[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-search-strategy":3,"mdc-jspkq0-key":34,"related-repo-anthropic-search-strategy":1231,"related-org-anthropic-search-strategy":1350},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"search-strategy","decompose queries into multi-source searches","Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.",{"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],{"name":14,"slug":15,"type":16},"Enterprise Search","enterprise-search","tag",{"name":18,"slug":19,"type":16},"Knowledge Management","knowledge-management",{"name":21,"slug":22,"type":16},"Search","search",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T17:58:38.761745",null,2736,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"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\u002Fsearch-strategy","---\nname: search-strategy\ndescription: Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.\nuser-invocable: false\n---\n\n# Search Strategy\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](..\u002F..\u002FCONNECTORS.md).\n\nThe core intelligence behind enterprise search. Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results.\n\n## The Goal\n\nTurn this:\n```\n\"What did we decide about the API migration timeline?\"\n```\n\nInto targeted searches across every connected source:\n```\n~~chat:  \"API migration timeline decision\" (semantic) + \"API migration\" in:#engineering after:2025-01-01\n~~knowledge base: semantic search \"API migration timeline decision\"\n~~project tracker:  text search \"API migration\" in relevant workspace\n```\n\nThen synthesize the results into a single coherent answer.\n\n## Query Decomposition\n\n### Step 1: Identify Query Type\n\nClassify the user's question to determine search strategy:\n\n| Query Type | Example | Strategy |\n|-----------|---------|----------|\n| **Decision** | \"What did we decide about X?\" | Prioritize conversations (~~chat, email), look for conclusion signals |\n| **Status** | \"What's the status of Project Y?\" | Prioritize recent activity, task trackers, status updates |\n| **Document** | \"Where's the spec for Z?\" | Prioritize Drive, wiki, shared docs |\n| **Person** | \"Who's working on X?\" | Search task assignments, message authors, doc collaborators |\n| **Factual** | \"What's our policy on X?\" | Prioritize wiki, official docs, then confirmatory conversations |\n| **Temporal** | \"When did X happen?\" | Search with broad date range, look for timestamps |\n| **Exploratory** | \"What do we know about X?\" | Broad search across all sources, synthesize |\n\n### Step 2: Extract Search Components\n\nFrom the query, extract:\n\n- **Keywords**: Core terms that must appear in results\n- **Entities**: People, projects, teams, tools (use memory system if available)\n- **Intent signals**: Decision words, status words, temporal markers\n- **Constraints**: Time ranges, source hints, author filters\n- **Negations**: Things to exclude\n\n### Step 3: Generate Sub-Queries Per Source\n\nFor each available source, create one or more targeted queries:\n\n**Prefer semantic search** for:\n- Conceptual questions (\"What do we think about...\")\n- Questions where exact keywords are unknown\n- Exploratory queries\n\n**Prefer keyword search** for:\n- Known terms, project names, acronyms\n- Exact phrases the user quoted\n- Filter-heavy queries (from:, in:, after:)\n\n**Generate multiple query variants** when the topic might be referred to differently:\n```\nUser: \"Kubernetes setup\"\nQueries: \"Kubernetes\", \"k8s\", \"cluster\", \"container orchestration\"\n```\n\n## Source-Specific Query Translation\n\n### ~~chat\n\n**Semantic search** (natural language questions):\n```\nquery: \"What is the status of project aurora?\"\n```\n\n**Keyword search:**\n```\nquery: \"project aurora status update\"\nquery: \"aurora in:#engineering after:2025-01-15\"\nquery: \"from:\u003C@UserID> aurora\"\n```\n\n**Filter mapping:**\n| Enterprise filter | ~~chat syntax |\n|------------------|--------------|\n| `from:sarah` | `from:sarah` or `from:\u003C@USERID>` |\n| `in:engineering` | `in:engineering` |\n| `after:2025-01-01` | `after:2025-01-01` |\n| `before:2025-02-01` | `before:2025-02-01` |\n| `type:thread` | `is:thread` |\n| `type:file` | `has:file` |\n\n### ~~knowledge base (Wiki)\n\n**Semantic search** — Use for conceptual queries:\n```\ndescriptive_query: \"API migration timeline and decision rationale\"\n```\n\n**Keyword search** — Use for exact terms:\n```\nquery: \"API migration\"\nquery: \"\\\"API migration timeline\\\"\"  (exact phrase)\n```\n\n### ~~project tracker\n\n**Task search:**\n```\ntext: \"API migration\"\nworkspace: [workspace_id]\ncompleted: false  (for status queries)\nassignee_any: \"me\"  (for \"my tasks\" queries)\n```\n\n**Filter mapping:**\n| Enterprise filter | ~~project tracker parameter |\n|------------------|----------------|\n| `from:sarah` | `assignee_any` or `created_by_any` |\n| `after:2025-01-01` | `modified_on_after: \"2025-01-01\"` |\n| `type:milestone` | `resource_subtype: \"milestone\"` |\n\n## Result Ranking\n\n### Relevance Scoring\n\nScore each result on these factors (weighted by query type):\n\n| Factor | Weight (Decision) | Weight (Status) | Weight (Document) | Weight (Factual) |\n|--------|-------------------|------------------|--------------------|-------------------|\n| Keyword match | 0.3 | 0.2 | 0.4 | 0.3 |\n| Freshness | 0.3 | 0.4 | 0.2 | 0.1 |\n| Authority | 0.2 | 0.1 | 0.3 | 0.4 |\n| Completeness | 0.2 | 0.3 | 0.1 | 0.2 |\n\n### Authority Hierarchy\n\nDepends on query type:\n\n**For factual\u002Fpolicy questions:**\n```\nWiki\u002FOfficial docs > Shared documents > Email announcements > Chat messages\n```\n\n**For \"what happened\" \u002F decision questions:**\n```\nMeeting notes > Thread conclusions > Email confirmations > Chat messages\n```\n\n**For status questions:**\n```\nTask tracker > Recent chat > Status docs > Email updates\n```\n\n## Handling Ambiguity\n\nWhen a query is ambiguous, prefer asking one focused clarifying question over guessing:\n\n```\nAmbiguous: \"search for the migration\"\n→ \"I found references to a few migrations. Are you looking for:\n   1. The database migration (Project Phoenix)\n   2. The cloud migration (AWS → GCP)\n   3. The email migration (Exchange → O365)\"\n```\n\nOnly ask for clarification when:\n- There are genuinely distinct interpretations that would produce very different results\n- The ambiguity would significantly affect which sources to search\n\nDo NOT ask for clarification when:\n- The query is clear enough to produce useful results\n- Minor ambiguity can be resolved by returning results from multiple interpretations\n\n## Fallback Strategies\n\nWhen a source is unavailable or returns no results:\n\n1. **Source unavailable**: Skip it, search remaining sources, note the gap\n2. **No results from a source**: Try broader query terms, remove date filters, try alternate keywords\n3. **All sources return nothing**: Suggest query modifications to the user\n4. **Rate limited**: Note the limitation, return results from other sources, suggest retrying later\n\n### Query Broadening\n\nIf initial queries return too few results:\n```\nOriginal: \"PostgreSQL migration Q2 timeline decision\"\nBroader:  \"PostgreSQL migration\"\nBroader:  \"database migration\"\nBroadest: \"migration\"\n```\n\nRemove constraints in this order:\n1. Date filters (search all time)\n2. Source\u002Flocation filters\n3. Less important keywords\n4. Keep only core entity\u002Ftopic terms\n\n## Parallel Execution\n\nAlways execute searches across sources in parallel, never sequentially. The total search time should be roughly equal to the slowest single source, not the sum of all sources.\n\n```\n[User query]\n     ↓ decompose\n[~~chat query] [~~email query] [~~cloud storage query] [Wiki query] [~~project tracker query]\n     ↓            ↓            ↓              ↓            ↓\n  (parallel execution)\n     ↓\n[Merge + Rank + Deduplicate]\n     ↓\n[Synthesized answer]\n```\n",{"data":35,"body":37},{"name":4,"description":6,"user-invocable":36},false,{"type":38,"children":39},"root",[40,48,67,72,79,84,97,102,111,116,122,129,134,315,321,326,381,387,392,402,420,429,447,457,466,472,478,488,497,505,514,522,674,680,689,698,708,717,723,731,740,747,836,842,848,853,990,996,1001,1009,1018,1026,1035,1043,1052,1058,1063,1072,1077,1090,1095,1108,1114,1119,1163,1169,1174,1183,1188,1211,1217,1222],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","Search Strategy",{"type":41,"tag":49,"props":50,"children":51},"blockquote",{},[52],{"type":41,"tag":53,"props":54,"children":55},"p",{},[56,58,65],{"type":46,"value":57},"If you see unfamiliar placeholders or need to check which tools are connected, see ",{"type":41,"tag":59,"props":60,"children":62},"a",{"href":61},"..\u002F..\u002FCONNECTORS.md",[63],{"type":46,"value":64},"CONNECTORS.md",{"type":46,"value":66},".",{"type":41,"tag":53,"props":68,"children":69},{},[70],{"type":46,"value":71},"The core intelligence behind enterprise search. Transforms a single natural language question into parallel, source-specific searches and produces ranked, deduplicated results.",{"type":41,"tag":73,"props":74,"children":76},"h2",{"id":75},"the-goal",[77],{"type":46,"value":78},"The Goal",{"type":41,"tag":53,"props":80,"children":81},{},[82],{"type":46,"value":83},"Turn this:",{"type":41,"tag":85,"props":86,"children":90},"pre",{"className":87,"code":89,"language":46},[88],"language-text","\"What did we decide about the API migration timeline?\"\n",[91],{"type":41,"tag":92,"props":93,"children":95},"code",{"__ignoreMap":94},"",[96],{"type":46,"value":89},{"type":41,"tag":53,"props":98,"children":99},{},[100],{"type":46,"value":101},"Into targeted searches across every connected source:",{"type":41,"tag":85,"props":103,"children":106},{"className":104,"code":105,"language":46},[88],"~~chat:  \"API migration timeline decision\" (semantic) + \"API migration\" in:#engineering after:2025-01-01\n~~knowledge base: semantic search \"API migration timeline decision\"\n~~project tracker:  text search \"API migration\" in relevant workspace\n",[107],{"type":41,"tag":92,"props":108,"children":109},{"__ignoreMap":94},[110],{"type":46,"value":105},{"type":41,"tag":53,"props":112,"children":113},{},[114],{"type":46,"value":115},"Then synthesize the results into a single coherent answer.",{"type":41,"tag":73,"props":117,"children":119},{"id":118},"query-decomposition",[120],{"type":46,"value":121},"Query Decomposition",{"type":41,"tag":123,"props":124,"children":126},"h3",{"id":125},"step-1-identify-query-type",[127],{"type":46,"value":128},"Step 1: Identify Query Type",{"type":41,"tag":53,"props":130,"children":131},{},[132],{"type":46,"value":133},"Classify the user's question to determine search strategy:",{"type":41,"tag":135,"props":136,"children":137},"table",{},[138,162],{"type":41,"tag":139,"props":140,"children":141},"thead",{},[142],{"type":41,"tag":143,"props":144,"children":145},"tr",{},[146,152,157],{"type":41,"tag":147,"props":148,"children":149},"th",{},[150],{"type":46,"value":151},"Query Type",{"type":41,"tag":147,"props":153,"children":154},{},[155],{"type":46,"value":156},"Example",{"type":41,"tag":147,"props":158,"children":159},{},[160],{"type":46,"value":161},"Strategy",{"type":41,"tag":163,"props":164,"children":165},"tbody",{},[166,189,210,231,252,273,294],{"type":41,"tag":143,"props":167,"children":168},{},[169,179,184],{"type":41,"tag":170,"props":171,"children":172},"td",{},[173],{"type":41,"tag":174,"props":175,"children":176},"strong",{},[177],{"type":46,"value":178},"Decision",{"type":41,"tag":170,"props":180,"children":181},{},[182],{"type":46,"value":183},"\"What did we decide about X?\"",{"type":41,"tag":170,"props":185,"children":186},{},[187],{"type":46,"value":188},"Prioritize conversations (~~chat, email), look for conclusion signals",{"type":41,"tag":143,"props":190,"children":191},{},[192,200,205],{"type":41,"tag":170,"props":193,"children":194},{},[195],{"type":41,"tag":174,"props":196,"children":197},{},[198],{"type":46,"value":199},"Status",{"type":41,"tag":170,"props":201,"children":202},{},[203],{"type":46,"value":204},"\"What's the status of Project Y?\"",{"type":41,"tag":170,"props":206,"children":207},{},[208],{"type":46,"value":209},"Prioritize recent activity, task trackers, status updates",{"type":41,"tag":143,"props":211,"children":212},{},[213,221,226],{"type":41,"tag":170,"props":214,"children":215},{},[216],{"type":41,"tag":174,"props":217,"children":218},{},[219],{"type":46,"value":220},"Document",{"type":41,"tag":170,"props":222,"children":223},{},[224],{"type":46,"value":225},"\"Where's the spec for Z?\"",{"type":41,"tag":170,"props":227,"children":228},{},[229],{"type":46,"value":230},"Prioritize Drive, wiki, shared docs",{"type":41,"tag":143,"props":232,"children":233},{},[234,242,247],{"type":41,"tag":170,"props":235,"children":236},{},[237],{"type":41,"tag":174,"props":238,"children":239},{},[240],{"type":46,"value":241},"Person",{"type":41,"tag":170,"props":243,"children":244},{},[245],{"type":46,"value":246},"\"Who's working on X?\"",{"type":41,"tag":170,"props":248,"children":249},{},[250],{"type":46,"value":251},"Search task assignments, message authors, doc collaborators",{"type":41,"tag":143,"props":253,"children":254},{},[255,263,268],{"type":41,"tag":170,"props":256,"children":257},{},[258],{"type":41,"tag":174,"props":259,"children":260},{},[261],{"type":46,"value":262},"Factual",{"type":41,"tag":170,"props":264,"children":265},{},[266],{"type":46,"value":267},"\"What's our policy on X?\"",{"type":41,"tag":170,"props":269,"children":270},{},[271],{"type":46,"value":272},"Prioritize wiki, official docs, then confirmatory conversations",{"type":41,"tag":143,"props":274,"children":275},{},[276,284,289],{"type":41,"tag":170,"props":277,"children":278},{},[279],{"type":41,"tag":174,"props":280,"children":281},{},[282],{"type":46,"value":283},"Temporal",{"type":41,"tag":170,"props":285,"children":286},{},[287],{"type":46,"value":288},"\"When did X happen?\"",{"type":41,"tag":170,"props":290,"children":291},{},[292],{"type":46,"value":293},"Search with broad date range, look for timestamps",{"type":41,"tag":143,"props":295,"children":296},{},[297,305,310],{"type":41,"tag":170,"props":298,"children":299},{},[300],{"type":41,"tag":174,"props":301,"children":302},{},[303],{"type":46,"value":304},"Exploratory",{"type":41,"tag":170,"props":306,"children":307},{},[308],{"type":46,"value":309},"\"What do we know about X?\"",{"type":41,"tag":170,"props":311,"children":312},{},[313],{"type":46,"value":314},"Broad search across all sources, synthesize",{"type":41,"tag":123,"props":316,"children":318},{"id":317},"step-2-extract-search-components",[319],{"type":46,"value":320},"Step 2: Extract Search Components",{"type":41,"tag":53,"props":322,"children":323},{},[324],{"type":46,"value":325},"From the query, extract:",{"type":41,"tag":327,"props":328,"children":329},"ul",{},[330,341,351,361,371],{"type":41,"tag":331,"props":332,"children":333},"li",{},[334,339],{"type":41,"tag":174,"props":335,"children":336},{},[337],{"type":46,"value":338},"Keywords",{"type":46,"value":340},": Core terms that must appear in results",{"type":41,"tag":331,"props":342,"children":343},{},[344,349],{"type":41,"tag":174,"props":345,"children":346},{},[347],{"type":46,"value":348},"Entities",{"type":46,"value":350},": People, projects, teams, tools (use memory system if available)",{"type":41,"tag":331,"props":352,"children":353},{},[354,359],{"type":41,"tag":174,"props":355,"children":356},{},[357],{"type":46,"value":358},"Intent signals",{"type":46,"value":360},": Decision words, status words, temporal markers",{"type":41,"tag":331,"props":362,"children":363},{},[364,369],{"type":41,"tag":174,"props":365,"children":366},{},[367],{"type":46,"value":368},"Constraints",{"type":46,"value":370},": Time ranges, source hints, author filters",{"type":41,"tag":331,"props":372,"children":373},{},[374,379],{"type":41,"tag":174,"props":375,"children":376},{},[377],{"type":46,"value":378},"Negations",{"type":46,"value":380},": Things to exclude",{"type":41,"tag":123,"props":382,"children":384},{"id":383},"step-3-generate-sub-queries-per-source",[385],{"type":46,"value":386},"Step 3: Generate Sub-Queries Per Source",{"type":41,"tag":53,"props":388,"children":389},{},[390],{"type":46,"value":391},"For each available source, create one or more targeted queries:",{"type":41,"tag":53,"props":393,"children":394},{},[395,400],{"type":41,"tag":174,"props":396,"children":397},{},[398],{"type":46,"value":399},"Prefer semantic search",{"type":46,"value":401}," for:",{"type":41,"tag":327,"props":403,"children":404},{},[405,410,415],{"type":41,"tag":331,"props":406,"children":407},{},[408],{"type":46,"value":409},"Conceptual questions (\"What do we think about...\")",{"type":41,"tag":331,"props":411,"children":412},{},[413],{"type":46,"value":414},"Questions where exact keywords are unknown",{"type":41,"tag":331,"props":416,"children":417},{},[418],{"type":46,"value":419},"Exploratory queries",{"type":41,"tag":53,"props":421,"children":422},{},[423,428],{"type":41,"tag":174,"props":424,"children":425},{},[426],{"type":46,"value":427},"Prefer keyword search",{"type":46,"value":401},{"type":41,"tag":327,"props":430,"children":431},{},[432,437,442],{"type":41,"tag":331,"props":433,"children":434},{},[435],{"type":46,"value":436},"Known terms, project names, acronyms",{"type":41,"tag":331,"props":438,"children":439},{},[440],{"type":46,"value":441},"Exact phrases the user quoted",{"type":41,"tag":331,"props":443,"children":444},{},[445],{"type":46,"value":446},"Filter-heavy queries (from:, in:, after:)",{"type":41,"tag":53,"props":448,"children":449},{},[450,455],{"type":41,"tag":174,"props":451,"children":452},{},[453],{"type":46,"value":454},"Generate multiple query variants",{"type":46,"value":456}," when the topic might be referred to differently:",{"type":41,"tag":85,"props":458,"children":461},{"className":459,"code":460,"language":46},[88],"User: \"Kubernetes setup\"\nQueries: \"Kubernetes\", \"k8s\", \"cluster\", \"container orchestration\"\n",[462],{"type":41,"tag":92,"props":463,"children":464},{"__ignoreMap":94},[465],{"type":46,"value":460},{"type":41,"tag":73,"props":467,"children":469},{"id":468},"source-specific-query-translation",[470],{"type":46,"value":471},"Source-Specific Query Translation",{"type":41,"tag":123,"props":473,"children":475},{"id":474},"chat",[476],{"type":46,"value":477},"~~chat",{"type":41,"tag":53,"props":479,"children":480},{},[481,486],{"type":41,"tag":174,"props":482,"children":483},{},[484],{"type":46,"value":485},"Semantic search",{"type":46,"value":487}," (natural language questions):",{"type":41,"tag":85,"props":489,"children":492},{"className":490,"code":491,"language":46},[88],"query: \"What is the status of project aurora?\"\n",[493],{"type":41,"tag":92,"props":494,"children":495},{"__ignoreMap":94},[496],{"type":46,"value":491},{"type":41,"tag":53,"props":498,"children":499},{},[500],{"type":41,"tag":174,"props":501,"children":502},{},[503],{"type":46,"value":504},"Keyword search:",{"type":41,"tag":85,"props":506,"children":509},{"className":507,"code":508,"language":46},[88],"query: \"project aurora status update\"\nquery: \"aurora in:#engineering after:2025-01-15\"\nquery: \"from:\u003C@UserID> aurora\"\n",[510],{"type":41,"tag":92,"props":511,"children":512},{"__ignoreMap":94},[513],{"type":46,"value":508},{"type":41,"tag":53,"props":515,"children":516},{},[517],{"type":41,"tag":174,"props":518,"children":519},{},[520],{"type":46,"value":521},"Filter mapping:",{"type":41,"tag":135,"props":523,"children":524},{},[525,541],{"type":41,"tag":139,"props":526,"children":527},{},[528],{"type":41,"tag":143,"props":529,"children":530},{},[531,536],{"type":41,"tag":147,"props":532,"children":533},{},[534],{"type":46,"value":535},"Enterprise filter",{"type":41,"tag":147,"props":537,"children":538},{},[539],{"type":46,"value":540},"~~chat syntax",{"type":41,"tag":163,"props":542,"children":543},{},[544,572,592,612,632,653],{"type":41,"tag":143,"props":545,"children":546},{},[547,556],{"type":41,"tag":170,"props":548,"children":549},{},[550],{"type":41,"tag":92,"props":551,"children":553},{"className":552},[],[554],{"type":46,"value":555},"from:sarah",{"type":41,"tag":170,"props":557,"children":558},{},[559,564,566],{"type":41,"tag":92,"props":560,"children":562},{"className":561},[],[563],{"type":46,"value":555},{"type":46,"value":565}," or ",{"type":41,"tag":92,"props":567,"children":569},{"className":568},[],[570],{"type":46,"value":571},"from:\u003C@USERID>",{"type":41,"tag":143,"props":573,"children":574},{},[575,584],{"type":41,"tag":170,"props":576,"children":577},{},[578],{"type":41,"tag":92,"props":579,"children":581},{"className":580},[],[582],{"type":46,"value":583},"in:engineering",{"type":41,"tag":170,"props":585,"children":586},{},[587],{"type":41,"tag":92,"props":588,"children":590},{"className":589},[],[591],{"type":46,"value":583},{"type":41,"tag":143,"props":593,"children":594},{},[595,604],{"type":41,"tag":170,"props":596,"children":597},{},[598],{"type":41,"tag":92,"props":599,"children":601},{"className":600},[],[602],{"type":46,"value":603},"after:2025-01-01",{"type":41,"tag":170,"props":605,"children":606},{},[607],{"type":41,"tag":92,"props":608,"children":610},{"className":609},[],[611],{"type":46,"value":603},{"type":41,"tag":143,"props":613,"children":614},{},[615,624],{"type":41,"tag":170,"props":616,"children":617},{},[618],{"type":41,"tag":92,"props":619,"children":621},{"className":620},[],[622],{"type":46,"value":623},"before:2025-02-01",{"type":41,"tag":170,"props":625,"children":626},{},[627],{"type":41,"tag":92,"props":628,"children":630},{"className":629},[],[631],{"type":46,"value":623},{"type":41,"tag":143,"props":633,"children":634},{},[635,644],{"type":41,"tag":170,"props":636,"children":637},{},[638],{"type":41,"tag":92,"props":639,"children":641},{"className":640},[],[642],{"type":46,"value":643},"type:thread",{"type":41,"tag":170,"props":645,"children":646},{},[647],{"type":41,"tag":92,"props":648,"children":650},{"className":649},[],[651],{"type":46,"value":652},"is:thread",{"type":41,"tag":143,"props":654,"children":655},{},[656,665],{"type":41,"tag":170,"props":657,"children":658},{},[659],{"type":41,"tag":92,"props":660,"children":662},{"className":661},[],[663],{"type":46,"value":664},"type:file",{"type":41,"tag":170,"props":666,"children":667},{},[668],{"type":41,"tag":92,"props":669,"children":671},{"className":670},[],[672],{"type":46,"value":673},"has:file",{"type":41,"tag":123,"props":675,"children":677},{"id":676},"knowledge-base-wiki",[678],{"type":46,"value":679},"~~knowledge base (Wiki)",{"type":41,"tag":53,"props":681,"children":682},{},[683,687],{"type":41,"tag":174,"props":684,"children":685},{},[686],{"type":46,"value":485},{"type":46,"value":688}," — Use for conceptual queries:",{"type":41,"tag":85,"props":690,"children":693},{"className":691,"code":692,"language":46},[88],"descriptive_query: \"API migration timeline and decision rationale\"\n",[694],{"type":41,"tag":92,"props":695,"children":696},{"__ignoreMap":94},[697],{"type":46,"value":692},{"type":41,"tag":53,"props":699,"children":700},{},[701,706],{"type":41,"tag":174,"props":702,"children":703},{},[704],{"type":46,"value":705},"Keyword search",{"type":46,"value":707}," — Use for exact terms:",{"type":41,"tag":85,"props":709,"children":712},{"className":710,"code":711,"language":46},[88],"query: \"API migration\"\nquery: \"\\\"API migration timeline\\\"\"  (exact phrase)\n",[713],{"type":41,"tag":92,"props":714,"children":715},{"__ignoreMap":94},[716],{"type":46,"value":711},{"type":41,"tag":123,"props":718,"children":720},{"id":719},"project-tracker",[721],{"type":46,"value":722},"~~project tracker",{"type":41,"tag":53,"props":724,"children":725},{},[726],{"type":41,"tag":174,"props":727,"children":728},{},[729],{"type":46,"value":730},"Task search:",{"type":41,"tag":85,"props":732,"children":735},{"className":733,"code":734,"language":46},[88],"text: \"API migration\"\nworkspace: [workspace_id]\ncompleted: false  (for status queries)\nassignee_any: \"me\"  (for \"my tasks\" queries)\n",[736],{"type":41,"tag":92,"props":737,"children":738},{"__ignoreMap":94},[739],{"type":46,"value":734},{"type":41,"tag":53,"props":741,"children":742},{},[743],{"type":41,"tag":174,"props":744,"children":745},{},[746],{"type":46,"value":521},{"type":41,"tag":135,"props":748,"children":749},{},[750,765],{"type":41,"tag":139,"props":751,"children":752},{},[753],{"type":41,"tag":143,"props":754,"children":755},{},[756,760],{"type":41,"tag":147,"props":757,"children":758},{},[759],{"type":46,"value":535},{"type":41,"tag":147,"props":761,"children":762},{},[763],{"type":46,"value":764},"~~project tracker parameter",{"type":41,"tag":163,"props":766,"children":767},{},[768,795,815],{"type":41,"tag":143,"props":769,"children":770},{},[771,779],{"type":41,"tag":170,"props":772,"children":773},{},[774],{"type":41,"tag":92,"props":775,"children":777},{"className":776},[],[778],{"type":46,"value":555},{"type":41,"tag":170,"props":780,"children":781},{},[782,788,789],{"type":41,"tag":92,"props":783,"children":785},{"className":784},[],[786],{"type":46,"value":787},"assignee_any",{"type":46,"value":565},{"type":41,"tag":92,"props":790,"children":792},{"className":791},[],[793],{"type":46,"value":794},"created_by_any",{"type":41,"tag":143,"props":796,"children":797},{},[798,806],{"type":41,"tag":170,"props":799,"children":800},{},[801],{"type":41,"tag":92,"props":802,"children":804},{"className":803},[],[805],{"type":46,"value":603},{"type":41,"tag":170,"props":807,"children":808},{},[809],{"type":41,"tag":92,"props":810,"children":812},{"className":811},[],[813],{"type":46,"value":814},"modified_on_after: \"2025-01-01\"",{"type":41,"tag":143,"props":816,"children":817},{},[818,827],{"type":41,"tag":170,"props":819,"children":820},{},[821],{"type":41,"tag":92,"props":822,"children":824},{"className":823},[],[825],{"type":46,"value":826},"type:milestone",{"type":41,"tag":170,"props":828,"children":829},{},[830],{"type":41,"tag":92,"props":831,"children":833},{"className":832},[],[834],{"type":46,"value":835},"resource_subtype: \"milestone\"",{"type":41,"tag":73,"props":837,"children":839},{"id":838},"result-ranking",[840],{"type":46,"value":841},"Result Ranking",{"type":41,"tag":123,"props":843,"children":845},{"id":844},"relevance-scoring",[846],{"type":46,"value":847},"Relevance Scoring",{"type":41,"tag":53,"props":849,"children":850},{},[851],{"type":46,"value":852},"Score each result on these factors (weighted by query type):",{"type":41,"tag":135,"props":854,"children":855},{},[856,887],{"type":41,"tag":139,"props":857,"children":858},{},[859],{"type":41,"tag":143,"props":860,"children":861},{},[862,867,872,877,882],{"type":41,"tag":147,"props":863,"children":864},{},[865],{"type":46,"value":866},"Factor",{"type":41,"tag":147,"props":868,"children":869},{},[870],{"type":46,"value":871},"Weight (Decision)",{"type":41,"tag":147,"props":873,"children":874},{},[875],{"type":46,"value":876},"Weight (Status)",{"type":41,"tag":147,"props":878,"children":879},{},[880],{"type":46,"value":881},"Weight (Document)",{"type":41,"tag":147,"props":883,"children":884},{},[885],{"type":46,"value":886},"Weight (Factual)",{"type":41,"tag":163,"props":888,"children":889},{},[890,917,942,966],{"type":41,"tag":143,"props":891,"children":892},{},[893,898,903,908,913],{"type":41,"tag":170,"props":894,"children":895},{},[896],{"type":46,"value":897},"Keyword match",{"type":41,"tag":170,"props":899,"children":900},{},[901],{"type":46,"value":902},"0.3",{"type":41,"tag":170,"props":904,"children":905},{},[906],{"type":46,"value":907},"0.2",{"type":41,"tag":170,"props":909,"children":910},{},[911],{"type":46,"value":912},"0.4",{"type":41,"tag":170,"props":914,"children":915},{},[916],{"type":46,"value":902},{"type":41,"tag":143,"props":918,"children":919},{},[920,925,929,933,937],{"type":41,"tag":170,"props":921,"children":922},{},[923],{"type":46,"value":924},"Freshness",{"type":41,"tag":170,"props":926,"children":927},{},[928],{"type":46,"value":902},{"type":41,"tag":170,"props":930,"children":931},{},[932],{"type":46,"value":912},{"type":41,"tag":170,"props":934,"children":935},{},[936],{"type":46,"value":907},{"type":41,"tag":170,"props":938,"children":939},{},[940],{"type":46,"value":941},"0.1",{"type":41,"tag":143,"props":943,"children":944},{},[945,950,954,958,962],{"type":41,"tag":170,"props":946,"children":947},{},[948],{"type":46,"value":949},"Authority",{"type":41,"tag":170,"props":951,"children":952},{},[953],{"type":46,"value":907},{"type":41,"tag":170,"props":955,"children":956},{},[957],{"type":46,"value":941},{"type":41,"tag":170,"props":959,"children":960},{},[961],{"type":46,"value":902},{"type":41,"tag":170,"props":963,"children":964},{},[965],{"type":46,"value":912},{"type":41,"tag":143,"props":967,"children":968},{},[969,974,978,982,986],{"type":41,"tag":170,"props":970,"children":971},{},[972],{"type":46,"value":973},"Completeness",{"type":41,"tag":170,"props":975,"children":976},{},[977],{"type":46,"value":907},{"type":41,"tag":170,"props":979,"children":980},{},[981],{"type":46,"value":902},{"type":41,"tag":170,"props":983,"children":984},{},[985],{"type":46,"value":941},{"type":41,"tag":170,"props":987,"children":988},{},[989],{"type":46,"value":907},{"type":41,"tag":123,"props":991,"children":993},{"id":992},"authority-hierarchy",[994],{"type":46,"value":995},"Authority Hierarchy",{"type":41,"tag":53,"props":997,"children":998},{},[999],{"type":46,"value":1000},"Depends on query type:",{"type":41,"tag":53,"props":1002,"children":1003},{},[1004],{"type":41,"tag":174,"props":1005,"children":1006},{},[1007],{"type":46,"value":1008},"For factual\u002Fpolicy questions:",{"type":41,"tag":85,"props":1010,"children":1013},{"className":1011,"code":1012,"language":46},[88],"Wiki\u002FOfficial docs > Shared documents > Email announcements > Chat messages\n",[1014],{"type":41,"tag":92,"props":1015,"children":1016},{"__ignoreMap":94},[1017],{"type":46,"value":1012},{"type":41,"tag":53,"props":1019,"children":1020},{},[1021],{"type":41,"tag":174,"props":1022,"children":1023},{},[1024],{"type":46,"value":1025},"For \"what happened\" \u002F decision questions:",{"type":41,"tag":85,"props":1027,"children":1030},{"className":1028,"code":1029,"language":46},[88],"Meeting notes > Thread conclusions > Email confirmations > Chat messages\n",[1031],{"type":41,"tag":92,"props":1032,"children":1033},{"__ignoreMap":94},[1034],{"type":46,"value":1029},{"type":41,"tag":53,"props":1036,"children":1037},{},[1038],{"type":41,"tag":174,"props":1039,"children":1040},{},[1041],{"type":46,"value":1042},"For status questions:",{"type":41,"tag":85,"props":1044,"children":1047},{"className":1045,"code":1046,"language":46},[88],"Task tracker > Recent chat > Status docs > Email updates\n",[1048],{"type":41,"tag":92,"props":1049,"children":1050},{"__ignoreMap":94},[1051],{"type":46,"value":1046},{"type":41,"tag":73,"props":1053,"children":1055},{"id":1054},"handling-ambiguity",[1056],{"type":46,"value":1057},"Handling Ambiguity",{"type":41,"tag":53,"props":1059,"children":1060},{},[1061],{"type":46,"value":1062},"When a query is ambiguous, prefer asking one focused clarifying question over guessing:",{"type":41,"tag":85,"props":1064,"children":1067},{"className":1065,"code":1066,"language":46},[88],"Ambiguous: \"search for the migration\"\n→ \"I found references to a few migrations. Are you looking for:\n   1. The database migration (Project Phoenix)\n   2. The cloud migration (AWS → GCP)\n   3. The email migration (Exchange → O365)\"\n",[1068],{"type":41,"tag":92,"props":1069,"children":1070},{"__ignoreMap":94},[1071],{"type":46,"value":1066},{"type":41,"tag":53,"props":1073,"children":1074},{},[1075],{"type":46,"value":1076},"Only ask for clarification when:",{"type":41,"tag":327,"props":1078,"children":1079},{},[1080,1085],{"type":41,"tag":331,"props":1081,"children":1082},{},[1083],{"type":46,"value":1084},"There are genuinely distinct interpretations that would produce very different results",{"type":41,"tag":331,"props":1086,"children":1087},{},[1088],{"type":46,"value":1089},"The ambiguity would significantly affect which sources to search",{"type":41,"tag":53,"props":1091,"children":1092},{},[1093],{"type":46,"value":1094},"Do NOT ask for clarification when:",{"type":41,"tag":327,"props":1096,"children":1097},{},[1098,1103],{"type":41,"tag":331,"props":1099,"children":1100},{},[1101],{"type":46,"value":1102},"The query is clear enough to produce useful results",{"type":41,"tag":331,"props":1104,"children":1105},{},[1106],{"type":46,"value":1107},"Minor ambiguity can be resolved by returning results from multiple interpretations",{"type":41,"tag":73,"props":1109,"children":1111},{"id":1110},"fallback-strategies",[1112],{"type":46,"value":1113},"Fallback Strategies",{"type":41,"tag":53,"props":1115,"children":1116},{},[1117],{"type":46,"value":1118},"When a source is unavailable or returns no results:",{"type":41,"tag":1120,"props":1121,"children":1122},"ol",{},[1123,1133,1143,1153],{"type":41,"tag":331,"props":1124,"children":1125},{},[1126,1131],{"type":41,"tag":174,"props":1127,"children":1128},{},[1129],{"type":46,"value":1130},"Source unavailable",{"type":46,"value":1132},": Skip it, search remaining sources, note the gap",{"type":41,"tag":331,"props":1134,"children":1135},{},[1136,1141],{"type":41,"tag":174,"props":1137,"children":1138},{},[1139],{"type":46,"value":1140},"No results from a source",{"type":46,"value":1142},": Try broader query terms, remove date filters, try alternate keywords",{"type":41,"tag":331,"props":1144,"children":1145},{},[1146,1151],{"type":41,"tag":174,"props":1147,"children":1148},{},[1149],{"type":46,"value":1150},"All sources return nothing",{"type":46,"value":1152},": Suggest query modifications to the user",{"type":41,"tag":331,"props":1154,"children":1155},{},[1156,1161],{"type":41,"tag":174,"props":1157,"children":1158},{},[1159],{"type":46,"value":1160},"Rate limited",{"type":46,"value":1162},": Note the limitation, return results from other sources, suggest retrying later",{"type":41,"tag":123,"props":1164,"children":1166},{"id":1165},"query-broadening",[1167],{"type":46,"value":1168},"Query Broadening",{"type":41,"tag":53,"props":1170,"children":1171},{},[1172],{"type":46,"value":1173},"If initial queries return too few results:",{"type":41,"tag":85,"props":1175,"children":1178},{"className":1176,"code":1177,"language":46},[88],"Original: \"PostgreSQL migration Q2 timeline decision\"\nBroader:  \"PostgreSQL migration\"\nBroader:  \"database migration\"\nBroadest: \"migration\"\n",[1179],{"type":41,"tag":92,"props":1180,"children":1181},{"__ignoreMap":94},[1182],{"type":46,"value":1177},{"type":41,"tag":53,"props":1184,"children":1185},{},[1186],{"type":46,"value":1187},"Remove constraints in this order:",{"type":41,"tag":1120,"props":1189,"children":1190},{},[1191,1196,1201,1206],{"type":41,"tag":331,"props":1192,"children":1193},{},[1194],{"type":46,"value":1195},"Date filters (search all time)",{"type":41,"tag":331,"props":1197,"children":1198},{},[1199],{"type":46,"value":1200},"Source\u002Flocation filters",{"type":41,"tag":331,"props":1202,"children":1203},{},[1204],{"type":46,"value":1205},"Less important keywords",{"type":41,"tag":331,"props":1207,"children":1208},{},[1209],{"type":46,"value":1210},"Keep only core entity\u002Ftopic terms",{"type":41,"tag":73,"props":1212,"children":1214},{"id":1213},"parallel-execution",[1215],{"type":46,"value":1216},"Parallel Execution",{"type":41,"tag":53,"props":1218,"children":1219},{},[1220],{"type":46,"value":1221},"Always execute searches across sources in parallel, never sequentially. The total search time should be roughly equal to the slowest single source, not the sum of all sources.",{"type":41,"tag":85,"props":1223,"children":1226},{"className":1224,"code":1225,"language":46},[88],"[User query]\n     ↓ decompose\n[~~chat query] [~~email query] [~~cloud storage query] [Wiki query] [~~project tracker query]\n     ↓            ↓            ↓              ↓            ↓\n  (parallel execution)\n     ↓\n[Merge + Rank + Deduplicate]\n     ↓\n[Synthesized answer]\n",[1227],{"type":41,"tag":92,"props":1228,"children":1229},{"__ignoreMap":94},[1230],{"type":46,"value":1225},{"items":1232,"total":1349},[1233,1249,1265,1281,1299,1318,1334],{"slug":1234,"name":1234,"fn":1235,"description":1236,"org":1237,"tags":1238,"stars":23,"repoUrl":24,"updatedAt":1248},"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},[1239,1242,1245],{"name":1240,"slug":1241,"type":16},"Accessibility","accessibility",{"name":1243,"slug":1244,"type":16},"Design","design",{"name":1246,"slug":1247,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":1250,"name":1250,"fn":1251,"description":1252,"org":1253,"tags":1254,"stars":23,"repoUrl":24,"updatedAt":1264},"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},[1255,1258,1261],{"name":1256,"slug":1257,"type":16},"CRM","crm",{"name":1259,"slug":1260,"type":16},"Research","research",{"name":1262,"slug":1263,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":1266,"name":1266,"fn":1267,"description":1268,"org":1269,"tags":1270,"stars":23,"repoUrl":24,"updatedAt":1280},"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},[1271,1274,1277],{"name":1272,"slug":1273,"type":16},"Analytics","analytics",{"name":1275,"slug":1276,"type":16},"Data Analysis","data-analysis",{"name":1278,"slug":1279,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":1282,"name":1282,"fn":1283,"description":1284,"org":1285,"tags":1286,"stars":23,"repoUrl":24,"updatedAt":1298},"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},[1287,1290,1292,1295],{"name":1288,"slug":1289,"type":16},"ADR","adr",{"name":1291,"slug":1282,"type":16},"Architecture",{"name":1293,"slug":1294,"type":16},"Documentation","documentation",{"name":1296,"slug":1297,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":1300,"name":1300,"fn":1301,"description":1302,"org":1303,"tags":1304,"stars":23,"repoUrl":24,"updatedAt":1317},"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},[1305,1308,1311,1314],{"name":1306,"slug":1307,"type":16},"Audit","audit",{"name":1309,"slug":1310,"type":16},"Finance","finance",{"name":1312,"slug":1313,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1315,"slug":1316,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":1319,"name":1319,"fn":1320,"description":1321,"org":1322,"tags":1323,"stars":23,"repoUrl":24,"updatedAt":1333},"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},[1324,1327,1330],{"name":1325,"slug":1326,"type":16},"Branding","branding",{"name":1328,"slug":1329,"type":16},"Marketing","marketing",{"name":1331,"slug":1332,"type":16},"Writing","writing","2026-04-06T17:58:19.548331",{"slug":1335,"name":1335,"fn":1336,"description":1337,"org":1338,"tags":1339,"stars":23,"repoUrl":24,"updatedAt":1348},"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},[1340,1341,1344,1347],{"name":1325,"slug":1326,"type":16},{"name":1342,"slug":1343,"type":16},"Communications","communications",{"name":1345,"slug":1346,"type":16},"Content Creation","content-creation",{"name":1331,"slug":1332,"type":16},"2026-04-06T18:00:23.528956",200,{"items":1351,"total":1528},[1352,1371,1383,1395,1414,1425,1446,1466,1476,1491,1499,1512],{"slug":1353,"name":1353,"fn":1354,"description":1355,"org":1356,"tags":1357,"stars":1368,"repoUrl":1369,"updatedAt":1370},"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},[1358,1361,1362,1365],{"name":1359,"slug":1360,"type":16},"Creative","creative",{"name":1243,"slug":1244,"type":16},{"name":1363,"slug":1364,"type":16},"Generative Art","generative-art",{"name":1366,"slug":1367,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1372,"name":1372,"fn":1373,"description":1374,"org":1375,"tags":1376,"stars":1368,"repoUrl":1369,"updatedAt":1382},"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},[1377,1378,1379],{"name":1325,"slug":1326,"type":16},{"name":1243,"slug":1244,"type":16},{"name":1380,"slug":1381,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1384,"name":1384,"fn":1385,"description":1386,"org":1387,"tags":1388,"stars":1368,"repoUrl":1369,"updatedAt":1394},"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},[1389,1390,1391],{"name":1359,"slug":1360,"type":16},{"name":1243,"slug":1244,"type":16},{"name":1392,"slug":1393,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1396,"name":1396,"fn":1397,"description":1398,"org":1399,"tags":1400,"stars":1368,"repoUrl":1369,"updatedAt":1413},"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},[1401,1404,1405,1408,1410],{"name":1402,"slug":1403,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1406,"slug":1407,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1409,"slug":1396,"type":16},"Claude API",{"name":1411,"slug":1412,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1415,"name":1415,"fn":1416,"description":1417,"org":1418,"tags":1419,"stars":1368,"repoUrl":1369,"updatedAt":1424},"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},[1420,1421],{"name":1293,"slug":1294,"type":16},{"name":1422,"slug":1423,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1426,"name":1426,"fn":1427,"description":1428,"org":1429,"tags":1430,"stars":1368,"repoUrl":1369,"updatedAt":1445},"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},[1431,1434,1436,1439,1442],{"name":1432,"slug":1433,"type":16},"Documents","documents",{"name":1435,"slug":1426,"type":16},"DOCX",{"name":1437,"slug":1438,"type":16},"Office","office",{"name":1440,"slug":1441,"type":16},"Templates","templates",{"name":1443,"slug":1444,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1447,"name":1447,"fn":1448,"description":1449,"org":1450,"tags":1451,"stars":1368,"repoUrl":1369,"updatedAt":1465},"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},[1452,1453,1456,1459,1462],{"name":1243,"slug":1244,"type":16},{"name":1454,"slug":1455,"type":16},"Frontend","frontend",{"name":1457,"slug":1458,"type":16},"React","react",{"name":1460,"slug":1461,"type":16},"Tailwind CSS","tailwind-css",{"name":1463,"slug":1464,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1467,"name":1467,"fn":1468,"description":1469,"org":1470,"tags":1471,"stars":1368,"repoUrl":1369,"updatedAt":1475},"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},[1472,1473,1474],{"name":1342,"slug":1343,"type":16},{"name":1440,"slug":1441,"type":16},{"name":1331,"slug":1332,"type":16},"2026-04-06T17:56:20.695522",{"slug":1477,"name":1477,"fn":1478,"description":1479,"org":1480,"tags":1481,"stars":1368,"repoUrl":1369,"updatedAt":1490},"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},[1482,1483,1486,1487],{"name":1402,"slug":1403,"type":16},{"name":1484,"slug":1485,"type":16},"API Development","api-development",{"name":1411,"slug":1412,"type":16},{"name":1488,"slug":1489,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1393,"name":1393,"fn":1492,"description":1493,"org":1494,"tags":1495,"stars":1368,"repoUrl":1369,"updatedAt":1498},"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},[1496,1497],{"name":1432,"slug":1433,"type":16},{"name":1392,"slug":1393,"type":16},"2026-04-06T17:56:02.483316",{"slug":1500,"name":1500,"fn":1501,"description":1502,"org":1503,"tags":1504,"stars":1368,"repoUrl":1369,"updatedAt":1511},"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},[1505,1508],{"name":1506,"slug":1507,"type":16},"PowerPoint","powerpoint",{"name":1509,"slug":1510,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1513,"name":1513,"fn":1514,"description":1515,"org":1516,"tags":1517,"stars":1368,"repoUrl":1369,"updatedAt":1527},"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},[1518,1519,1520,1523,1526],{"name":1402,"slug":1403,"type":16},{"name":1293,"slug":1294,"type":16},{"name":1521,"slug":1522,"type":16},"Evals","evals",{"name":1524,"slug":1525,"type":16},"Performance","performance",{"name":1422,"slug":1423,"type":16},"2026-04-19T06:45:40.804",490]