[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-write-query":3,"mdc-3kdagu-key":34,"related-repo-anthropic-write-query":689,"related-org-anthropic-write-query":806},{"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},"write-query","write optimized SQL queries","Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.",{"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},"Performance","performance","tag",{"name":18,"slug":19,"type":16},"Database","database",{"name":21,"slug":22,"type":16},"SQL","sql",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T17:57:27.88468",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\u002Fdata\u002Fskills\u002Fwrite-query","---\nname: write-query\ndescription: Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.\nargument-hint: \"\u003Cdescription of what data you need>\"\n---\n\n# \u002Fwrite-query - Write Optimized SQL\n\n> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](..\u002F..\u002FCONNECTORS.md).\n\nWrite a SQL query from a natural language description, optimized for your specific SQL dialect and following best practices.\n\n## Usage\n\n```\n\u002Fwrite-query \u003Cdescription of what data you need>\n```\n\n## Workflow\n\n### 1. Understand the Request\n\nParse the user's description to identify:\n\n- **Output columns**: What fields should the result include?\n- **Filters**: What conditions limit the data (time ranges, segments, statuses)?\n- **Aggregations**: Are there GROUP BY operations, counts, sums, averages?\n- **Joins**: Does this require combining multiple tables?\n- **Ordering**: How should results be sorted?\n- **Limits**: Is there a top-N or sample requirement?\n\n### 2. Determine SQL Dialect\n\nIf the user's SQL dialect is not already known, ask which they use:\n\n- **PostgreSQL** (including Aurora, RDS, Supabase, Neon)\n- **Snowflake**\n- **BigQuery** (Google Cloud)\n- **Redshift** (Amazon)\n- **Databricks SQL**\n- **MySQL** (including Aurora MySQL, PlanetScale)\n- **SQL Server** (Microsoft)\n- **DuckDB**\n- **SQLite**\n- **Other** (ask for specifics)\n\nRemember the dialect for future queries in the same session.\n\n### 3. Discover Schema (If Warehouse Connected)\n\nIf a data warehouse MCP server is connected:\n\n1. Search for relevant tables based on the user's description\n2. Inspect column names, types, and relationships\n3. Check for partitioning or clustering keys that affect performance\n4. Look for pre-built views or materialized views that might simplify the query\n\n### 4. Write the Query\n\nFollow these best practices:\n\n**Structure:**\n- Use CTEs (WITH clauses) for readability when queries have multiple logical steps\n- One CTE per logical transformation or data source\n- Name CTEs descriptively (e.g., `daily_signups`, `active_users`, `revenue_by_product`)\n\n**Performance:**\n- Never use `SELECT *` in production queries -- specify only needed columns\n- Filter early (push WHERE clauses as close to the base tables as possible)\n- Use partition filters when available (especially date partitions)\n- Prefer `EXISTS` over `IN` for subqueries with large result sets\n- Use appropriate JOIN types (don't use LEFT JOIN when INNER JOIN is correct)\n- Avoid correlated subqueries when a JOIN or window function works\n- Be mindful of exploding joins (many-to-many)\n\n**Readability:**\n- Add comments explaining the \"why\" for non-obvious logic\n- Use consistent indentation and formatting\n- Alias tables with meaningful short names (not just `a`, `b`, `c`)\n- Put each major clause on its own line\n\n**Dialect-specific optimizations:**\n- Apply dialect-specific syntax and functions (see `sql-queries` skill for details)\n- Use dialect-appropriate date functions, string functions, and window syntax\n- Note any dialect-specific performance features (e.g., Snowflake clustering, BigQuery partitioning)\n\n### 5. Present the Query\n\nProvide:\n\n1. **The complete query** in a SQL code block with syntax highlighting\n2. **Brief explanation** of what each CTE or section does\n3. **Performance notes** if relevant (expected cost, partition usage, potential bottlenecks)\n4. **Modification suggestions** -- how to adjust for common variations (different time range, different granularity, additional filters)\n\n### 6. Offer to Execute\n\nIf a data warehouse is connected, offer to run the query and analyze the results. If the user wants to run it themselves, the query is ready to copy-paste.\n\n## Examples\n\n**Simple aggregation:**\n```\n\u002Fwrite-query Count of orders by status for the last 30 days\n```\n\n**Complex analysis:**\n```\n\u002Fwrite-query Cohort retention analysis -- group users by their signup month, then show what percentage are still active (had at least one event) at 1, 3, 6, and 12 months after signup\n```\n\n**Performance-critical:**\n```\n\u002Fwrite-query We have a 500M row events table partitioned by date. Find the top 100 users by event count in the last 7 days with their most recent event type.\n```\n\n## Tips\n\n- Mention your SQL dialect upfront to get the right syntax immediately\n- If you know the table names, include them -- otherwise Claude will help you find them\n- Specify if you need the query to be idempotent (safe to re-run) or one-time\n- For recurring queries, mention if it should be parameterized for date ranges\n",{"data":35,"body":37},{"name":4,"description":6,"argument-hint":36},"\u003Cdescription of what data you need>",{"type":38,"children":39},"root",[40,49,68,73,80,93,99,106,111,177,183,188,283,288,294,299,323,329,334,342,383,391,453,461,504,512,538,544,549,592,598,603,609,617,626,634,643,651,660,666],{"type":41,"tag":42,"props":43,"children":45},"element","h1",{"id":44},"write-query-write-optimized-sql",[46],{"type":47,"value":48},"text","\u002Fwrite-query - Write Optimized SQL",{"type":41,"tag":50,"props":51,"children":52},"blockquote",{},[53],{"type":41,"tag":54,"props":55,"children":56},"p",{},[57,59,66],{"type":47,"value":58},"If you see unfamiliar placeholders or need to check which tools are connected, see ",{"type":41,"tag":60,"props":61,"children":63},"a",{"href":62},"..\u002F..\u002FCONNECTORS.md",[64],{"type":47,"value":65},"CONNECTORS.md",{"type":47,"value":67},".",{"type":41,"tag":54,"props":69,"children":70},{},[71],{"type":47,"value":72},"Write a SQL query from a natural language description, optimized for your specific SQL dialect and following best practices.",{"type":41,"tag":74,"props":75,"children":77},"h2",{"id":76},"usage",[78],{"type":47,"value":79},"Usage",{"type":41,"tag":81,"props":82,"children":86},"pre",{"className":83,"code":85,"language":47},[84],"language-text","\u002Fwrite-query \u003Cdescription of what data you need>\n",[87],{"type":41,"tag":88,"props":89,"children":91},"code",{"__ignoreMap":90},"",[92],{"type":47,"value":85},{"type":41,"tag":74,"props":94,"children":96},{"id":95},"workflow",[97],{"type":47,"value":98},"Workflow",{"type":41,"tag":100,"props":101,"children":103},"h3",{"id":102},"_1-understand-the-request",[104],{"type":47,"value":105},"1. Understand the Request",{"type":41,"tag":54,"props":107,"children":108},{},[109],{"type":47,"value":110},"Parse the user's description to identify:",{"type":41,"tag":112,"props":113,"children":114},"ul",{},[115,127,137,147,157,167],{"type":41,"tag":116,"props":117,"children":118},"li",{},[119,125],{"type":41,"tag":120,"props":121,"children":122},"strong",{},[123],{"type":47,"value":124},"Output columns",{"type":47,"value":126},": What fields should the result include?",{"type":41,"tag":116,"props":128,"children":129},{},[130,135],{"type":41,"tag":120,"props":131,"children":132},{},[133],{"type":47,"value":134},"Filters",{"type":47,"value":136},": What conditions limit the data (time ranges, segments, statuses)?",{"type":41,"tag":116,"props":138,"children":139},{},[140,145],{"type":41,"tag":120,"props":141,"children":142},{},[143],{"type":47,"value":144},"Aggregations",{"type":47,"value":146},": Are there GROUP BY operations, counts, sums, averages?",{"type":41,"tag":116,"props":148,"children":149},{},[150,155],{"type":41,"tag":120,"props":151,"children":152},{},[153],{"type":47,"value":154},"Joins",{"type":47,"value":156},": Does this require combining multiple tables?",{"type":41,"tag":116,"props":158,"children":159},{},[160,165],{"type":41,"tag":120,"props":161,"children":162},{},[163],{"type":47,"value":164},"Ordering",{"type":47,"value":166},": How should results be sorted?",{"type":41,"tag":116,"props":168,"children":169},{},[170,175],{"type":41,"tag":120,"props":171,"children":172},{},[173],{"type":47,"value":174},"Limits",{"type":47,"value":176},": Is there a top-N or sample requirement?",{"type":41,"tag":100,"props":178,"children":180},{"id":179},"_2-determine-sql-dialect",[181],{"type":47,"value":182},"2. Determine SQL Dialect",{"type":41,"tag":54,"props":184,"children":185},{},[186],{"type":47,"value":187},"If the user's SQL dialect is not already known, ask which they use:",{"type":41,"tag":112,"props":189,"children":190},{},[191,201,209,219,229,237,247,257,265,273],{"type":41,"tag":116,"props":192,"children":193},{},[194,199],{"type":41,"tag":120,"props":195,"children":196},{},[197],{"type":47,"value":198},"PostgreSQL",{"type":47,"value":200}," (including Aurora, RDS, Supabase, Neon)",{"type":41,"tag":116,"props":202,"children":203},{},[204],{"type":41,"tag":120,"props":205,"children":206},{},[207],{"type":47,"value":208},"Snowflake",{"type":41,"tag":116,"props":210,"children":211},{},[212,217],{"type":41,"tag":120,"props":213,"children":214},{},[215],{"type":47,"value":216},"BigQuery",{"type":47,"value":218}," (Google Cloud)",{"type":41,"tag":116,"props":220,"children":221},{},[222,227],{"type":41,"tag":120,"props":223,"children":224},{},[225],{"type":47,"value":226},"Redshift",{"type":47,"value":228}," (Amazon)",{"type":41,"tag":116,"props":230,"children":231},{},[232],{"type":41,"tag":120,"props":233,"children":234},{},[235],{"type":47,"value":236},"Databricks SQL",{"type":41,"tag":116,"props":238,"children":239},{},[240,245],{"type":41,"tag":120,"props":241,"children":242},{},[243],{"type":47,"value":244},"MySQL",{"type":47,"value":246}," (including Aurora MySQL, PlanetScale)",{"type":41,"tag":116,"props":248,"children":249},{},[250,255],{"type":41,"tag":120,"props":251,"children":252},{},[253],{"type":47,"value":254},"SQL Server",{"type":47,"value":256}," (Microsoft)",{"type":41,"tag":116,"props":258,"children":259},{},[260],{"type":41,"tag":120,"props":261,"children":262},{},[263],{"type":47,"value":264},"DuckDB",{"type":41,"tag":116,"props":266,"children":267},{},[268],{"type":41,"tag":120,"props":269,"children":270},{},[271],{"type":47,"value":272},"SQLite",{"type":41,"tag":116,"props":274,"children":275},{},[276,281],{"type":41,"tag":120,"props":277,"children":278},{},[279],{"type":47,"value":280},"Other",{"type":47,"value":282}," (ask for specifics)",{"type":41,"tag":54,"props":284,"children":285},{},[286],{"type":47,"value":287},"Remember the dialect for future queries in the same session.",{"type":41,"tag":100,"props":289,"children":291},{"id":290},"_3-discover-schema-if-warehouse-connected",[292],{"type":47,"value":293},"3. Discover Schema (If Warehouse Connected)",{"type":41,"tag":54,"props":295,"children":296},{},[297],{"type":47,"value":298},"If a data warehouse MCP server is connected:",{"type":41,"tag":300,"props":301,"children":302},"ol",{},[303,308,313,318],{"type":41,"tag":116,"props":304,"children":305},{},[306],{"type":47,"value":307},"Search for relevant tables based on the user's description",{"type":41,"tag":116,"props":309,"children":310},{},[311],{"type":47,"value":312},"Inspect column names, types, and relationships",{"type":41,"tag":116,"props":314,"children":315},{},[316],{"type":47,"value":317},"Check for partitioning or clustering keys that affect performance",{"type":41,"tag":116,"props":319,"children":320},{},[321],{"type":47,"value":322},"Look for pre-built views or materialized views that might simplify the query",{"type":41,"tag":100,"props":324,"children":326},{"id":325},"_4-write-the-query",[327],{"type":47,"value":328},"4. Write the Query",{"type":41,"tag":54,"props":330,"children":331},{},[332],{"type":47,"value":333},"Follow these best practices:",{"type":41,"tag":54,"props":335,"children":336},{},[337],{"type":41,"tag":120,"props":338,"children":339},{},[340],{"type":47,"value":341},"Structure:",{"type":41,"tag":112,"props":343,"children":344},{},[345,350,355],{"type":41,"tag":116,"props":346,"children":347},{},[348],{"type":47,"value":349},"Use CTEs (WITH clauses) for readability when queries have multiple logical steps",{"type":41,"tag":116,"props":351,"children":352},{},[353],{"type":47,"value":354},"One CTE per logical transformation or data source",{"type":41,"tag":116,"props":356,"children":357},{},[358,360,366,368,374,375,381],{"type":47,"value":359},"Name CTEs descriptively (e.g., ",{"type":41,"tag":88,"props":361,"children":363},{"className":362},[],[364],{"type":47,"value":365},"daily_signups",{"type":47,"value":367},", ",{"type":41,"tag":88,"props":369,"children":371},{"className":370},[],[372],{"type":47,"value":373},"active_users",{"type":47,"value":367},{"type":41,"tag":88,"props":376,"children":378},{"className":377},[],[379],{"type":47,"value":380},"revenue_by_product",{"type":47,"value":382},")",{"type":41,"tag":54,"props":384,"children":385},{},[386],{"type":41,"tag":120,"props":387,"children":388},{},[389],{"type":47,"value":390},"Performance:",{"type":41,"tag":112,"props":392,"children":393},{},[394,407,412,417,438,443,448],{"type":41,"tag":116,"props":395,"children":396},{},[397,399,405],{"type":47,"value":398},"Never use ",{"type":41,"tag":88,"props":400,"children":402},{"className":401},[],[403],{"type":47,"value":404},"SELECT *",{"type":47,"value":406}," in production queries -- specify only needed columns",{"type":41,"tag":116,"props":408,"children":409},{},[410],{"type":47,"value":411},"Filter early (push WHERE clauses as close to the base tables as possible)",{"type":41,"tag":116,"props":413,"children":414},{},[415],{"type":47,"value":416},"Use partition filters when available (especially date partitions)",{"type":41,"tag":116,"props":418,"children":419},{},[420,422,428,430,436],{"type":47,"value":421},"Prefer ",{"type":41,"tag":88,"props":423,"children":425},{"className":424},[],[426],{"type":47,"value":427},"EXISTS",{"type":47,"value":429}," over ",{"type":41,"tag":88,"props":431,"children":433},{"className":432},[],[434],{"type":47,"value":435},"IN",{"type":47,"value":437}," for subqueries with large result sets",{"type":41,"tag":116,"props":439,"children":440},{},[441],{"type":47,"value":442},"Use appropriate JOIN types (don't use LEFT JOIN when INNER JOIN is correct)",{"type":41,"tag":116,"props":444,"children":445},{},[446],{"type":47,"value":447},"Avoid correlated subqueries when a JOIN or window function works",{"type":41,"tag":116,"props":449,"children":450},{},[451],{"type":47,"value":452},"Be mindful of exploding joins (many-to-many)",{"type":41,"tag":54,"props":454,"children":455},{},[456],{"type":41,"tag":120,"props":457,"children":458},{},[459],{"type":47,"value":460},"Readability:",{"type":41,"tag":112,"props":462,"children":463},{},[464,469,474,499],{"type":41,"tag":116,"props":465,"children":466},{},[467],{"type":47,"value":468},"Add comments explaining the \"why\" for non-obvious logic",{"type":41,"tag":116,"props":470,"children":471},{},[472],{"type":47,"value":473},"Use consistent indentation and formatting",{"type":41,"tag":116,"props":475,"children":476},{},[477,479,484,485,491,492,498],{"type":47,"value":478},"Alias tables with meaningful short names (not just ",{"type":41,"tag":88,"props":480,"children":482},{"className":481},[],[483],{"type":47,"value":60},{"type":47,"value":367},{"type":41,"tag":88,"props":486,"children":488},{"className":487},[],[489],{"type":47,"value":490},"b",{"type":47,"value":367},{"type":41,"tag":88,"props":493,"children":495},{"className":494},[],[496],{"type":47,"value":497},"c",{"type":47,"value":382},{"type":41,"tag":116,"props":500,"children":501},{},[502],{"type":47,"value":503},"Put each major clause on its own line",{"type":41,"tag":54,"props":505,"children":506},{},[507],{"type":41,"tag":120,"props":508,"children":509},{},[510],{"type":47,"value":511},"Dialect-specific optimizations:",{"type":41,"tag":112,"props":513,"children":514},{},[515,528,533],{"type":41,"tag":116,"props":516,"children":517},{},[518,520,526],{"type":47,"value":519},"Apply dialect-specific syntax and functions (see ",{"type":41,"tag":88,"props":521,"children":523},{"className":522},[],[524],{"type":47,"value":525},"sql-queries",{"type":47,"value":527}," skill for details)",{"type":41,"tag":116,"props":529,"children":530},{},[531],{"type":47,"value":532},"Use dialect-appropriate date functions, string functions, and window syntax",{"type":41,"tag":116,"props":534,"children":535},{},[536],{"type":47,"value":537},"Note any dialect-specific performance features (e.g., Snowflake clustering, BigQuery partitioning)",{"type":41,"tag":100,"props":539,"children":541},{"id":540},"_5-present-the-query",[542],{"type":47,"value":543},"5. Present the Query",{"type":41,"tag":54,"props":545,"children":546},{},[547],{"type":47,"value":548},"Provide:",{"type":41,"tag":300,"props":550,"children":551},{},[552,562,572,582],{"type":41,"tag":116,"props":553,"children":554},{},[555,560],{"type":41,"tag":120,"props":556,"children":557},{},[558],{"type":47,"value":559},"The complete query",{"type":47,"value":561}," in a SQL code block with syntax highlighting",{"type":41,"tag":116,"props":563,"children":564},{},[565,570],{"type":41,"tag":120,"props":566,"children":567},{},[568],{"type":47,"value":569},"Brief explanation",{"type":47,"value":571}," of what each CTE or section does",{"type":41,"tag":116,"props":573,"children":574},{},[575,580],{"type":41,"tag":120,"props":576,"children":577},{},[578],{"type":47,"value":579},"Performance notes",{"type":47,"value":581}," if relevant (expected cost, partition usage, potential bottlenecks)",{"type":41,"tag":116,"props":583,"children":584},{},[585,590],{"type":41,"tag":120,"props":586,"children":587},{},[588],{"type":47,"value":589},"Modification suggestions",{"type":47,"value":591}," -- how to adjust for common variations (different time range, different granularity, additional filters)",{"type":41,"tag":100,"props":593,"children":595},{"id":594},"_6-offer-to-execute",[596],{"type":47,"value":597},"6. Offer to Execute",{"type":41,"tag":54,"props":599,"children":600},{},[601],{"type":47,"value":602},"If a data warehouse is connected, offer to run the query and analyze the results. If the user wants to run it themselves, the query is ready to copy-paste.",{"type":41,"tag":74,"props":604,"children":606},{"id":605},"examples",[607],{"type":47,"value":608},"Examples",{"type":41,"tag":54,"props":610,"children":611},{},[612],{"type":41,"tag":120,"props":613,"children":614},{},[615],{"type":47,"value":616},"Simple aggregation:",{"type":41,"tag":81,"props":618,"children":621},{"className":619,"code":620,"language":47},[84],"\u002Fwrite-query Count of orders by status for the last 30 days\n",[622],{"type":41,"tag":88,"props":623,"children":624},{"__ignoreMap":90},[625],{"type":47,"value":620},{"type":41,"tag":54,"props":627,"children":628},{},[629],{"type":41,"tag":120,"props":630,"children":631},{},[632],{"type":47,"value":633},"Complex analysis:",{"type":41,"tag":81,"props":635,"children":638},{"className":636,"code":637,"language":47},[84],"\u002Fwrite-query Cohort retention analysis -- group users by their signup month, then show what percentage are still active (had at least one event) at 1, 3, 6, and 12 months after signup\n",[639],{"type":41,"tag":88,"props":640,"children":641},{"__ignoreMap":90},[642],{"type":47,"value":637},{"type":41,"tag":54,"props":644,"children":645},{},[646],{"type":41,"tag":120,"props":647,"children":648},{},[649],{"type":47,"value":650},"Performance-critical:",{"type":41,"tag":81,"props":652,"children":655},{"className":653,"code":654,"language":47},[84],"\u002Fwrite-query We have a 500M row events table partitioned by date. Find the top 100 users by event count in the last 7 days with their most recent event type.\n",[656],{"type":41,"tag":88,"props":657,"children":658},{"__ignoreMap":90},[659],{"type":47,"value":654},{"type":41,"tag":74,"props":661,"children":663},{"id":662},"tips",[664],{"type":47,"value":665},"Tips",{"type":41,"tag":112,"props":667,"children":668},{},[669,674,679,684],{"type":41,"tag":116,"props":670,"children":671},{},[672],{"type":47,"value":673},"Mention your SQL dialect upfront to get the right syntax immediately",{"type":41,"tag":116,"props":675,"children":676},{},[677],{"type":47,"value":678},"If you know the table names, include them -- otherwise Claude will help you find them",{"type":41,"tag":116,"props":680,"children":681},{},[682],{"type":47,"value":683},"Specify if you need the query to be idempotent (safe to re-run) or one-time",{"type":41,"tag":116,"props":685,"children":686},{},[687],{"type":47,"value":688},"For recurring queries, mention if it should be parameterized for date ranges",{"items":690,"total":805},[691,707,723,737,755,774,790],{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":23,"repoUrl":24,"updatedAt":706},"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},[697,700,703],{"name":698,"slug":699,"type":16},"Accessibility","accessibility",{"name":701,"slug":702,"type":16},"Design","design",{"name":704,"slug":705,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":708,"name":708,"fn":709,"description":710,"org":711,"tags":712,"stars":23,"repoUrl":24,"updatedAt":722},"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},[713,716,719],{"name":714,"slug":715,"type":16},"CRM","crm",{"name":717,"slug":718,"type":16},"Research","research",{"name":720,"slug":721,"type":16},"Sales","sales","2026-04-06T17:56:41.410418",{"slug":724,"name":724,"fn":725,"description":726,"org":727,"tags":728,"stars":23,"repoUrl":24,"updatedAt":736},"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},[729,732,735],{"name":730,"slug":731,"type":16},"Analytics","analytics",{"name":733,"slug":734,"type":16},"Data Analysis","data-analysis",{"name":21,"slug":22,"type":16},"2026-04-06T17:57:21.593647",{"slug":738,"name":738,"fn":739,"description":740,"org":741,"tags":742,"stars":23,"repoUrl":24,"updatedAt":754},"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},[743,746,748,751],{"name":744,"slug":745,"type":16},"ADR","adr",{"name":747,"slug":738,"type":16},"Architecture",{"name":749,"slug":750,"type":16},"Documentation","documentation",{"name":752,"slug":753,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":756,"name":756,"fn":757,"description":758,"org":759,"tags":760,"stars":23,"repoUrl":24,"updatedAt":773},"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},[761,764,767,770],{"name":762,"slug":763,"type":16},"Audit","audit",{"name":765,"slug":766,"type":16},"Finance","finance",{"name":768,"slug":769,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":771,"slug":772,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":775,"name":775,"fn":776,"description":777,"org":778,"tags":779,"stars":23,"repoUrl":24,"updatedAt":789},"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},[780,783,786],{"name":781,"slug":782,"type":16},"Branding","branding",{"name":784,"slug":785,"type":16},"Marketing","marketing",{"name":787,"slug":788,"type":16},"Writing","writing","2026-04-06T17:58:19.548331",{"slug":791,"name":791,"fn":792,"description":793,"org":794,"tags":795,"stars":23,"repoUrl":24,"updatedAt":804},"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},[796,797,800,803],{"name":781,"slug":782,"type":16},{"name":798,"slug":799,"type":16},"Communications","communications",{"name":801,"slug":802,"type":16},"Content Creation","content-creation",{"name":787,"slug":788,"type":16},"2026-04-06T18:00:23.528956",200,{"items":807,"total":982},[808,827,839,851,870,881,902,922,932,947,955,968],{"slug":809,"name":809,"fn":810,"description":811,"org":812,"tags":813,"stars":824,"repoUrl":825,"updatedAt":826},"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},[814,817,818,821],{"name":815,"slug":816,"type":16},"Creative","creative",{"name":701,"slug":702,"type":16},{"name":819,"slug":820,"type":16},"Generative Art","generative-art",{"name":822,"slug":823,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":828,"name":828,"fn":829,"description":830,"org":831,"tags":832,"stars":824,"repoUrl":825,"updatedAt":838},"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},[833,834,835],{"name":781,"slug":782,"type":16},{"name":701,"slug":702,"type":16},{"name":836,"slug":837,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":840,"name":840,"fn":841,"description":842,"org":843,"tags":844,"stars":824,"repoUrl":825,"updatedAt":850},"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},[845,846,847],{"name":815,"slug":816,"type":16},{"name":701,"slug":702,"type":16},{"name":848,"slug":849,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":852,"name":852,"fn":853,"description":854,"org":855,"tags":856,"stars":824,"repoUrl":825,"updatedAt":869},"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},[857,860,861,864,866],{"name":858,"slug":859,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":862,"slug":863,"type":16},"Anthropic SDK","anthropic-sdk",{"name":865,"slug":852,"type":16},"Claude API",{"name":867,"slug":868,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":871,"name":871,"fn":872,"description":873,"org":874,"tags":875,"stars":824,"repoUrl":825,"updatedAt":880},"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},[876,877],{"name":749,"slug":750,"type":16},{"name":878,"slug":879,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":882,"name":882,"fn":883,"description":884,"org":885,"tags":886,"stars":824,"repoUrl":825,"updatedAt":901},"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},[887,890,892,895,898],{"name":888,"slug":889,"type":16},"Documents","documents",{"name":891,"slug":882,"type":16},"DOCX",{"name":893,"slug":894,"type":16},"Office","office",{"name":896,"slug":897,"type":16},"Templates","templates",{"name":899,"slug":900,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":903,"name":903,"fn":904,"description":905,"org":906,"tags":907,"stars":824,"repoUrl":825,"updatedAt":921},"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},[908,909,912,915,918],{"name":701,"slug":702,"type":16},{"name":910,"slug":911,"type":16},"Frontend","frontend",{"name":913,"slug":914,"type":16},"React","react",{"name":916,"slug":917,"type":16},"Tailwind CSS","tailwind-css",{"name":919,"slug":920,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":923,"name":923,"fn":924,"description":925,"org":926,"tags":927,"stars":824,"repoUrl":825,"updatedAt":931},"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},[928,929,930],{"name":798,"slug":799,"type":16},{"name":896,"slug":897,"type":16},{"name":787,"slug":788,"type":16},"2026-04-06T17:56:20.695522",{"slug":933,"name":933,"fn":934,"description":935,"org":936,"tags":937,"stars":824,"repoUrl":825,"updatedAt":946},"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},[938,939,942,943],{"name":858,"slug":859,"type":16},{"name":940,"slug":941,"type":16},"API Development","api-development",{"name":867,"slug":868,"type":16},{"name":944,"slug":945,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":849,"name":849,"fn":948,"description":949,"org":950,"tags":951,"stars":824,"repoUrl":825,"updatedAt":954},"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},[952,953],{"name":888,"slug":889,"type":16},{"name":848,"slug":849,"type":16},"2026-04-06T17:56:02.483316",{"slug":956,"name":956,"fn":957,"description":958,"org":959,"tags":960,"stars":824,"repoUrl":825,"updatedAt":967},"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},[961,964],{"name":962,"slug":963,"type":16},"PowerPoint","powerpoint",{"name":965,"slug":966,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":969,"name":969,"fn":970,"description":971,"org":972,"tags":973,"stars":824,"repoUrl":825,"updatedAt":981},"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},[974,975,976,979,980],{"name":858,"slug":859,"type":16},{"name":749,"slug":750,"type":16},{"name":977,"slug":978,"type":16},"Evals","evals",{"name":14,"slug":15,"type":16},{"name":878,"slug":879,"type":16},"2026-04-19T06:45:40.804",490]