[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-knowledge-synthesis":3,"mdc--a672ec-key":37,"related-org-anthropic-knowledge-synthesis":852,"related-repo-anthropic-knowledge-synthesis":1041},{"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},"knowledge-synthesis","synthesize multi-source search results","Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.",{"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},"Summarization","summarization","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},"Search","search",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T17:58:41.217232",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\u002Fenterprise-search\u002Fskills\u002Fknowledge-synthesis","---\nname: knowledge-synthesis\ndescription: Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.\nuser-invocable: false\n---\n\n# Knowledge Synthesis\n\nThe last mile of enterprise search. Takes raw results from multiple sources and produces a coherent, trustworthy answer.\n\n## The Goal\n\nTransform this:\n```\n~~chat result: \"Sarah said in #eng: 'let's go with REST, GraphQL is overkill for our use case'\"\n~~email result: \"Subject: API Decision — Sarah's email confirming REST approach with rationale\"\n~~cloud storage result: \"API Design Doc v3 — updated section 2 to reflect REST decision\"\n~~project tracker result: \"Task: Finalize API approach — marked complete by Sarah\"\n```\n\nInto this:\n```\nThe team decided to go with REST over GraphQL for the API redesign. Sarah made the\ncall, noting that GraphQL was overkill for the current use case. This was discussed\nin #engineering on Tuesday, confirmed via email Wednesday, and the design doc has\nbeen updated to reflect the decision. The related ~~project tracker task is marked complete.\n\nSources:\n- ~~chat: #engineering thread (Jan 14)\n- ~~email: \"API Decision\" from Sarah (Jan 15)\n- ~~cloud storage: \"API Design Doc v3\" (updated Jan 15)\n- ~~project tracker: \"Finalize API approach\" (completed Jan 15)\n```\n\n## Deduplication\n\n### Cross-Source Deduplication\n\nThe same information often appears in multiple places. Identify and merge duplicates:\n\n**Signals that results are about the same thing:**\n- Same or very similar text content\n- Same author\u002Fsender\n- Timestamps within a short window (same day or adjacent days)\n- References to the same entity (project name, document, decision)\n- One source references another (\"as discussed in ~~chat\", \"per the email\", \"see the doc\")\n\n**How to merge:**\n- Combine into a single narrative item\n- Cite all sources where it appeared\n- Use the most complete version as the primary text\n- Add unique details from each source\n\n### Deduplication Priority\n\nWhen the same information exists in multiple sources, prefer:\n```\n1. The most complete version (fullest context)\n2. The most authoritative source (official doc > chat)\n3. The most recent version (latest update wins for evolving info)\n```\n\n### What NOT to Deduplicate\n\nKeep as separate items when:\n- The same topic is discussed but with different conclusions\n- Different people express different viewpoints\n- The information evolved meaningfully between sources (v1 vs v2 of a decision)\n- Different time periods are represented\n\n## Citation and Source Attribution\n\nEvery claim in the synthesized answer must be attributable to a source.\n\n### Attribution Format\n\nInline for direct references:\n```\nSarah confirmed the REST approach in her email on Wednesday.\nThe design doc was updated to reflect this (~~cloud storage: \"API Design Doc v3\").\n```\n\nSource list at the end for completeness:\n```\nSources:\n- ~~chat: #engineering discussion (Jan 14) — initial decision thread\n- ~~email: \"API Decision\" from Sarah Chen (Jan 15) — formal confirmation\n- ~~cloud storage: \"API Design Doc v3\" last modified Jan 15 — updated specification\n```\n\n### Attribution Rules\n\n- Always name the source type (~~chat, ~~email, ~~cloud storage, etc.)\n- Include the specific location (channel, folder, thread)\n- Include the date or relative time\n- Include the author when relevant\n- Include document\u002Fthread titles when available\n- For ~~chat, note the channel name\n- For ~~email, note the subject line and sender\n- For ~~cloud storage, note the document title\n\n## Confidence Levels\n\nNot all results are equally trustworthy. Assess confidence based on:\n\n### Freshness\n\n| Recency | Confidence impact |\n|---------|------------------|\n| Today \u002F yesterday | High confidence for current state |\n| This week | Good confidence |\n| This month | Moderate — things may have changed |\n| Older than a month | Lower confidence — flag as potentially outdated |\n\nFor status queries, heavily weight freshness. For policy\u002Ffactual queries, freshness matters less.\n\n### Authority\n\n| Source type | Authority level |\n|-------------|----------------|\n| Official wiki \u002F knowledge base | Highest — curated, maintained |\n| Shared documents (final versions) | High — intentionally published |\n| Email announcements | High — formal communication |\n| Meeting notes | Moderate-high — may be incomplete |\n| Chat messages (thread conclusions) | Moderate — informal but real-time |\n| Chat messages (mid-thread) | Lower — may not reflect final position |\n| Draft documents | Low — not finalized |\n| Task comments | Contextual — depends on commenter |\n\n### Expressing Confidence\n\nWhen confidence is high (multiple fresh, authoritative sources agree):\n```\nThe team decided to use REST for the API redesign. [direct statement]\n```\n\nWhen confidence is moderate (single source or somewhat dated):\n```\nBased on the discussion in #engineering last month, the team was leaning\ntoward REST for the API redesign. This may have evolved since then.\n```\n\nWhen confidence is low (old data, informal source, or conflicting signals):\n```\nI found a reference to an API migration discussion from three months ago\nin ~~chat, but I couldn't find a formal decision document. The information\nmay be outdated. You might want to check with the team for current status.\n```\n\n### Conflicting Information\n\nWhen sources disagree:\n```\nI found conflicting information about the API approach:\n- The ~~chat discussion on Jan 10 suggested GraphQL\n- But Sarah's email on Jan 15 confirmed REST\n- The design doc (updated Jan 15) reflects REST\n\nThe most recent sources indicate REST was the final decision,\nbut the earlier ~~chat discussion explored GraphQL first.\n```\n\nAlways surface conflicts rather than silently picking one version.\n\n## Summarization Strategies\n\n### For Small Result Sets (1-5 results)\n\nPresent each result with context. No summarization needed — give the user everything:\n```\n[Direct answer synthesized from results]\n\n[Detail from source 1]\n[Detail from source 2]\n\nSources: [full attribution]\n```\n\n### For Medium Result Sets (5-15 results)\n\nGroup by theme and summarize each group:\n```\n[Overall answer]\n\nTheme 1: [summary of related results]\nTheme 2: [summary of related results]\n\nKey sources: [top 3-5 most relevant sources]\nFull results: [count] items found across [sources]\n```\n\n### For Large Result Sets (15+ results)\n\nProvide a high-level synthesis with the option to drill down:\n```\n[Overall answer based on most relevant results]\n\nSummary:\n- [Key finding 1] (supported by N sources)\n- [Key finding 2] (supported by N sources)\n- [Key finding 3] (supported by N sources)\n\nTop sources:\n- [Most authoritative\u002Frelevant source]\n- [Second most relevant]\n- [Third most relevant]\n\nFound [total count] results across [source list].\nWant me to dig deeper into any specific aspect?\n```\n\n### Summarization Rules\n\n- Lead with the answer, not the search process\n- Do not list raw results — synthesize them into narrative\n- Group related items from different sources together\n- Preserve important nuance and caveats\n- Include enough detail that the user can decide whether to dig deeper\n- Always offer to provide more detail if the result set was large\n\n## Synthesis Workflow\n\n```\n[Raw results from all sources]\n          ↓\n[1. Deduplicate — merge same info from different sources]\n          ↓\n[2. Cluster — group related results by theme\u002Ftopic]\n          ↓\n[3. Rank — order clusters and items by relevance to query]\n          ↓\n[4. Assess confidence — freshness × authority × agreement]\n          ↓\n[5. Synthesize — produce narrative answer with attribution]\n          ↓\n[6. Format — choose appropriate detail level for result count]\n          ↓\n[Coherent answer with sources]\n```\n\n## Anti-Patterns\n\n**Do not:**\n- List results source by source (\"From ~~chat: ... From ~~email: ... From ~~cloud storage: ...\")\n- Include irrelevant results just because they matched a keyword\n- Bury the answer under methodology explanation\n- Present conflicting info without flagging the conflict\n- Omit source attribution\n- Present uncertain information with the same confidence as well-supported facts\n- Summarize so aggressively that useful detail is lost\n\n**Do:**\n- Lead with the answer\n- Group by topic, not by source\n- Flag confidence levels when appropriate\n- Surface conflicts explicitly\n- Attribute all claims to sources\n- Offer to go deeper when result sets are large\n",{"data":38,"body":40},{"name":4,"description":6,"user-invocable":39},false,{"type":41,"children":42},"root",[43,51,57,64,69,82,87,96,102,109,114,123,153,161,184,190,195,204,210,215,238,244,249,255,260,269,274,283,289,332,338,343,349,429,434,440,566,572,577,586,591,600,605,614,620,625,634,639,645,651,656,665,671,676,685,691,696,705,711,744,750,759,765,773,811,819],{"type":44,"tag":45,"props":46,"children":47},"element","h1",{"id":4},[48],{"type":49,"value":50},"text","Knowledge Synthesis",{"type":44,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"The last mile of enterprise search. Takes raw results from multiple sources and produces a coherent, trustworthy answer.",{"type":44,"tag":58,"props":59,"children":61},"h2",{"id":60},"the-goal",[62],{"type":49,"value":63},"The Goal",{"type":44,"tag":52,"props":65,"children":66},{},[67],{"type":49,"value":68},"Transform this:",{"type":44,"tag":70,"props":71,"children":75},"pre",{"className":72,"code":74,"language":49},[73],"language-text","~~chat result: \"Sarah said in #eng: 'let's go with REST, GraphQL is overkill for our use case'\"\n~~email result: \"Subject: API Decision — Sarah's email confirming REST approach with rationale\"\n~~cloud storage result: \"API Design Doc v3 — updated section 2 to reflect REST decision\"\n~~project tracker result: \"Task: Finalize API approach — marked complete by Sarah\"\n",[76],{"type":44,"tag":77,"props":78,"children":80},"code",{"__ignoreMap":79},"",[81],{"type":49,"value":74},{"type":44,"tag":52,"props":83,"children":84},{},[85],{"type":49,"value":86},"Into this:",{"type":44,"tag":70,"props":88,"children":91},{"className":89,"code":90,"language":49},[73],"The team decided to go with REST over GraphQL for the API redesign. Sarah made the\ncall, noting that GraphQL was overkill for the current use case. This was discussed\nin #engineering on Tuesday, confirmed via email Wednesday, and the design doc has\nbeen updated to reflect the decision. The related ~~project tracker task is marked complete.\n\nSources:\n- ~~chat: #engineering thread (Jan 14)\n- ~~email: \"API Decision\" from Sarah (Jan 15)\n- ~~cloud storage: \"API Design Doc v3\" (updated Jan 15)\n- ~~project tracker: \"Finalize API approach\" (completed Jan 15)\n",[92],{"type":44,"tag":77,"props":93,"children":94},{"__ignoreMap":79},[95],{"type":49,"value":90},{"type":44,"tag":58,"props":97,"children":99},{"id":98},"deduplication",[100],{"type":49,"value":101},"Deduplication",{"type":44,"tag":103,"props":104,"children":106},"h3",{"id":105},"cross-source-deduplication",[107],{"type":49,"value":108},"Cross-Source Deduplication",{"type":44,"tag":52,"props":110,"children":111},{},[112],{"type":49,"value":113},"The same information often appears in multiple places. Identify and merge duplicates:",{"type":44,"tag":52,"props":115,"children":116},{},[117],{"type":44,"tag":118,"props":119,"children":120},"strong",{},[121],{"type":49,"value":122},"Signals that results are about the same thing:",{"type":44,"tag":124,"props":125,"children":126},"ul",{},[127,133,138,143,148],{"type":44,"tag":128,"props":129,"children":130},"li",{},[131],{"type":49,"value":132},"Same or very similar text content",{"type":44,"tag":128,"props":134,"children":135},{},[136],{"type":49,"value":137},"Same author\u002Fsender",{"type":44,"tag":128,"props":139,"children":140},{},[141],{"type":49,"value":142},"Timestamps within a short window (same day or adjacent days)",{"type":44,"tag":128,"props":144,"children":145},{},[146],{"type":49,"value":147},"References to the same entity (project name, document, decision)",{"type":44,"tag":128,"props":149,"children":150},{},[151],{"type":49,"value":152},"One source references another (\"as discussed in ~~chat\", \"per the email\", \"see the doc\")",{"type":44,"tag":52,"props":154,"children":155},{},[156],{"type":44,"tag":118,"props":157,"children":158},{},[159],{"type":49,"value":160},"How to merge:",{"type":44,"tag":124,"props":162,"children":163},{},[164,169,174,179],{"type":44,"tag":128,"props":165,"children":166},{},[167],{"type":49,"value":168},"Combine into a single narrative item",{"type":44,"tag":128,"props":170,"children":171},{},[172],{"type":49,"value":173},"Cite all sources where it appeared",{"type":44,"tag":128,"props":175,"children":176},{},[177],{"type":49,"value":178},"Use the most complete version as the primary text",{"type":44,"tag":128,"props":180,"children":181},{},[182],{"type":49,"value":183},"Add unique details from each source",{"type":44,"tag":103,"props":185,"children":187},{"id":186},"deduplication-priority",[188],{"type":49,"value":189},"Deduplication Priority",{"type":44,"tag":52,"props":191,"children":192},{},[193],{"type":49,"value":194},"When the same information exists in multiple sources, prefer:",{"type":44,"tag":70,"props":196,"children":199},{"className":197,"code":198,"language":49},[73],"1. The most complete version (fullest context)\n2. The most authoritative source (official doc > chat)\n3. The most recent version (latest update wins for evolving info)\n",[200],{"type":44,"tag":77,"props":201,"children":202},{"__ignoreMap":79},[203],{"type":49,"value":198},{"type":44,"tag":103,"props":205,"children":207},{"id":206},"what-not-to-deduplicate",[208],{"type":49,"value":209},"What NOT to Deduplicate",{"type":44,"tag":52,"props":211,"children":212},{},[213],{"type":49,"value":214},"Keep as separate items when:",{"type":44,"tag":124,"props":216,"children":217},{},[218,223,228,233],{"type":44,"tag":128,"props":219,"children":220},{},[221],{"type":49,"value":222},"The same topic is discussed but with different conclusions",{"type":44,"tag":128,"props":224,"children":225},{},[226],{"type":49,"value":227},"Different people express different viewpoints",{"type":44,"tag":128,"props":229,"children":230},{},[231],{"type":49,"value":232},"The information evolved meaningfully between sources (v1 vs v2 of a decision)",{"type":44,"tag":128,"props":234,"children":235},{},[236],{"type":49,"value":237},"Different time periods are represented",{"type":44,"tag":58,"props":239,"children":241},{"id":240},"citation-and-source-attribution",[242],{"type":49,"value":243},"Citation and Source Attribution",{"type":44,"tag":52,"props":245,"children":246},{},[247],{"type":49,"value":248},"Every claim in the synthesized answer must be attributable to a source.",{"type":44,"tag":103,"props":250,"children":252},{"id":251},"attribution-format",[253],{"type":49,"value":254},"Attribution Format",{"type":44,"tag":52,"props":256,"children":257},{},[258],{"type":49,"value":259},"Inline for direct references:",{"type":44,"tag":70,"props":261,"children":264},{"className":262,"code":263,"language":49},[73],"Sarah confirmed the REST approach in her email on Wednesday.\nThe design doc was updated to reflect this (~~cloud storage: \"API Design Doc v3\").\n",[265],{"type":44,"tag":77,"props":266,"children":267},{"__ignoreMap":79},[268],{"type":49,"value":263},{"type":44,"tag":52,"props":270,"children":271},{},[272],{"type":49,"value":273},"Source list at the end for completeness:",{"type":44,"tag":70,"props":275,"children":278},{"className":276,"code":277,"language":49},[73],"Sources:\n- ~~chat: #engineering discussion (Jan 14) — initial decision thread\n- ~~email: \"API Decision\" from Sarah Chen (Jan 15) — formal confirmation\n- ~~cloud storage: \"API Design Doc v3\" last modified Jan 15 — updated specification\n",[279],{"type":44,"tag":77,"props":280,"children":281},{"__ignoreMap":79},[282],{"type":49,"value":277},{"type":44,"tag":103,"props":284,"children":286},{"id":285},"attribution-rules",[287],{"type":49,"value":288},"Attribution Rules",{"type":44,"tag":124,"props":290,"children":291},{},[292,297,302,307,312,317,322,327],{"type":44,"tag":128,"props":293,"children":294},{},[295],{"type":49,"value":296},"Always name the source type (~~chat, ~~email, ~~cloud storage, etc.)",{"type":44,"tag":128,"props":298,"children":299},{},[300],{"type":49,"value":301},"Include the specific location (channel, folder, thread)",{"type":44,"tag":128,"props":303,"children":304},{},[305],{"type":49,"value":306},"Include the date or relative time",{"type":44,"tag":128,"props":308,"children":309},{},[310],{"type":49,"value":311},"Include the author when relevant",{"type":44,"tag":128,"props":313,"children":314},{},[315],{"type":49,"value":316},"Include document\u002Fthread titles when available",{"type":44,"tag":128,"props":318,"children":319},{},[320],{"type":49,"value":321},"For ~~chat, note the channel name",{"type":44,"tag":128,"props":323,"children":324},{},[325],{"type":49,"value":326},"For ~~email, note the subject line and sender",{"type":44,"tag":128,"props":328,"children":329},{},[330],{"type":49,"value":331},"For ~~cloud storage, note the document title",{"type":44,"tag":58,"props":333,"children":335},{"id":334},"confidence-levels",[336],{"type":49,"value":337},"Confidence Levels",{"type":44,"tag":52,"props":339,"children":340},{},[341],{"type":49,"value":342},"Not all results are equally trustworthy. Assess confidence based on:",{"type":44,"tag":103,"props":344,"children":346},{"id":345},"freshness",[347],{"type":49,"value":348},"Freshness",{"type":44,"tag":350,"props":351,"children":352},"table",{},[353,372],{"type":44,"tag":354,"props":355,"children":356},"thead",{},[357],{"type":44,"tag":358,"props":359,"children":360},"tr",{},[361,367],{"type":44,"tag":362,"props":363,"children":364},"th",{},[365],{"type":49,"value":366},"Recency",{"type":44,"tag":362,"props":368,"children":369},{},[370],{"type":49,"value":371},"Confidence impact",{"type":44,"tag":373,"props":374,"children":375},"tbody",{},[376,390,403,416],{"type":44,"tag":358,"props":377,"children":378},{},[379,385],{"type":44,"tag":380,"props":381,"children":382},"td",{},[383],{"type":49,"value":384},"Today \u002F yesterday",{"type":44,"tag":380,"props":386,"children":387},{},[388],{"type":49,"value":389},"High confidence for current state",{"type":44,"tag":358,"props":391,"children":392},{},[393,398],{"type":44,"tag":380,"props":394,"children":395},{},[396],{"type":49,"value":397},"This week",{"type":44,"tag":380,"props":399,"children":400},{},[401],{"type":49,"value":402},"Good confidence",{"type":44,"tag":358,"props":404,"children":405},{},[406,411],{"type":44,"tag":380,"props":407,"children":408},{},[409],{"type":49,"value":410},"This month",{"type":44,"tag":380,"props":412,"children":413},{},[414],{"type":49,"value":415},"Moderate — things may have changed",{"type":44,"tag":358,"props":417,"children":418},{},[419,424],{"type":44,"tag":380,"props":420,"children":421},{},[422],{"type":49,"value":423},"Older than a month",{"type":44,"tag":380,"props":425,"children":426},{},[427],{"type":49,"value":428},"Lower confidence — flag as potentially outdated",{"type":44,"tag":52,"props":430,"children":431},{},[432],{"type":49,"value":433},"For status queries, heavily weight freshness. For policy\u002Ffactual queries, freshness matters less.",{"type":44,"tag":103,"props":435,"children":437},{"id":436},"authority",[438],{"type":49,"value":439},"Authority",{"type":44,"tag":350,"props":441,"children":442},{},[443,459],{"type":44,"tag":354,"props":444,"children":445},{},[446],{"type":44,"tag":358,"props":447,"children":448},{},[449,454],{"type":44,"tag":362,"props":450,"children":451},{},[452],{"type":49,"value":453},"Source type",{"type":44,"tag":362,"props":455,"children":456},{},[457],{"type":49,"value":458},"Authority level",{"type":44,"tag":373,"props":460,"children":461},{},[462,475,488,501,514,527,540,553],{"type":44,"tag":358,"props":463,"children":464},{},[465,470],{"type":44,"tag":380,"props":466,"children":467},{},[468],{"type":49,"value":469},"Official wiki \u002F knowledge base",{"type":44,"tag":380,"props":471,"children":472},{},[473],{"type":49,"value":474},"Highest — curated, maintained",{"type":44,"tag":358,"props":476,"children":477},{},[478,483],{"type":44,"tag":380,"props":479,"children":480},{},[481],{"type":49,"value":482},"Shared documents (final versions)",{"type":44,"tag":380,"props":484,"children":485},{},[486],{"type":49,"value":487},"High — intentionally published",{"type":44,"tag":358,"props":489,"children":490},{},[491,496],{"type":44,"tag":380,"props":492,"children":493},{},[494],{"type":49,"value":495},"Email announcements",{"type":44,"tag":380,"props":497,"children":498},{},[499],{"type":49,"value":500},"High — formal communication",{"type":44,"tag":358,"props":502,"children":503},{},[504,509],{"type":44,"tag":380,"props":505,"children":506},{},[507],{"type":49,"value":508},"Meeting notes",{"type":44,"tag":380,"props":510,"children":511},{},[512],{"type":49,"value":513},"Moderate-high — may be incomplete",{"type":44,"tag":358,"props":515,"children":516},{},[517,522],{"type":44,"tag":380,"props":518,"children":519},{},[520],{"type":49,"value":521},"Chat messages (thread conclusions)",{"type":44,"tag":380,"props":523,"children":524},{},[525],{"type":49,"value":526},"Moderate — informal but real-time",{"type":44,"tag":358,"props":528,"children":529},{},[530,535],{"type":44,"tag":380,"props":531,"children":532},{},[533],{"type":49,"value":534},"Chat messages (mid-thread)",{"type":44,"tag":380,"props":536,"children":537},{},[538],{"type":49,"value":539},"Lower — may not reflect final position",{"type":44,"tag":358,"props":541,"children":542},{},[543,548],{"type":44,"tag":380,"props":544,"children":545},{},[546],{"type":49,"value":547},"Draft documents",{"type":44,"tag":380,"props":549,"children":550},{},[551],{"type":49,"value":552},"Low — not finalized",{"type":44,"tag":358,"props":554,"children":555},{},[556,561],{"type":44,"tag":380,"props":557,"children":558},{},[559],{"type":49,"value":560},"Task comments",{"type":44,"tag":380,"props":562,"children":563},{},[564],{"type":49,"value":565},"Contextual — depends on commenter",{"type":44,"tag":103,"props":567,"children":569},{"id":568},"expressing-confidence",[570],{"type":49,"value":571},"Expressing Confidence",{"type":44,"tag":52,"props":573,"children":574},{},[575],{"type":49,"value":576},"When confidence is high (multiple fresh, authoritative sources agree):",{"type":44,"tag":70,"props":578,"children":581},{"className":579,"code":580,"language":49},[73],"The team decided to use REST for the API redesign. [direct statement]\n",[582],{"type":44,"tag":77,"props":583,"children":584},{"__ignoreMap":79},[585],{"type":49,"value":580},{"type":44,"tag":52,"props":587,"children":588},{},[589],{"type":49,"value":590},"When confidence is moderate (single source or somewhat dated):",{"type":44,"tag":70,"props":592,"children":595},{"className":593,"code":594,"language":49},[73],"Based on the discussion in #engineering last month, the team was leaning\ntoward REST for the API redesign. This may have evolved since then.\n",[596],{"type":44,"tag":77,"props":597,"children":598},{"__ignoreMap":79},[599],{"type":49,"value":594},{"type":44,"tag":52,"props":601,"children":602},{},[603],{"type":49,"value":604},"When confidence is low (old data, informal source, or conflicting signals):",{"type":44,"tag":70,"props":606,"children":609},{"className":607,"code":608,"language":49},[73],"I found a reference to an API migration discussion from three months ago\nin ~~chat, but I couldn't find a formal decision document. The information\nmay be outdated. You might want to check with the team for current status.\n",[610],{"type":44,"tag":77,"props":611,"children":612},{"__ignoreMap":79},[613],{"type":49,"value":608},{"type":44,"tag":103,"props":615,"children":617},{"id":616},"conflicting-information",[618],{"type":49,"value":619},"Conflicting Information",{"type":44,"tag":52,"props":621,"children":622},{},[623],{"type":49,"value":624},"When sources disagree:",{"type":44,"tag":70,"props":626,"children":629},{"className":627,"code":628,"language":49},[73],"I found conflicting information about the API approach:\n- The ~~chat discussion on Jan 10 suggested GraphQL\n- But Sarah's email on Jan 15 confirmed REST\n- The design doc (updated Jan 15) reflects REST\n\nThe most recent sources indicate REST was the final decision,\nbut the earlier ~~chat discussion explored GraphQL first.\n",[630],{"type":44,"tag":77,"props":631,"children":632},{"__ignoreMap":79},[633],{"type":49,"value":628},{"type":44,"tag":52,"props":635,"children":636},{},[637],{"type":49,"value":638},"Always surface conflicts rather than silently picking one version.",{"type":44,"tag":58,"props":640,"children":642},{"id":641},"summarization-strategies",[643],{"type":49,"value":644},"Summarization Strategies",{"type":44,"tag":103,"props":646,"children":648},{"id":647},"for-small-result-sets-1-5-results",[649],{"type":49,"value":650},"For Small Result Sets (1-5 results)",{"type":44,"tag":52,"props":652,"children":653},{},[654],{"type":49,"value":655},"Present each result with context. No summarization needed — give the user everything:",{"type":44,"tag":70,"props":657,"children":660},{"className":658,"code":659,"language":49},[73],"[Direct answer synthesized from results]\n\n[Detail from source 1]\n[Detail from source 2]\n\nSources: [full attribution]\n",[661],{"type":44,"tag":77,"props":662,"children":663},{"__ignoreMap":79},[664],{"type":49,"value":659},{"type":44,"tag":103,"props":666,"children":668},{"id":667},"for-medium-result-sets-5-15-results",[669],{"type":49,"value":670},"For Medium Result Sets (5-15 results)",{"type":44,"tag":52,"props":672,"children":673},{},[674],{"type":49,"value":675},"Group by theme and summarize each group:",{"type":44,"tag":70,"props":677,"children":680},{"className":678,"code":679,"language":49},[73],"[Overall answer]\n\nTheme 1: [summary of related results]\nTheme 2: [summary of related results]\n\nKey sources: [top 3-5 most relevant sources]\nFull results: [count] items found across [sources]\n",[681],{"type":44,"tag":77,"props":682,"children":683},{"__ignoreMap":79},[684],{"type":49,"value":679},{"type":44,"tag":103,"props":686,"children":688},{"id":687},"for-large-result-sets-15-results",[689],{"type":49,"value":690},"For Large Result Sets (15+ results)",{"type":44,"tag":52,"props":692,"children":693},{},[694],{"type":49,"value":695},"Provide a high-level synthesis with the option to drill down:",{"type":44,"tag":70,"props":697,"children":700},{"className":698,"code":699,"language":49},[73],"[Overall answer based on most relevant results]\n\nSummary:\n- [Key finding 1] (supported by N sources)\n- [Key finding 2] (supported by N sources)\n- [Key finding 3] (supported by N sources)\n\nTop sources:\n- [Most authoritative\u002Frelevant source]\n- [Second most relevant]\n- [Third most relevant]\n\nFound [total count] results across [source list].\nWant me to dig deeper into any specific aspect?\n",[701],{"type":44,"tag":77,"props":702,"children":703},{"__ignoreMap":79},[704],{"type":49,"value":699},{"type":44,"tag":103,"props":706,"children":708},{"id":707},"summarization-rules",[709],{"type":49,"value":710},"Summarization Rules",{"type":44,"tag":124,"props":712,"children":713},{},[714,719,724,729,734,739],{"type":44,"tag":128,"props":715,"children":716},{},[717],{"type":49,"value":718},"Lead with the answer, not the search process",{"type":44,"tag":128,"props":720,"children":721},{},[722],{"type":49,"value":723},"Do not list raw results — synthesize them into narrative",{"type":44,"tag":128,"props":725,"children":726},{},[727],{"type":49,"value":728},"Group related items from different sources together",{"type":44,"tag":128,"props":730,"children":731},{},[732],{"type":49,"value":733},"Preserve important nuance and caveats",{"type":44,"tag":128,"props":735,"children":736},{},[737],{"type":49,"value":738},"Include enough detail that the user can decide whether to dig deeper",{"type":44,"tag":128,"props":740,"children":741},{},[742],{"type":49,"value":743},"Always offer to provide more detail if the result set was large",{"type":44,"tag":58,"props":745,"children":747},{"id":746},"synthesis-workflow",[748],{"type":49,"value":749},"Synthesis Workflow",{"type":44,"tag":70,"props":751,"children":754},{"className":752,"code":753,"language":49},[73],"[Raw results from all sources]\n          ↓\n[1. Deduplicate — merge same info from different sources]\n          ↓\n[2. Cluster — group related results by theme\u002Ftopic]\n          ↓\n[3. Rank — order clusters and items by relevance to query]\n          ↓\n[4. Assess confidence — freshness × authority × agreement]\n          ↓\n[5. Synthesize — produce narrative answer with attribution]\n          ↓\n[6. Format — choose appropriate detail level for result count]\n          ↓\n[Coherent answer with sources]\n",[755],{"type":44,"tag":77,"props":756,"children":757},{"__ignoreMap":79},[758],{"type":49,"value":753},{"type":44,"tag":58,"props":760,"children":762},{"id":761},"anti-patterns",[763],{"type":49,"value":764},"Anti-Patterns",{"type":44,"tag":52,"props":766,"children":767},{},[768],{"type":44,"tag":118,"props":769,"children":770},{},[771],{"type":49,"value":772},"Do not:",{"type":44,"tag":124,"props":774,"children":775},{},[776,781,786,791,796,801,806],{"type":44,"tag":128,"props":777,"children":778},{},[779],{"type":49,"value":780},"List results source by source (\"From ~~chat: ... From ~~email: ... From ~~cloud storage: ...\")",{"type":44,"tag":128,"props":782,"children":783},{},[784],{"type":49,"value":785},"Include irrelevant results just because they matched a keyword",{"type":44,"tag":128,"props":787,"children":788},{},[789],{"type":49,"value":790},"Bury the answer under methodology explanation",{"type":44,"tag":128,"props":792,"children":793},{},[794],{"type":49,"value":795},"Present conflicting info without flagging the conflict",{"type":44,"tag":128,"props":797,"children":798},{},[799],{"type":49,"value":800},"Omit source attribution",{"type":44,"tag":128,"props":802,"children":803},{},[804],{"type":49,"value":805},"Present uncertain information with the same confidence as well-supported facts",{"type":44,"tag":128,"props":807,"children":808},{},[809],{"type":49,"value":810},"Summarize so aggressively that useful detail is lost",{"type":44,"tag":52,"props":812,"children":813},{},[814],{"type":44,"tag":118,"props":815,"children":816},{},[817],{"type":49,"value":818},"Do:",{"type":44,"tag":124,"props":820,"children":821},{},[822,827,832,837,842,847],{"type":44,"tag":128,"props":823,"children":824},{},[825],{"type":49,"value":826},"Lead with the answer",{"type":44,"tag":128,"props":828,"children":829},{},[830],{"type":49,"value":831},"Group by topic, not by source",{"type":44,"tag":128,"props":833,"children":834},{},[835],{"type":49,"value":836},"Flag confidence levels when appropriate",{"type":44,"tag":128,"props":838,"children":839},{},[840],{"type":49,"value":841},"Surface conflicts explicitly",{"type":44,"tag":128,"props":843,"children":844},{},[845],{"type":49,"value":846},"Attribute all claims to sources",{"type":44,"tag":128,"props":848,"children":849},{},[850],{"type":49,"value":851},"Offer to go deeper when result sets are large",{"items":853,"total":1040},[854,875,889,901,920,933,954,974,988,1003,1011,1024],{"slug":855,"name":855,"fn":856,"description":857,"org":858,"tags":859,"stars":872,"repoUrl":873,"updatedAt":874},"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},[860,863,866,869],{"name":861,"slug":862,"type":16},"Creative","creative",{"name":864,"slug":865,"type":16},"Design","design",{"name":867,"slug":868,"type":16},"Generative Art","generative-art",{"name":870,"slug":871,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":876,"name":876,"fn":877,"description":878,"org":879,"tags":880,"stars":872,"repoUrl":873,"updatedAt":888},"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},[881,884,885],{"name":882,"slug":883,"type":16},"Branding","branding",{"name":864,"slug":865,"type":16},{"name":886,"slug":887,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":872,"repoUrl":873,"updatedAt":900},"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},[895,896,897],{"name":861,"slug":862,"type":16},{"name":864,"slug":865,"type":16},{"name":898,"slug":899,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":902,"name":902,"fn":903,"description":904,"org":905,"tags":906,"stars":872,"repoUrl":873,"updatedAt":919},"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},[907,910,911,914,916],{"name":908,"slug":909,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":912,"slug":913,"type":16},"Anthropic SDK","anthropic-sdk",{"name":915,"slug":902,"type":16},"Claude API",{"name":917,"slug":918,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":921,"name":921,"fn":922,"description":923,"org":924,"tags":925,"stars":872,"repoUrl":873,"updatedAt":932},"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},[926,929],{"name":927,"slug":928,"type":16},"Documentation","documentation",{"name":930,"slug":931,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":934,"name":934,"fn":935,"description":936,"org":937,"tags":938,"stars":872,"repoUrl":873,"updatedAt":953},"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},[939,942,944,947,950],{"name":940,"slug":941,"type":16},"Documents","documents",{"name":943,"slug":934,"type":16},"DOCX",{"name":945,"slug":946,"type":16},"Office","office",{"name":948,"slug":949,"type":16},"Templates","templates",{"name":951,"slug":952,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":955,"name":955,"fn":956,"description":957,"org":958,"tags":959,"stars":872,"repoUrl":873,"updatedAt":973},"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},[960,961,964,967,970],{"name":864,"slug":865,"type":16},{"name":962,"slug":963,"type":16},"Frontend","frontend",{"name":965,"slug":966,"type":16},"React","react",{"name":968,"slug":969,"type":16},"Tailwind CSS","tailwind-css",{"name":971,"slug":972,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":975,"name":975,"fn":976,"description":977,"org":978,"tags":979,"stars":872,"repoUrl":873,"updatedAt":987},"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},[980,983,984],{"name":981,"slug":982,"type":16},"Communications","communications",{"name":948,"slug":949,"type":16},{"name":985,"slug":986,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":989,"name":989,"fn":990,"description":991,"org":992,"tags":993,"stars":872,"repoUrl":873,"updatedAt":1002},"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},[994,995,998,999],{"name":908,"slug":909,"type":16},{"name":996,"slug":997,"type":16},"API Development","api-development",{"name":917,"slug":918,"type":16},{"name":1000,"slug":1001,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":899,"name":899,"fn":1004,"description":1005,"org":1006,"tags":1007,"stars":872,"repoUrl":873,"updatedAt":1010},"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},[1008,1009],{"name":940,"slug":941,"type":16},{"name":898,"slug":899,"type":16},"2026-04-06T17:56:02.483316",{"slug":1012,"name":1012,"fn":1013,"description":1014,"org":1015,"tags":1016,"stars":872,"repoUrl":873,"updatedAt":1023},"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},[1017,1020],{"name":1018,"slug":1019,"type":16},"PowerPoint","powerpoint",{"name":1021,"slug":1022,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1025,"name":1025,"fn":1026,"description":1027,"org":1028,"tags":1029,"stars":872,"repoUrl":873,"updatedAt":1039},"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},[1030,1031,1032,1035,1038],{"name":908,"slug":909,"type":16},{"name":927,"slug":928,"type":16},{"name":1033,"slug":1034,"type":16},"Evals","evals",{"name":1036,"slug":1037,"type":16},"Performance","performance",{"name":930,"slug":931,"type":16},"2026-04-19T06:45:40.804",490,{"items":1042,"total":1149},[1043,1057,1073,1089,1105,1124,1136],{"slug":1044,"name":1044,"fn":1045,"description":1046,"org":1047,"tags":1048,"stars":26,"repoUrl":27,"updatedAt":1056},"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},[1049,1052,1053],{"name":1050,"slug":1051,"type":16},"Accessibility","accessibility",{"name":864,"slug":865,"type":16},{"name":1054,"slug":1055,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":1058,"name":1058,"fn":1059,"description":1060,"org":1061,"tags":1062,"stars":26,"repoUrl":27,"updatedAt":1072},"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},[1063,1066,1069],{"name":1064,"slug":1065,"type":16},"CRM","crm",{"name":1067,"slug":1068,"type":16},"Research","research",{"name":1070,"slug":1071,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":1074,"name":1074,"fn":1075,"description":1076,"org":1077,"tags":1078,"stars":26,"repoUrl":27,"updatedAt":1088},"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},[1079,1082,1085],{"name":1080,"slug":1081,"type":16},"Analytics","analytics",{"name":1083,"slug":1084,"type":16},"Data Analysis","data-analysis",{"name":1086,"slug":1087,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":1090,"name":1090,"fn":1091,"description":1092,"org":1093,"tags":1094,"stars":26,"repoUrl":27,"updatedAt":1104},"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},[1095,1098,1100,1101],{"name":1096,"slug":1097,"type":16},"ADR","adr",{"name":1099,"slug":1090,"type":16},"Architecture",{"name":927,"slug":928,"type":16},{"name":1102,"slug":1103,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":1106,"name":1106,"fn":1107,"description":1108,"org":1109,"tags":1110,"stars":26,"repoUrl":27,"updatedAt":1123},"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},[1111,1114,1117,1120],{"name":1112,"slug":1113,"type":16},"Audit","audit",{"name":1115,"slug":1116,"type":16},"Finance","finance",{"name":1118,"slug":1119,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1121,"slug":1122,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":1125,"name":1125,"fn":1126,"description":1127,"org":1128,"tags":1129,"stars":26,"repoUrl":27,"updatedAt":1135},"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},[1130,1131,1134],{"name":882,"slug":883,"type":16},{"name":1132,"slug":1133,"type":16},"Marketing","marketing",{"name":985,"slug":986,"type":16},"2026-04-06T17:58:19.548331",{"slug":1137,"name":1137,"fn":1138,"description":1139,"org":1140,"tags":1141,"stars":26,"repoUrl":27,"updatedAt":1148},"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},[1142,1143,1144,1147],{"name":882,"slug":883,"type":16},{"name":981,"slug":982,"type":16},{"name":1145,"slug":1146,"type":16},"Content Creation","content-creation",{"name":985,"slug":986,"type":16},"2026-04-06T18:00:23.528956",200]