[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-cline-steering-user-elicitation":3,"mdc-7v0prq-key":33,"related-repo-cline-steering-user-elicitation":323,"related-org-cline-steering-user-elicitation":444},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"steering-user-elicitation","clarify data analysis requirements","Elicit and challenge data-analysis requirements before querying. Use when the user asks ambiguous data questions, requests business\u002Freport answers, needs metric definitions clarified, or may be drawing decisions from incomplete data.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"cline","Cline","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fcline.png",[12,16,19],{"name":13,"slug":14,"type":15},"Requirements","requirements","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":20,"slug":21,"type":15},"Analytics","analytics",10,"https:\u002F\u002Fgithub.com\u002Fcline\u002Fskills","2026-07-12T08:14:10.476044",null,4,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"A collection of skills used at Cline","https:\u002F\u002Fgithub.com\u002Fcline\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fdata-analyst\u002Fskills\u002Fsteering-user-elicitation","---\nname: steering-user-elicitation\ndescription: Elicit and challenge data-analysis requirements before querying. Use when the user asks ambiguous data questions, requests business\u002Freport answers, needs metric definitions clarified, or may be drawing decisions from incomplete data.\n---\n\n# Steering and User Elicitation\n\nThis skill describes how to fill the Intent block (defined in the parent `data-analyst\u002FSKILL.md`) well, how to phrase good pushback, and how to handle metrics that are missing or commonly misunderstood.\n\nStart from the assumption that the first request is underspecified; it almost always is. Most data requests have hidden ambiguity even when they read cleanly. Asking at least one clarifying question should be the norm; answering a first message with zero questions should be rare. The goal is productive friction, not an exhausting questionnaire.\n\n## Filling each Intent field\n\nFor each Intent field, choose the right marker:\n\n- Confirmed when the user stated it explicitly in this conversation.\n- Assumed only for genuinely low-stakes fields where a wrong guess would not change the answer's shape or the user's decision. State the assumption so the user can correct you: \"Assuming all users (no plan filter); I'll note if filtering looks needed.\" If a wrong guess could mislead, it is NEED FROM USER, not Assumed.\n- NEED FROM USER when the field materially affects the result and the user did not specify it, the normal state of most fields on a first request. Stop and ask one targeted question.\n- LOOK UP: `\u003Cterm>` when the field references a term with a documented definition (a named metric, a funnel stage). Resolve it via `..\u002Freading-data-dict\u002F` before querying; do not guess its meaning.\n\nWhat each field is asking:\n\n- Metric: what exactly should be counted, summed, averaged, or compared?\n- Population: users, accounts, sessions, requests, versions, providers, or feature users?\n- Time window: dates, release window, week-over-week, last N days?\n- Grain: daily, weekly, per release, per user, per workspace?\n- Filters: plan, platform, model\u002Fprovider, version, geography, telemetry enabled?\n- Output: quick answer, SQL, CSV, chart, HTML\u002Freport, or dashboard seed?\n\nAlso keep audience in mind (internal debug, exec\u002Fbusiness update, customer\u002Finvestor answer); it raises the bar for confirming definitions before presenting.\n\nA block with no questions at all should be rare and deliberate, not the easy path. If you filled every field as Confirmed or Assumed, stop and re-check: which metric definition, which population (unique users vs events), which window (and the current partial day?), which grain? At least one of these is usually a real choice the user should make. The rule is \"ask the one or two questions that most change the answer,\" not \"find a default for everything so you can proceed.\"\n\n## Good pushback\n\nUse targeted pushback like:\n\n- \"I can answer this two ways: raw event count or unique affected users. Which do you want?\"\n- \"This metric is only representative of telemetry-enabled users. Is directional analysis acceptable?\"\n- \"A 2-day window may be noisy. Should I compare against the prior 2 days or prior week?\"\n- \"Before plotting this, I want to confirm the definition of active user.\"\n\n## When the metric doesn't exist\n\nIf the exact metric the user is asking for does not exist in the available data (schema, data dictionary, or known tables), do not silently substitute a proxy metric. Instead, pause and ask clarifying questions:\n\n- \"I don't see a direct metric for X. The closest available options are Y and Z, would either of these work?\"\n- \"That metric isn't in our current schema. Can you describe what you're trying to measure so I can find the best approximation?\"\n- \"I can approximate this using [field], but it may not match your definition exactly. Should I proceed with that caveat, or would you like to refine the request?\"\n\n## When the metric exists but the user likely means something else\n\nThe harder case is a term that is documented but commonly means different things. \"Revenue\" may mean billings, net, or gross; \"active user\" may mean any-event vs a task-creating user; a \"task\" may be created vs completed. When a request uses such a term:\n\n- Mark it LOOK UP in the Intent block and resolve the documented definition.\n- If the documented definition diverges from common usage, surface it before assuming: \"Our `revenue` model is net of refunds, is that the figure you want, or gross billings?\"\n- Do not silently adopt the documented definition just because it exists. Confirm it when the divergence could change the answer or the decision.\n\n## When to skip the full Intent block\n\nAlways produce the Intent block. You may skip asking questions (mark every field Confirmed or Assumed, none NEED FROM USER) only when the request is mechanically unambiguous. Treat this as a checkable test, not a judgment call, skip questions only if the user's message contains all of:\n\n- a fully-qualified table or documented metric name (no interpretation needed),\n- an explicit time window (a date literal or an unambiguous relative window),\n- an explicit aggregate or operation (count, sum, avg, top-N, etc.).\n\nExample that qualifies: \"How many rows in `analytics.events_daily` from 2026-05-20 to 2026-05-27?\"\n\nIf any of those three is missing or interpretable, at least one field is NEED FROM USER or LOOK UP, do not skip.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,62,67,74,79,120,125,158,163,168,174,179,202,208,213,239,245,250,276,282,287,305,318],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"steering-and-user-elicitation",[44],{"type":45,"value":46},"text","Steering and User Elicitation",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51,53,60],{"type":45,"value":52},"This skill describes how to fill the Intent block (defined in the parent ",{"type":39,"tag":54,"props":55,"children":57},"code",{"className":56},[],[58],{"type":45,"value":59},"data-analyst\u002FSKILL.md",{"type":45,"value":61},") well, how to phrase good pushback, and how to handle metrics that are missing or commonly misunderstood.",{"type":39,"tag":48,"props":63,"children":64},{},[65],{"type":45,"value":66},"Start from the assumption that the first request is underspecified; it almost always is. Most data requests have hidden ambiguity even when they read cleanly. Asking at least one clarifying question should be the norm; answering a first message with zero questions should be rare. The goal is productive friction, not an exhausting questionnaire.",{"type":39,"tag":68,"props":69,"children":71},"h2",{"id":70},"filling-each-intent-field",[72],{"type":45,"value":73},"Filling each Intent field",{"type":39,"tag":48,"props":75,"children":76},{},[77],{"type":45,"value":78},"For each Intent field, choose the right marker:",{"type":39,"tag":80,"props":81,"children":82},"ul",{},[83,89,94,99],{"type":39,"tag":84,"props":85,"children":86},"li",{},[87],{"type":45,"value":88},"Confirmed when the user stated it explicitly in this conversation.",{"type":39,"tag":84,"props":90,"children":91},{},[92],{"type":45,"value":93},"Assumed only for genuinely low-stakes fields where a wrong guess would not change the answer's shape or the user's decision. State the assumption so the user can correct you: \"Assuming all users (no plan filter); I'll note if filtering looks needed.\" If a wrong guess could mislead, it is NEED FROM USER, not Assumed.",{"type":39,"tag":84,"props":95,"children":96},{},[97],{"type":45,"value":98},"NEED FROM USER when the field materially affects the result and the user did not specify it, the normal state of most fields on a first request. Stop and ask one targeted question.",{"type":39,"tag":84,"props":100,"children":101},{},[102,104,110,112,118],{"type":45,"value":103},"LOOK UP: ",{"type":39,"tag":54,"props":105,"children":107},{"className":106},[],[108],{"type":45,"value":109},"\u003Cterm>",{"type":45,"value":111}," when the field references a term with a documented definition (a named metric, a funnel stage). Resolve it via ",{"type":39,"tag":54,"props":113,"children":115},{"className":114},[],[116],{"type":45,"value":117},"..\u002Freading-data-dict\u002F",{"type":45,"value":119}," before querying; do not guess its meaning.",{"type":39,"tag":48,"props":121,"children":122},{},[123],{"type":45,"value":124},"What each field is asking:",{"type":39,"tag":80,"props":126,"children":127},{},[128,133,138,143,148,153],{"type":39,"tag":84,"props":129,"children":130},{},[131],{"type":45,"value":132},"Metric: what exactly should be counted, summed, averaged, or compared?",{"type":39,"tag":84,"props":134,"children":135},{},[136],{"type":45,"value":137},"Population: users, accounts, sessions, requests, versions, providers, or feature users?",{"type":39,"tag":84,"props":139,"children":140},{},[141],{"type":45,"value":142},"Time window: dates, release window, week-over-week, last N days?",{"type":39,"tag":84,"props":144,"children":145},{},[146],{"type":45,"value":147},"Grain: daily, weekly, per release, per user, per workspace?",{"type":39,"tag":84,"props":149,"children":150},{},[151],{"type":45,"value":152},"Filters: plan, platform, model\u002Fprovider, version, geography, telemetry enabled?",{"type":39,"tag":84,"props":154,"children":155},{},[156],{"type":45,"value":157},"Output: quick answer, SQL, CSV, chart, HTML\u002Freport, or dashboard seed?",{"type":39,"tag":48,"props":159,"children":160},{},[161],{"type":45,"value":162},"Also keep audience in mind (internal debug, exec\u002Fbusiness update, customer\u002Finvestor answer); it raises the bar for confirming definitions before presenting.",{"type":39,"tag":48,"props":164,"children":165},{},[166],{"type":45,"value":167},"A block with no questions at all should be rare and deliberate, not the easy path. If you filled every field as Confirmed or Assumed, stop and re-check: which metric definition, which population (unique users vs events), which window (and the current partial day?), which grain? At least one of these is usually a real choice the user should make. The rule is \"ask the one or two questions that most change the answer,\" not \"find a default for everything so you can proceed.\"",{"type":39,"tag":68,"props":169,"children":171},{"id":170},"good-pushback",[172],{"type":45,"value":173},"Good pushback",{"type":39,"tag":48,"props":175,"children":176},{},[177],{"type":45,"value":178},"Use targeted pushback like:",{"type":39,"tag":80,"props":180,"children":181},{},[182,187,192,197],{"type":39,"tag":84,"props":183,"children":184},{},[185],{"type":45,"value":186},"\"I can answer this two ways: raw event count or unique affected users. Which do you want?\"",{"type":39,"tag":84,"props":188,"children":189},{},[190],{"type":45,"value":191},"\"This metric is only representative of telemetry-enabled users. Is directional analysis acceptable?\"",{"type":39,"tag":84,"props":193,"children":194},{},[195],{"type":45,"value":196},"\"A 2-day window may be noisy. Should I compare against the prior 2 days or prior week?\"",{"type":39,"tag":84,"props":198,"children":199},{},[200],{"type":45,"value":201},"\"Before plotting this, I want to confirm the definition of active user.\"",{"type":39,"tag":68,"props":203,"children":205},{"id":204},"when-the-metric-doesnt-exist",[206],{"type":45,"value":207},"When the metric doesn't exist",{"type":39,"tag":48,"props":209,"children":210},{},[211],{"type":45,"value":212},"If the exact metric the user is asking for does not exist in the available data (schema, data dictionary, or known tables), do not silently substitute a proxy metric. Instead, pause and ask clarifying questions:",{"type":39,"tag":80,"props":214,"children":215},{},[216,221,226],{"type":39,"tag":84,"props":217,"children":218},{},[219],{"type":45,"value":220},"\"I don't see a direct metric for X. The closest available options are Y and Z, would either of these work?\"",{"type":39,"tag":84,"props":222,"children":223},{},[224],{"type":45,"value":225},"\"That metric isn't in our current schema. Can you describe what you're trying to measure so I can find the best approximation?\"",{"type":39,"tag":84,"props":227,"children":228},{},[229,231,237],{"type":45,"value":230},"\"I can approximate this using ",{"type":39,"tag":232,"props":233,"children":234},"span",{},[235],{"type":45,"value":236},"field",{"type":45,"value":238},", but it may not match your definition exactly. Should I proceed with that caveat, or would you like to refine the request?\"",{"type":39,"tag":68,"props":240,"children":242},{"id":241},"when-the-metric-exists-but-the-user-likely-means-something-else",[243],{"type":45,"value":244},"When the metric exists but the user likely means something else",{"type":39,"tag":48,"props":246,"children":247},{},[248],{"type":45,"value":249},"The harder case is a term that is documented but commonly means different things. \"Revenue\" may mean billings, net, or gross; \"active user\" may mean any-event vs a task-creating user; a \"task\" may be created vs completed. When a request uses such a term:",{"type":39,"tag":80,"props":251,"children":252},{},[253,258,271],{"type":39,"tag":84,"props":254,"children":255},{},[256],{"type":45,"value":257},"Mark it LOOK UP in the Intent block and resolve the documented definition.",{"type":39,"tag":84,"props":259,"children":260},{},[261,263,269],{"type":45,"value":262},"If the documented definition diverges from common usage, surface it before assuming: \"Our ",{"type":39,"tag":54,"props":264,"children":266},{"className":265},[],[267],{"type":45,"value":268},"revenue",{"type":45,"value":270}," model is net of refunds, is that the figure you want, or gross billings?\"",{"type":39,"tag":84,"props":272,"children":273},{},[274],{"type":45,"value":275},"Do not silently adopt the documented definition just because it exists. Confirm it when the divergence could change the answer or the decision.",{"type":39,"tag":68,"props":277,"children":279},{"id":278},"when-to-skip-the-full-intent-block",[280],{"type":45,"value":281},"When to skip the full Intent block",{"type":39,"tag":48,"props":283,"children":284},{},[285],{"type":45,"value":286},"Always produce the Intent block. You may skip asking questions (mark every field Confirmed or Assumed, none NEED FROM USER) only when the request is mechanically unambiguous. Treat this as a checkable test, not a judgment call, skip questions only if the user's message contains all of:",{"type":39,"tag":80,"props":288,"children":289},{},[290,295,300],{"type":39,"tag":84,"props":291,"children":292},{},[293],{"type":45,"value":294},"a fully-qualified table or documented metric name (no interpretation needed),",{"type":39,"tag":84,"props":296,"children":297},{},[298],{"type":45,"value":299},"an explicit time window (a date literal or an unambiguous relative window),",{"type":39,"tag":84,"props":301,"children":302},{},[303],{"type":45,"value":304},"an explicit aggregate or operation (count, sum, avg, top-N, etc.).",{"type":39,"tag":48,"props":306,"children":307},{},[308,310,316],{"type":45,"value":309},"Example that qualifies: \"How many rows in ",{"type":39,"tag":54,"props":311,"children":313},{"className":312},[],[314],{"type":45,"value":315},"analytics.events_daily",{"type":45,"value":317}," from 2026-05-20 to 2026-05-27?\"",{"type":39,"tag":48,"props":319,"children":320},{},[321],{"type":45,"value":322},"If any of those three is missing or interpretable, at least one field is NEED FROM USER or LOOK UP, do not skip.",{"items":324,"total":443},[325,344,364,379,396,412,431],{"slug":326,"name":326,"fn":327,"description":328,"org":329,"tags":330,"stars":22,"repoUrl":23,"updatedAt":343},"amazon-location-service","integrate Amazon Location Service APIs","Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[331,334,337,340],{"name":332,"slug":333,"type":15},"API Development","api-development",{"name":335,"slug":336,"type":15},"AWS","aws",{"name":338,"slug":339,"type":15},"Maps","maps",{"name":341,"slug":342,"type":15},"Navigation","navigation","2026-07-12T08:13:53.294026",{"slug":345,"name":345,"fn":346,"description":347,"org":348,"tags":349,"stars":22,"repoUrl":23,"updatedAt":363},"amplify-workflow","build full-stack apps with AWS Amplify","Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync\u002FDynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify\u002F directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM\u002FCDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[350,353,354,357,360],{"name":351,"slug":352,"type":15},"Auth","auth",{"name":335,"slug":336,"type":15},{"name":355,"slug":356,"type":15},"Database","database",{"name":358,"slug":359,"type":15},"Frontend","frontend",{"name":361,"slug":362,"type":15},"TypeScript","typescript","2026-07-12T08:13:47.134012",{"slug":365,"name":365,"fn":366,"description":367,"org":368,"tags":369,"stars":22,"repoUrl":23,"updatedAt":378},"analyzer","analyze queried data for trends","Analyze queried data for trends, week-over-week comparisons, distributions, funnels, cohorts, top-N lists, anomalies, sanity checks, and report-ready findings. Use after or alongside ClickHouse queries when the user wants insight rather than raw rows.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[370,371,374,375],{"name":20,"slug":21,"type":15},{"name":372,"slug":373,"type":15},"ClickHouse","clickhouse",{"name":17,"slug":18,"type":15},{"name":376,"slug":377,"type":15},"Statistics","statistics","2026-07-12T08:14:05.606036",{"slug":380,"name":380,"fn":381,"description":382,"org":383,"tags":384,"stars":22,"repoUrl":23,"updatedAt":395},"artifact-management","manage and organize analysis artifacts","Save, organize, and describe reusable analysis artifacts such as SQL, result snapshots, CSV exports, summaries, caveats, plots, and report-ready files. Use when users ask to save, export, share, cite, reproduce, or organize data-analysis outputs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[385,386,389,392],{"name":17,"slug":18,"type":15},{"name":387,"slug":388,"type":15},"Productivity","productivity",{"name":390,"slug":391,"type":15},"Reporting","reporting",{"name":393,"slug":394,"type":15},"SQL","sql","2026-07-12T08:14:09.265555",{"slug":397,"name":397,"fn":398,"description":399,"org":400,"tags":401,"stars":22,"repoUrl":23,"updatedAt":411},"attorney-assist","connect with attorneys for legal consultation","Connects the user with a LegalZoom attorney for legal consultation. Use when a user asks about attorneys, lawyers, or legal help, or when contract review reveals high risks or low-confidence findings.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[402,405,408],{"name":403,"slug":404,"type":15},"Contracts","contracts",{"name":406,"slug":407,"type":15},"Legal","legal",{"name":409,"slug":410,"type":15},"Risk Assessment","risk-assessment","2026-07-12T08:13:45.878361",{"slug":413,"name":413,"fn":414,"description":415,"org":416,"tags":417,"stars":22,"repoUrl":23,"updatedAt":430},"building-pydantic-ai-agents","build AI agents with Pydantic AI","Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools\u002Fcapabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[418,421,424,427],{"name":419,"slug":420,"type":15},"Agents","agents",{"name":422,"slug":423,"type":15},"LLM","llm",{"name":425,"slug":426,"type":15},"Multi-Agent","multi-agent",{"name":428,"slug":429,"type":15},"Python","python","2026-07-12T08:14:01.893781",{"slug":373,"name":373,"fn":432,"description":433,"org":434,"tags":435,"stars":22,"repoUrl":23,"updatedAt":442},"query ClickHouse databases via CLI","Connect to and query ClickHouse (a local server or a ClickHouse Cloud service) from the terminal using the official clickhousectl CLI, including the browser OAuth login flow. Use when the user wants to run SQL against ClickHouse, explore schemas and tables, inspect Cloud services, or authenticate clickhousectl. For building a local dev environment or deploying to Cloud, defer to the official ClickHouse skills (see Scope).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[436,437,440,441],{"name":20,"slug":21,"type":15},{"name":438,"slug":439,"type":15},"CLI","cli",{"name":372,"slug":373,"type":15},{"name":355,"slug":356,"type":15},"2026-07-12T08:14:06.829692",43,{"items":445,"total":571},[446,453,461,468,475,481,488,495,507,525,545,558],{"slug":326,"name":326,"fn":327,"description":328,"org":447,"tags":448,"stars":22,"repoUrl":23,"updatedAt":343},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[449,450,451,452],{"name":332,"slug":333,"type":15},{"name":335,"slug":336,"type":15},{"name":338,"slug":339,"type":15},{"name":341,"slug":342,"type":15},{"slug":345,"name":345,"fn":346,"description":347,"org":454,"tags":455,"stars":22,"repoUrl":23,"updatedAt":363},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[456,457,458,459,460],{"name":351,"slug":352,"type":15},{"name":335,"slug":336,"type":15},{"name":355,"slug":356,"type":15},{"name":358,"slug":359,"type":15},{"name":361,"slug":362,"type":15},{"slug":365,"name":365,"fn":366,"description":367,"org":462,"tags":463,"stars":22,"repoUrl":23,"updatedAt":378},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[464,465,466,467],{"name":20,"slug":21,"type":15},{"name":372,"slug":373,"type":15},{"name":17,"slug":18,"type":15},{"name":376,"slug":377,"type":15},{"slug":380,"name":380,"fn":381,"description":382,"org":469,"tags":470,"stars":22,"repoUrl":23,"updatedAt":395},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[471,472,473,474],{"name":17,"slug":18,"type":15},{"name":387,"slug":388,"type":15},{"name":390,"slug":391,"type":15},{"name":393,"slug":394,"type":15},{"slug":397,"name":397,"fn":398,"description":399,"org":476,"tags":477,"stars":22,"repoUrl":23,"updatedAt":411},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[478,479,480],{"name":403,"slug":404,"type":15},{"name":406,"slug":407,"type":15},{"name":409,"slug":410,"type":15},{"slug":413,"name":413,"fn":414,"description":415,"org":482,"tags":483,"stars":22,"repoUrl":23,"updatedAt":430},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[484,485,486,487],{"name":419,"slug":420,"type":15},{"name":422,"slug":423,"type":15},{"name":425,"slug":426,"type":15},{"name":428,"slug":429,"type":15},{"slug":373,"name":373,"fn":432,"description":433,"org":489,"tags":490,"stars":22,"repoUrl":23,"updatedAt":442},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[491,492,493,494],{"name":20,"slug":21,"type":15},{"name":438,"slug":439,"type":15},{"name":372,"slug":373,"type":15},{"name":355,"slug":356,"type":15},{"slug":496,"name":496,"fn":497,"description":498,"org":499,"tags":500,"stars":22,"repoUrl":23,"updatedAt":506},"cline-session-history","search and browse Cline session history","Search and browse Cline session history. Use when the user asks to find, list, inspect, or export Cline sessions by time period, prompt content, status, model, provider, source, mode, workspace, or other criteria. Also use when the user wants to read a session transcript or export sessions to a directory. Trigger phrases include \"find my session\", \"search my session history\", \"show me past sessions\", \"what was that session where\", \"find the session that started with\", and any mention of past Cline conversations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[501,502,505],{"name":419,"slug":420,"type":15},{"name":503,"slug":504,"type":15},"History","history",{"name":387,"slug":388,"type":15},"2026-07-19T06:03:13.945151",{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":22,"repoUrl":23,"updatedAt":524},"convex-design","build reactive backends with Convex","Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries\u002Fmutations\u002Factions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM\u002Fagent workflows on Convex's one-platform stack.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[513,514,517,518,521],{"name":351,"slug":352,"type":15},{"name":515,"slug":516,"type":15},"Backend","backend",{"name":355,"slug":356,"type":15},{"name":519,"slug":520,"type":15},"Real-time","real-time",{"name":522,"slug":523,"type":15},"Storage","storage","2026-07-12T08:13:37.101253",{"slug":526,"name":526,"fn":527,"description":528,"org":529,"tags":530,"stars":22,"repoUrl":23,"updatedAt":544},"cosmosdb-best-practices","optimize Azure Cosmos DB performance","Azure Cosmos DB performance optimization and best practices guidelines for NoSQL,\npartitioning, queries, SDK usage, and vector search. Use when writing, reviewing,\nor refactoring code that interacts with Azure Cosmos DB, designing data models,\noptimizing queries, or implementing high-performance database operations.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[531,534,537,538,541],{"name":532,"slug":533,"type":15},"Azure","azure",{"name":535,"slug":536,"type":15},"Cosmos DB","cosmos-db",{"name":355,"slug":356,"type":15},{"name":539,"slug":540,"type":15},"NoSQL","nosql",{"name":542,"slug":543,"type":15},"Performance","performance","2026-07-12T08:13:54.531719",{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":22,"repoUrl":23,"updatedAt":557},"data-analyst","analyze ClickHouse analytics data","Act as an interactive data analyst for ClickHouse-backed analytics. Use when the user asks questions about internal data, metrics, dashboards, telemetry, active users, revenue, funnels, trends, distributions, or wants an analyst-style conversation, ad hoc SQL, charts, or a data export against ClickHouse (local or ClickHouse Cloud).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[551,552,553,556],{"name":20,"slug":21,"type":15},{"name":372,"slug":373,"type":15},{"name":554,"slug":555,"type":15},"Dashboards","dashboards",{"name":17,"slug":18,"type":15},"2026-07-12T08:13:31.975246",{"slug":559,"name":559,"fn":560,"description":561,"org":562,"tags":563,"stars":22,"repoUrl":23,"updatedAt":570},"dataproc-skills","manage Dataproc clusters and jobs","Skills to interact with your Dataproc clusters and jobs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[564,567],{"name":565,"slug":566,"type":15},"Data Engineering","data-engineering",{"name":568,"slug":569,"type":15},"Operations","operations","2026-07-12T08:13:42.179275",45]