[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-guideline-generation":3,"mdc-na27xq-key":37,"related-org-anthropic-guideline-generation":993,"related-repo-anthropic-guideline-generation":1178},{"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},"guideline-generation","generate brand voice guidelines","This skill generates, creates, or builds brand voice guidelines from source materials. It should be used when the user asks to \"generate brand guidelines\", \"create a style guide\", \"extract brand voice\", \"create guidelines from calls\", \"consolidate brand materials\", \"analyze my sales calls for brand voice\", \"build a brand playbook from documents\", \"synthesize a voice and tone guide\", or uploads brand documents, transcripts, or meeting recordings for brand analysis. Also triggers when the user has a discovery report and wants to convert it into actionable guidelines.\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},"Content Creation","content-creation","tag",{"name":18,"slug":19,"type":16},"Marketing","marketing",{"name":21,"slug":22,"type":16},"Writing","writing",{"name":24,"slug":25,"type":16},"Branding","branding",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T18:00:22.243121",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\u002Fguideline-generation","---\nname: guideline-generation\ndescription: >\n  This skill generates, creates, or builds brand voice guidelines from source\n  materials. It should be used when the user asks to \"generate brand guidelines\",\n  \"create a style guide\", \"extract brand voice\", \"create guidelines from calls\",\n  \"consolidate brand materials\", \"analyze my sales calls for brand voice\",\n  \"build a brand playbook from documents\", \"synthesize a voice and tone guide\",\n  or uploads brand documents, transcripts, or meeting recordings for brand\n  analysis. Also triggers when the user has a discovery report and wants to\n  convert it into actionable guidelines.\n---\n\n# Guideline Generation\n\nGenerate comprehensive, LLM-ready brand voice guidelines from any combination of sources — brand documents, sales call transcripts, discovery reports, or direct user input. Transform raw materials into structured, enforceable guidelines with confidence scoring and open questions.\n\n## Inputs\n\nAccept any combination of:\n- **Discovery report** from the discover-brand skill (structured, pre-triaged)\n- **Brand documents** uploaded or from connected platforms (PDF, PPTX, DOCX, MD, TXT)\n- **Conversation transcripts** from Gong, Granola, manual uploads, or Notion meeting notes\n- **Direct user input** about their brand voice and values\n\nWhen a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.\n\n## Generation Workflow\n\n### 1. Identify and Classify Sources\n\nDetermine what the user has provided. If no sources are available:\n- Check if a discovery report exists from a previous `\u002Fbrand-voice:discover-brand` run\n- Check `.claude\u002Fbrand-voice.local.md` for known brand material locations\n- Suggest running discovery first: `\u002Fbrand-voice:discover-brand`\n\n### 2. Process Sources\n\n**For documents:** Delegate to the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.\n\n**For transcripts:** Delegate to the conversation-analysis agent for pattern recognition. Extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.\n\n**For discovery reports:** Extract pre-triaged sources, conflicts, and gaps. Use the ranked sources directly.\n\n### 3. Synthesize Into Guidelines\n\nMerge all findings into a unified guideline document following the template in `references\u002Fguideline-template.md`. Key sections:\n\n**\"We Are \u002F We Are Not\" Table** — The core brand identity anchor:\n\n| We Are | We Are Not |\n|--------|------------|\n| [Attribute — e.g., \"Confident\"] | [Counter — e.g., \"Arrogant\"] |\n| [Attribute — e.g., \"Approachable\"] | [Counter — e.g., \"Casual or sloppy\"] |\n\nDerive attributes from the most consistent patterns across sources. Each row should have supporting evidence.\n\n**Voice Constants vs. Tone Flexes** — Clarify what stays fixed and what adapts:\n- **Voice** = personality, values, \"We Are \u002F We Are Not\" — constant across all content\n- **Tone** = formality, energy, technical depth — flexes by context\n\n**Tone-by-Context Matrix:**\n\n| Context | Formality | Energy | Technical Depth | Example |\n|---------|-----------|--------|-----------------|---------|\n| Cold outreach | Medium | High | Low | \"[example phrase]\" |\n| Enterprise proposal | High | Medium | High | \"[example phrase]\" |\n| Social media | Low | High | Low | \"[example phrase]\" |\n\n### 4. Assign Confidence Scores\n\nScore each section using the methodology in `references\u002Fconfidence-scoring.md`:\n- **High confidence**: 3+ corroborating sources, explicit guidance found\n- **Medium confidence**: 1-2 sources, or inferred from patterns\n- **Low confidence**: Single source, inferred, or conflicting data\n\n### 5. Surface Open Questions\n\nGenerate open questions for any ambiguity that cannot be resolved:\n\n```markdown\n## Open Questions for Team Discussion\n\n### High Priority (blocks guideline completion)\n1. **[Question Title]**\n   - What was found: [conflicting or incomplete info]\n   - Agent recommendation: [suggested resolution with reasoning]\n   - Need from you: [specific decision or confirmation needed]\n```\n\nEvery open question MUST include an agent recommendation. Turn ambiguity into \"confirm or override\" — never a dead end.\n\n### 6. Quality Check\n\nBefore presenting, verify via the quality-assurance agent (defined in `agents\u002Fquality-assurance.md`):\n- All major sections populated (including Brand Personality and Content Examples if sources support them)\n- At least 3 voice attributes with evidence\n- \"We Are \u002F We Are Not\" table has 4+ rows\n- Tone matrix covers at least 3 contexts\n- Confidence scores assigned per section\n- Source attribution for all extracted elements\n- No PII exposed\n- Open questions include recommendations\n\n### 7. Present and Offer Next Steps\n\nSummarize key findings:\n- Total sections generated with confidence breakdown\n- Strongest voice attribute and most effective message\n- Number of open questions (if any)\n\n### 8. Save for Future Sessions\n\nThe default save location is `.claude\u002Fbrand-voice-guidelines.md` inside the user's working folder.\n\n**Important:** The agent's working directory may not be the user's project root (especially in Cowork, where plugins run from a plugin cache directory). Always resolve the path relative to the user's working folder, not the current working directory. If no working folder is set, skip the file save and tell the user guidelines will only be available in this conversation.\n\n1. **Resolve the save path.** The file MUST be saved to `.claude\u002Fbrand-voice-guidelines.md` inside the user's working folder. Confirm the working folder path before writing.\n2. **Check if guidelines already exist** at that path\n3. **If they exist, archive the previous version:** Rename the existing file to `brand-voice-guidelines-YYYY-MM-DD.md` in the same directory (using today's date)\n4. **Save new guidelines** to `.claude\u002Fbrand-voice-guidelines.md` inside the working folder\n5. **Confirm to the user** with the full absolute path: \"Guidelines saved to `\u003Cfull-path>`. `\u002Fbrand-voice:enforce-voice` will find them automatically in future sessions.\"\n\nThe guidelines are also present in this conversation, so `\u002Fbrand-voice:enforce-voice` can use them immediately without loading from file.\n\nAfter saving, offer:\n1. Walk through the guidelines section by section\n2. Start creating content with `\u002Fbrand-voice:enforce-voice`\n3. Resolve open questions\n\n## Privacy and Security\n\nEnforce these privacy constraints throughout the entire generation workflow, not only at output time:\n- Redact customer names and contact information from all examples\n- Anonymize company names in transcript excerpts if requested\n- Flag any sensitive information detected during processing\n\n## Reference Files\n\n- **`references\u002Fguideline-template.md`** — Complete output template with all sections, field definitions, and formatting guidance\n- **`references\u002Fconfidence-scoring.md`** — Confidence scoring methodology, thresholds, and examples\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,56,63,68,114,119,125,132,137,177,183,193,203,213,219,232,242,309,314,324,347,355,484,490,503,536,542,547,666,671,677,690,733,739,744,762,768,781,791,883,895,900,923,929,934,952,958,987],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","Guideline Generation",{"type":43,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Generate comprehensive, LLM-ready brand voice guidelines from any combination of sources — brand documents, sales call transcripts, discovery reports, or direct user input. Transform raw materials into structured, enforceable guidelines with confidence scoring and open questions.",{"type":43,"tag":57,"props":58,"children":60},"h2",{"id":59},"inputs",[61],{"type":48,"value":62},"Inputs",{"type":43,"tag":51,"props":64,"children":65},{},[66],{"type":48,"value":67},"Accept any combination of:",{"type":43,"tag":69,"props":70,"children":71},"ul",{},[72,84,94,104],{"type":43,"tag":73,"props":74,"children":75},"li",{},[76,82],{"type":43,"tag":77,"props":78,"children":79},"strong",{},[80],{"type":48,"value":81},"Discovery report",{"type":48,"value":83}," from the discover-brand skill (structured, pre-triaged)",{"type":43,"tag":73,"props":85,"children":86},{},[87,92],{"type":43,"tag":77,"props":88,"children":89},{},[90],{"type":48,"value":91},"Brand documents",{"type":48,"value":93}," uploaded or from connected platforms (PDF, PPTX, DOCX, MD, TXT)",{"type":43,"tag":73,"props":95,"children":96},{},[97,102],{"type":43,"tag":77,"props":98,"children":99},{},[100],{"type":48,"value":101},"Conversation transcripts",{"type":48,"value":103}," from Gong, Granola, manual uploads, or Notion meeting notes",{"type":43,"tag":73,"props":105,"children":106},{},[107,112],{"type":43,"tag":77,"props":108,"children":109},{},[110],{"type":48,"value":111},"Direct user input",{"type":48,"value":113}," about their brand voice and values",{"type":43,"tag":51,"props":115,"children":116},{},[117],{"type":48,"value":118},"When a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.",{"type":43,"tag":57,"props":120,"children":122},{"id":121},"generation-workflow",[123],{"type":48,"value":124},"Generation Workflow",{"type":43,"tag":126,"props":127,"children":129},"h3",{"id":128},"_1-identify-and-classify-sources",[130],{"type":48,"value":131},"1. Identify and Classify Sources",{"type":43,"tag":51,"props":133,"children":134},{},[135],{"type":48,"value":136},"Determine what the user has provided. If no sources are available:",{"type":43,"tag":69,"props":138,"children":139},{},[140,154,167],{"type":43,"tag":73,"props":141,"children":142},{},[143,145,152],{"type":48,"value":144},"Check if a discovery report exists from a previous ",{"type":43,"tag":146,"props":147,"children":149},"code",{"className":148},[],[150],{"type":48,"value":151},"\u002Fbrand-voice:discover-brand",{"type":48,"value":153}," run",{"type":43,"tag":73,"props":155,"children":156},{},[157,159,165],{"type":48,"value":158},"Check ",{"type":43,"tag":146,"props":160,"children":162},{"className":161},[],[163],{"type":48,"value":164},".claude\u002Fbrand-voice.local.md",{"type":48,"value":166}," for known brand material locations",{"type":43,"tag":73,"props":168,"children":169},{},[170,172],{"type":48,"value":171},"Suggest running discovery first: ",{"type":43,"tag":146,"props":173,"children":175},{"className":174},[],[176],{"type":48,"value":151},{"type":43,"tag":126,"props":178,"children":180},{"id":179},"_2-process-sources",[181],{"type":48,"value":182},"2. Process Sources",{"type":43,"tag":51,"props":184,"children":185},{},[186,191],{"type":43,"tag":77,"props":187,"children":188},{},[189],{"type":48,"value":190},"For documents:",{"type":48,"value":192}," Delegate to the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.",{"type":43,"tag":51,"props":194,"children":195},{},[196,201],{"type":43,"tag":77,"props":197,"children":198},{},[199],{"type":48,"value":200},"For transcripts:",{"type":48,"value":202}," Delegate to the conversation-analysis agent for pattern recognition. Extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.",{"type":43,"tag":51,"props":204,"children":205},{},[206,211],{"type":43,"tag":77,"props":207,"children":208},{},[209],{"type":48,"value":210},"For discovery reports:",{"type":48,"value":212}," Extract pre-triaged sources, conflicts, and gaps. Use the ranked sources directly.",{"type":43,"tag":126,"props":214,"children":216},{"id":215},"_3-synthesize-into-guidelines",[217],{"type":48,"value":218},"3. Synthesize Into Guidelines",{"type":43,"tag":51,"props":220,"children":221},{},[222,224,230],{"type":48,"value":223},"Merge all findings into a unified guideline document following the template in ",{"type":43,"tag":146,"props":225,"children":227},{"className":226},[],[228],{"type":48,"value":229},"references\u002Fguideline-template.md",{"type":48,"value":231},". Key sections:",{"type":43,"tag":51,"props":233,"children":234},{},[235,240],{"type":43,"tag":77,"props":236,"children":237},{},[238],{"type":48,"value":239},"\"We Are \u002F We Are Not\" Table",{"type":48,"value":241}," — The core brand identity anchor:",{"type":43,"tag":243,"props":244,"children":245},"table",{},[246,265],{"type":43,"tag":247,"props":248,"children":249},"thead",{},[250],{"type":43,"tag":251,"props":252,"children":253},"tr",{},[254,260],{"type":43,"tag":255,"props":256,"children":257},"th",{},[258],{"type":48,"value":259},"We Are",{"type":43,"tag":255,"props":261,"children":262},{},[263],{"type":48,"value":264},"We Are Not",{"type":43,"tag":266,"props":267,"children":268},"tbody",{},[269,290],{"type":43,"tag":251,"props":270,"children":271},{},[272,282],{"type":43,"tag":273,"props":274,"children":275},"td",{},[276],{"type":43,"tag":277,"props":278,"children":279},"span",{},[280],{"type":48,"value":281},"Attribute — e.g., \"Confident\"",{"type":43,"tag":273,"props":283,"children":284},{},[285],{"type":43,"tag":277,"props":286,"children":287},{},[288],{"type":48,"value":289},"Counter — e.g., \"Arrogant\"",{"type":43,"tag":251,"props":291,"children":292},{},[293,301],{"type":43,"tag":273,"props":294,"children":295},{},[296],{"type":43,"tag":277,"props":297,"children":298},{},[299],{"type":48,"value":300},"Attribute — e.g., \"Approachable\"",{"type":43,"tag":273,"props":302,"children":303},{},[304],{"type":43,"tag":277,"props":305,"children":306},{},[307],{"type":48,"value":308},"Counter — e.g., \"Casual or sloppy\"",{"type":43,"tag":51,"props":310,"children":311},{},[312],{"type":48,"value":313},"Derive attributes from the most consistent patterns across sources. Each row should have supporting evidence.",{"type":43,"tag":51,"props":315,"children":316},{},[317,322],{"type":43,"tag":77,"props":318,"children":319},{},[320],{"type":48,"value":321},"Voice Constants vs. Tone Flexes",{"type":48,"value":323}," — Clarify what stays fixed and what adapts:",{"type":43,"tag":69,"props":325,"children":326},{},[327,337],{"type":43,"tag":73,"props":328,"children":329},{},[330,335],{"type":43,"tag":77,"props":331,"children":332},{},[333],{"type":48,"value":334},"Voice",{"type":48,"value":336}," = personality, values, \"We Are \u002F We Are Not\" — constant across all content",{"type":43,"tag":73,"props":338,"children":339},{},[340,345],{"type":43,"tag":77,"props":341,"children":342},{},[343],{"type":48,"value":344},"Tone",{"type":48,"value":346}," = formality, energy, technical depth — flexes by context",{"type":43,"tag":51,"props":348,"children":349},{},[350],{"type":43,"tag":77,"props":351,"children":352},{},[353],{"type":48,"value":354},"Tone-by-Context Matrix:",{"type":43,"tag":243,"props":356,"children":357},{},[358,389],{"type":43,"tag":247,"props":359,"children":360},{},[361],{"type":43,"tag":251,"props":362,"children":363},{},[364,369,374,379,384],{"type":43,"tag":255,"props":365,"children":366},{},[367],{"type":48,"value":368},"Context",{"type":43,"tag":255,"props":370,"children":371},{},[372],{"type":48,"value":373},"Formality",{"type":43,"tag":255,"props":375,"children":376},{},[377],{"type":48,"value":378},"Energy",{"type":43,"tag":255,"props":380,"children":381},{},[382],{"type":48,"value":383},"Technical Depth",{"type":43,"tag":255,"props":385,"children":386},{},[387],{"type":48,"value":388},"Example",{"type":43,"tag":266,"props":390,"children":391},{},[392,426,455],{"type":43,"tag":251,"props":393,"children":394},{},[395,400,405,410,415],{"type":43,"tag":273,"props":396,"children":397},{},[398],{"type":48,"value":399},"Cold outreach",{"type":43,"tag":273,"props":401,"children":402},{},[403],{"type":48,"value":404},"Medium",{"type":43,"tag":273,"props":406,"children":407},{},[408],{"type":48,"value":409},"High",{"type":43,"tag":273,"props":411,"children":412},{},[413],{"type":48,"value":414},"Low",{"type":43,"tag":273,"props":416,"children":417},{},[418,420,425],{"type":48,"value":419},"\"",{"type":43,"tag":277,"props":421,"children":422},{},[423],{"type":48,"value":424},"example phrase",{"type":48,"value":419},{"type":43,"tag":251,"props":427,"children":428},{},[429,434,438,442,446],{"type":43,"tag":273,"props":430,"children":431},{},[432],{"type":48,"value":433},"Enterprise proposal",{"type":43,"tag":273,"props":435,"children":436},{},[437],{"type":48,"value":409},{"type":43,"tag":273,"props":439,"children":440},{},[441],{"type":48,"value":404},{"type":43,"tag":273,"props":443,"children":444},{},[445],{"type":48,"value":409},{"type":43,"tag":273,"props":447,"children":448},{},[449,450,454],{"type":48,"value":419},{"type":43,"tag":277,"props":451,"children":452},{},[453],{"type":48,"value":424},{"type":48,"value":419},{"type":43,"tag":251,"props":456,"children":457},{},[458,463,467,471,475],{"type":43,"tag":273,"props":459,"children":460},{},[461],{"type":48,"value":462},"Social media",{"type":43,"tag":273,"props":464,"children":465},{},[466],{"type":48,"value":414},{"type":43,"tag":273,"props":468,"children":469},{},[470],{"type":48,"value":409},{"type":43,"tag":273,"props":472,"children":473},{},[474],{"type":48,"value":414},{"type":43,"tag":273,"props":476,"children":477},{},[478,479,483],{"type":48,"value":419},{"type":43,"tag":277,"props":480,"children":481},{},[482],{"type":48,"value":424},{"type":48,"value":419},{"type":43,"tag":126,"props":485,"children":487},{"id":486},"_4-assign-confidence-scores",[488],{"type":48,"value":489},"4. Assign Confidence Scores",{"type":43,"tag":51,"props":491,"children":492},{},[493,495,501],{"type":48,"value":494},"Score each section using the methodology in ",{"type":43,"tag":146,"props":496,"children":498},{"className":497},[],[499],{"type":48,"value":500},"references\u002Fconfidence-scoring.md",{"type":48,"value":502},":",{"type":43,"tag":69,"props":504,"children":505},{},[506,516,526],{"type":43,"tag":73,"props":507,"children":508},{},[509,514],{"type":43,"tag":77,"props":510,"children":511},{},[512],{"type":48,"value":513},"High confidence",{"type":48,"value":515},": 3+ corroborating sources, explicit guidance found",{"type":43,"tag":73,"props":517,"children":518},{},[519,524],{"type":43,"tag":77,"props":520,"children":521},{},[522],{"type":48,"value":523},"Medium confidence",{"type":48,"value":525},": 1-2 sources, or inferred from patterns",{"type":43,"tag":73,"props":527,"children":528},{},[529,534],{"type":43,"tag":77,"props":530,"children":531},{},[532],{"type":48,"value":533},"Low confidence",{"type":48,"value":535},": Single source, inferred, or conflicting data",{"type":43,"tag":126,"props":537,"children":539},{"id":538},"_5-surface-open-questions",[540],{"type":48,"value":541},"5. Surface Open Questions",{"type":43,"tag":51,"props":543,"children":544},{},[545],{"type":48,"value":546},"Generate open questions for any ambiguity that cannot be resolved:",{"type":43,"tag":548,"props":549,"children":554},"pre",{"className":550,"code":551,"language":552,"meta":553,"style":553},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","## Open Questions for Team Discussion\n\n### High Priority (blocks guideline completion)\n1. **[Question Title]**\n   - What was found: [conflicting or incomplete info]\n   - Agent recommendation: [suggested resolution with reasoning]\n   - Need from you: [specific decision or confirmation needed]\n","markdown","",[555],{"type":43,"tag":146,"props":556,"children":557},{"__ignoreMap":553},[558,575,585,599,625,640,653],{"type":43,"tag":277,"props":559,"children":562},{"class":560,"line":561},"line",1,[563,569],{"type":43,"tag":277,"props":564,"children":566},{"style":565},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[567],{"type":48,"value":568},"## ",{"type":43,"tag":277,"props":570,"children":572},{"style":571},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[573],{"type":48,"value":574},"Open Questions for Team Discussion\n",{"type":43,"tag":277,"props":576,"children":578},{"class":560,"line":577},2,[579],{"type":43,"tag":277,"props":580,"children":582},{"emptyLinePlaceholder":581},true,[583],{"type":48,"value":584},"\n",{"type":43,"tag":277,"props":586,"children":588},{"class":560,"line":587},3,[589,594],{"type":43,"tag":277,"props":590,"children":591},{"style":565},[592],{"type":48,"value":593},"### ",{"type":43,"tag":277,"props":595,"children":596},{"style":571},[597],{"type":48,"value":598},"High Priority (blocks guideline completion)\n",{"type":43,"tag":277,"props":600,"children":602},{"class":560,"line":601},4,[603,608,614,620],{"type":43,"tag":277,"props":604,"children":605},{"style":565},[606],{"type":48,"value":607},"1.",{"type":43,"tag":277,"props":609,"children":611},{"style":610},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[612],{"type":48,"value":613}," **",{"type":43,"tag":277,"props":615,"children":617},{"style":616},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[618],{"type":48,"value":619},"[Question Title]",{"type":43,"tag":277,"props":621,"children":622},{"style":610},[623],{"type":48,"value":624},"**\n",{"type":43,"tag":277,"props":626,"children":628},{"class":560,"line":627},5,[629,634],{"type":43,"tag":277,"props":630,"children":631},{"style":565},[632],{"type":48,"value":633},"   -",{"type":43,"tag":277,"props":635,"children":637},{"style":636},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[638],{"type":48,"value":639}," What was found: [conflicting or incomplete info]\n",{"type":43,"tag":277,"props":641,"children":643},{"class":560,"line":642},6,[644,648],{"type":43,"tag":277,"props":645,"children":646},{"style":565},[647],{"type":48,"value":633},{"type":43,"tag":277,"props":649,"children":650},{"style":636},[651],{"type":48,"value":652}," Agent recommendation: [suggested resolution with reasoning]\n",{"type":43,"tag":277,"props":654,"children":656},{"class":560,"line":655},7,[657,661],{"type":43,"tag":277,"props":658,"children":659},{"style":565},[660],{"type":48,"value":633},{"type":43,"tag":277,"props":662,"children":663},{"style":636},[664],{"type":48,"value":665}," Need from you: [specific decision or confirmation needed]\n",{"type":43,"tag":51,"props":667,"children":668},{},[669],{"type":48,"value":670},"Every open question MUST include an agent recommendation. Turn ambiguity into \"confirm or override\" — never a dead end.",{"type":43,"tag":126,"props":672,"children":674},{"id":673},"_6-quality-check",[675],{"type":48,"value":676},"6. Quality Check",{"type":43,"tag":51,"props":678,"children":679},{},[680,682,688],{"type":48,"value":681},"Before presenting, verify via the quality-assurance agent (defined in ",{"type":43,"tag":146,"props":683,"children":685},{"className":684},[],[686],{"type":48,"value":687},"agents\u002Fquality-assurance.md",{"type":48,"value":689},"):",{"type":43,"tag":69,"props":691,"children":692},{},[693,698,703,708,713,718,723,728],{"type":43,"tag":73,"props":694,"children":695},{},[696],{"type":48,"value":697},"All major sections populated (including Brand Personality and Content Examples if sources support them)",{"type":43,"tag":73,"props":699,"children":700},{},[701],{"type":48,"value":702},"At least 3 voice attributes with evidence",{"type":43,"tag":73,"props":704,"children":705},{},[706],{"type":48,"value":707},"\"We Are \u002F We Are Not\" table has 4+ rows",{"type":43,"tag":73,"props":709,"children":710},{},[711],{"type":48,"value":712},"Tone matrix covers at least 3 contexts",{"type":43,"tag":73,"props":714,"children":715},{},[716],{"type":48,"value":717},"Confidence scores assigned per section",{"type":43,"tag":73,"props":719,"children":720},{},[721],{"type":48,"value":722},"Source attribution for all extracted elements",{"type":43,"tag":73,"props":724,"children":725},{},[726],{"type":48,"value":727},"No PII exposed",{"type":43,"tag":73,"props":729,"children":730},{},[731],{"type":48,"value":732},"Open questions include recommendations",{"type":43,"tag":126,"props":734,"children":736},{"id":735},"_7-present-and-offer-next-steps",[737],{"type":48,"value":738},"7. Present and Offer Next Steps",{"type":43,"tag":51,"props":740,"children":741},{},[742],{"type":48,"value":743},"Summarize key findings:",{"type":43,"tag":69,"props":745,"children":746},{},[747,752,757],{"type":43,"tag":73,"props":748,"children":749},{},[750],{"type":48,"value":751},"Total sections generated with confidence breakdown",{"type":43,"tag":73,"props":753,"children":754},{},[755],{"type":48,"value":756},"Strongest voice attribute and most effective message",{"type":43,"tag":73,"props":758,"children":759},{},[760],{"type":48,"value":761},"Number of open questions (if any)",{"type":43,"tag":126,"props":763,"children":765},{"id":764},"_8-save-for-future-sessions",[766],{"type":48,"value":767},"8. Save for Future Sessions",{"type":43,"tag":51,"props":769,"children":770},{},[771,773,779],{"type":48,"value":772},"The default save location is ",{"type":43,"tag":146,"props":774,"children":776},{"className":775},[],[777],{"type":48,"value":778},".claude\u002Fbrand-voice-guidelines.md",{"type":48,"value":780}," inside the user's working folder.",{"type":43,"tag":51,"props":782,"children":783},{},[784,789],{"type":43,"tag":77,"props":785,"children":786},{},[787],{"type":48,"value":788},"Important:",{"type":48,"value":790}," The agent's working directory may not be the user's project root (especially in Cowork, where plugins run from a plugin cache directory). Always resolve the path relative to the user's working folder, not the current working directory. If no working folder is set, skip the file save and tell the user guidelines will only be available in this conversation.",{"type":43,"tag":792,"props":793,"children":794},"ol",{},[795,812,822,840,857],{"type":43,"tag":73,"props":796,"children":797},{},[798,803,805,810],{"type":43,"tag":77,"props":799,"children":800},{},[801],{"type":48,"value":802},"Resolve the save path.",{"type":48,"value":804}," The file MUST be saved to ",{"type":43,"tag":146,"props":806,"children":808},{"className":807},[],[809],{"type":48,"value":778},{"type":48,"value":811}," inside the user's working folder. Confirm the working folder path before writing.",{"type":43,"tag":73,"props":813,"children":814},{},[815,820],{"type":43,"tag":77,"props":816,"children":817},{},[818],{"type":48,"value":819},"Check if guidelines already exist",{"type":48,"value":821}," at that path",{"type":43,"tag":73,"props":823,"children":824},{},[825,830,832,838],{"type":43,"tag":77,"props":826,"children":827},{},[828],{"type":48,"value":829},"If they exist, archive the previous version:",{"type":48,"value":831}," Rename the existing file to ",{"type":43,"tag":146,"props":833,"children":835},{"className":834},[],[836],{"type":48,"value":837},"brand-voice-guidelines-YYYY-MM-DD.md",{"type":48,"value":839}," in the same directory (using today's date)",{"type":43,"tag":73,"props":841,"children":842},{},[843,848,850,855],{"type":43,"tag":77,"props":844,"children":845},{},[846],{"type":48,"value":847},"Save new guidelines",{"type":48,"value":849}," to ",{"type":43,"tag":146,"props":851,"children":853},{"className":852},[],[854],{"type":48,"value":778},{"type":48,"value":856}," inside the working folder",{"type":43,"tag":73,"props":858,"children":859},{},[860,865,867,873,875,881],{"type":43,"tag":77,"props":861,"children":862},{},[863],{"type":48,"value":864},"Confirm to the user",{"type":48,"value":866}," with the full absolute path: \"Guidelines saved to ",{"type":43,"tag":146,"props":868,"children":870},{"className":869},[],[871],{"type":48,"value":872},"\u003Cfull-path>",{"type":48,"value":874},". ",{"type":43,"tag":146,"props":876,"children":878},{"className":877},[],[879],{"type":48,"value":880},"\u002Fbrand-voice:enforce-voice",{"type":48,"value":882}," will find them automatically in future sessions.\"",{"type":43,"tag":51,"props":884,"children":885},{},[886,888,893],{"type":48,"value":887},"The guidelines are also present in this conversation, so ",{"type":43,"tag":146,"props":889,"children":891},{"className":890},[],[892],{"type":48,"value":880},{"type":48,"value":894}," can use them immediately without loading from file.",{"type":43,"tag":51,"props":896,"children":897},{},[898],{"type":48,"value":899},"After saving, offer:",{"type":43,"tag":792,"props":901,"children":902},{},[903,908,918],{"type":43,"tag":73,"props":904,"children":905},{},[906],{"type":48,"value":907},"Walk through the guidelines section by section",{"type":43,"tag":73,"props":909,"children":910},{},[911,913],{"type":48,"value":912},"Start creating content with ",{"type":43,"tag":146,"props":914,"children":916},{"className":915},[],[917],{"type":48,"value":880},{"type":43,"tag":73,"props":919,"children":920},{},[921],{"type":48,"value":922},"Resolve open questions",{"type":43,"tag":57,"props":924,"children":926},{"id":925},"privacy-and-security",[927],{"type":48,"value":928},"Privacy and Security",{"type":43,"tag":51,"props":930,"children":931},{},[932],{"type":48,"value":933},"Enforce these privacy constraints throughout the entire generation workflow, not only at output time:",{"type":43,"tag":69,"props":935,"children":936},{},[937,942,947],{"type":43,"tag":73,"props":938,"children":939},{},[940],{"type":48,"value":941},"Redact customer names and contact information from all examples",{"type":43,"tag":73,"props":943,"children":944},{},[945],{"type":48,"value":946},"Anonymize company names in transcript excerpts if requested",{"type":43,"tag":73,"props":948,"children":949},{},[950],{"type":48,"value":951},"Flag any sensitive information detected during processing",{"type":43,"tag":57,"props":953,"children":955},{"id":954},"reference-files",[956],{"type":48,"value":957},"Reference Files",{"type":43,"tag":69,"props":959,"children":960},{},[961,974],{"type":43,"tag":73,"props":962,"children":963},{},[964,972],{"type":43,"tag":77,"props":965,"children":966},{},[967],{"type":43,"tag":146,"props":968,"children":970},{"className":969},[],[971],{"type":48,"value":229},{"type":48,"value":973}," — Complete output template with all sections, field definitions, and formatting guidance",{"type":43,"tag":73,"props":975,"children":976},{},[977,985],{"type":43,"tag":77,"props":978,"children":979},{},[980],{"type":43,"tag":146,"props":981,"children":983},{"className":982},[],[984],{"type":48,"value":500},{"type":48,"value":986}," — Confidence scoring methodology, thresholds, and examples",{"type":43,"tag":988,"props":989,"children":990},"style",{},[991],{"type":48,"value":992},"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":994,"total":1177},[995,1016,1028,1040,1059,1072,1093,1113,1125,1140,1148,1161],{"slug":996,"name":996,"fn":997,"description":998,"org":999,"tags":1000,"stars":1013,"repoUrl":1014,"updatedAt":1015},"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},[1001,1004,1007,1010],{"name":1002,"slug":1003,"type":16},"Creative","creative",{"name":1005,"slug":1006,"type":16},"Design","design",{"name":1008,"slug":1009,"type":16},"Generative Art","generative-art",{"name":1011,"slug":1012,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1017,"name":1017,"fn":1018,"description":1019,"org":1020,"tags":1021,"stars":1013,"repoUrl":1014,"updatedAt":1027},"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},[1022,1023,1024],{"name":24,"slug":25,"type":16},{"name":1005,"slug":1006,"type":16},{"name":1025,"slug":1026,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1029,"name":1029,"fn":1030,"description":1031,"org":1032,"tags":1033,"stars":1013,"repoUrl":1014,"updatedAt":1039},"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},[1034,1035,1036],{"name":1002,"slug":1003,"type":16},{"name":1005,"slug":1006,"type":16},{"name":1037,"slug":1038,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1041,"name":1041,"fn":1042,"description":1043,"org":1044,"tags":1045,"stars":1013,"repoUrl":1014,"updatedAt":1058},"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},[1046,1049,1050,1053,1055],{"name":1047,"slug":1048,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1051,"slug":1052,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1054,"slug":1041,"type":16},"Claude API",{"name":1056,"slug":1057,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1060,"name":1060,"fn":1061,"description":1062,"org":1063,"tags":1064,"stars":1013,"repoUrl":1014,"updatedAt":1071},"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},[1065,1068],{"name":1066,"slug":1067,"type":16},"Documentation","documentation",{"name":1069,"slug":1070,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1076,"tags":1077,"stars":1013,"repoUrl":1014,"updatedAt":1092},"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},[1078,1081,1083,1086,1089],{"name":1079,"slug":1080,"type":16},"Documents","documents",{"name":1082,"slug":1073,"type":16},"DOCX",{"name":1084,"slug":1085,"type":16},"Office","office",{"name":1087,"slug":1088,"type":16},"Templates","templates",{"name":1090,"slug":1091,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1094,"name":1094,"fn":1095,"description":1096,"org":1097,"tags":1098,"stars":1013,"repoUrl":1014,"updatedAt":1112},"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},[1099,1100,1103,1106,1109],{"name":1005,"slug":1006,"type":16},{"name":1101,"slug":1102,"type":16},"Frontend","frontend",{"name":1104,"slug":1105,"type":16},"React","react",{"name":1107,"slug":1108,"type":16},"Tailwind CSS","tailwind-css",{"name":1110,"slug":1111,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1114,"name":1114,"fn":1115,"description":1116,"org":1117,"tags":1118,"stars":1013,"repoUrl":1014,"updatedAt":1124},"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},[1119,1122,1123],{"name":1120,"slug":1121,"type":16},"Communications","communications",{"name":1087,"slug":1088,"type":16},{"name":21,"slug":22,"type":16},"2026-04-06T17:56:20.695522",{"slug":1126,"name":1126,"fn":1127,"description":1128,"org":1129,"tags":1130,"stars":1013,"repoUrl":1014,"updatedAt":1139},"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},[1131,1132,1135,1136],{"name":1047,"slug":1048,"type":16},{"name":1133,"slug":1134,"type":16},"API Development","api-development",{"name":1056,"slug":1057,"type":16},{"name":1137,"slug":1138,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1038,"name":1038,"fn":1141,"description":1142,"org":1143,"tags":1144,"stars":1013,"repoUrl":1014,"updatedAt":1147},"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},[1145,1146],{"name":1079,"slug":1080,"type":16},{"name":1037,"slug":1038,"type":16},"2026-04-06T17:56:02.483316",{"slug":1149,"name":1149,"fn":1150,"description":1151,"org":1152,"tags":1153,"stars":1013,"repoUrl":1014,"updatedAt":1160},"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},[1154,1157],{"name":1155,"slug":1156,"type":16},"PowerPoint","powerpoint",{"name":1158,"slug":1159,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1162,"name":1162,"fn":1163,"description":1164,"org":1165,"tags":1166,"stars":1013,"repoUrl":1014,"updatedAt":1176},"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},[1167,1168,1169,1172,1175],{"name":1047,"slug":1048,"type":16},{"name":1066,"slug":1067,"type":16},{"name":1170,"slug":1171,"type":16},"Evals","evals",{"name":1173,"slug":1174,"type":16},"Performance","performance",{"name":1069,"slug":1070,"type":16},"2026-04-19T06:45:40.804",490,{"items":1179,"total":1282},[1180,1194,1210,1226,1242,1261,1271],{"slug":1181,"name":1181,"fn":1182,"description":1183,"org":1184,"tags":1185,"stars":26,"repoUrl":27,"updatedAt":1193},"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},[1186,1189,1190],{"name":1187,"slug":1188,"type":16},"Accessibility","accessibility",{"name":1005,"slug":1006,"type":16},{"name":1191,"slug":1192,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":1195,"name":1195,"fn":1196,"description":1197,"org":1198,"tags":1199,"stars":26,"repoUrl":27,"updatedAt":1209},"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},[1200,1203,1206],{"name":1201,"slug":1202,"type":16},"CRM","crm",{"name":1204,"slug":1205,"type":16},"Research","research",{"name":1207,"slug":1208,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":1211,"name":1211,"fn":1212,"description":1213,"org":1214,"tags":1215,"stars":26,"repoUrl":27,"updatedAt":1225},"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},[1216,1219,1222],{"name":1217,"slug":1218,"type":16},"Analytics","analytics",{"name":1220,"slug":1221,"type":16},"Data Analysis","data-analysis",{"name":1223,"slug":1224,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":1227,"name":1227,"fn":1228,"description":1229,"org":1230,"tags":1231,"stars":26,"repoUrl":27,"updatedAt":1241},"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},[1232,1235,1237,1238],{"name":1233,"slug":1234,"type":16},"ADR","adr",{"name":1236,"slug":1227,"type":16},"Architecture",{"name":1066,"slug":1067,"type":16},{"name":1239,"slug":1240,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":1243,"name":1243,"fn":1244,"description":1245,"org":1246,"tags":1247,"stars":26,"repoUrl":27,"updatedAt":1260},"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},[1248,1251,1254,1257],{"name":1249,"slug":1250,"type":16},"Audit","audit",{"name":1252,"slug":1253,"type":16},"Finance","finance",{"name":1255,"slug":1256,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1258,"slug":1259,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":1262,"name":1262,"fn":1263,"description":1264,"org":1265,"tags":1266,"stars":26,"repoUrl":27,"updatedAt":1270},"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},[1267,1268,1269],{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},"2026-04-06T17:58:19.548331",{"slug":1272,"name":1272,"fn":1273,"description":1274,"org":1275,"tags":1276,"stars":26,"repoUrl":27,"updatedAt":1281},"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},[1277,1278,1279,1280],{"name":24,"slug":25,"type":16},{"name":1120,"slug":1121,"type":16},{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},"2026-04-06T18:00:23.528956",200]