fn":820,"description":821,"org":822,"tags":823,"stars":791,"repoUrl":792,"updatedAt":836},"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},[824,827,828,831,833],{"name":825,"slug":826,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":829,"slug":830,"type":16},"Anthropic SDK","anthropic-sdk",{"name":832,"slug":819,"type":16},"Claude API",{"name":834,"slug":835,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":838,"name":838,"fn":839,"description":840,"org":841,"tags":842,"stars":791,"repoUrl":792,"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},[843,844],{"name":720,"slug":721,"type":16},{"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":791,"repoUrl":792,"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":791,"repoUrl":792,"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":670,"slug":671,"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":791,"repoUrl":792,"updatedAt":898},"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},[895,896,897],{"name":765,"slug":766,"type":16},{"name":863,"slug":864,"type":16},{"name":754,"slug":755,"type":16},"2026-04-06T17:56:20.695522",{"slug":900,"name":900,"fn":901,"description":902,"org":903,"tags":904,"stars":791,"repoUrl":792,"updatedAt":913},"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},[905,906,909,910],{"name":825,"slug":826,"type":16},{"name":907,"slug":908,"type":16},"API Development","api-development",{"name":834,"slug":835,"type":16},{"name":911,"slug":912,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":816,"name":816,"fn":915,"description":916,"org":917,"tags":918,"stars":791,"repoUrl":792,"updatedAt":921},"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},[919,920],{"name":855,"slug":856,"type":16},{"name":815,"slug":816,"type":16},"2026-04-06T17:56:02.483316",{"slug":923,"name":923,"fn":924,"description":925,"org":926,"tags":927,"stars":791,"repoUrl":792,"updatedAt":934},"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},[928,931],{"name":929,"slug":930,"type":16},"PowerPoint","powerpoint",{"name":932,"slug":933,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":936,"name":936,"fn":937,"description":938,"org":939,"tags":940,"stars":791,"repoUrl":792,"updatedAt":950},"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},[941,942,943,946,949],{"name":825,"slug":826,"type":16},{"name":720,"slug":721,"type":16},{"name":944,"slug":945,"type":16},"Evals","evals",{"name":947,"slug":948,"type":16},"Performance","performance",{"name":845,"slug":846,"type":16},"2026-04-19T06:45:40.804",490]