[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698R7P1TPYJ9J3V44WR9HXZ":3,"skill-same:01M698R7P1TPYJ9J3V44WR9HXZ":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M698R7P1TPYJ9J3V44WR9HXZ","convex-insights",null,"Query a running Convex app's logs + health in natural language (official MCP): failures, slow\u002Fexpensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.","openclaw\u002Fclawhub","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698PDMKEC6E49395505BD05",9555,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-insights\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"convex insights","convex","insights","running","MCP","scoped","with","link","app","deep","query","natural language","language","functions","evidence","health","logs","official","deploy","dashboard","2026-11-10 10:12:30",false,"---\nname: convex-insights\ndescription: \"Query a running Convex app's logs + health in natural language (official MCP): failures, slow\u002Fexpensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.\"\n---\n\n\u003C!-- GENERATED from convex-agents content\u002Fcapabilities\u002Fconvex-insights.json — do not edit by hand. -->\n\n# Query logs + health in natural language\n\nThe deployment already records what happened; the agent just has to ask well. This capability is a disciplined wrapper over the official Convex MCP's read tools (`logs`, `insights`, `functionSpec`, `status`) that turns operational questions into narrow, evidence-returning queries and hands back answers a human can one-click verify in the dashboard. The discipline is copied from the observability MCP surface that works best in the wild: discover fields before querying, three views not fifteen tools, token-frugal output, and a dashboard deep link on every answer.\n\n## Workflow\n\n1. GUARD: deploy-guard step 0-1 — identify + announce which deployment is being read. Reading logs\u002Finsights is read-only; never enable prod mutation flags for an insights pass.\n2. DISCOVER before you query — never guess identifiers. Use `functionSpec` to list the real function names and `status` for the deployment\u002Fversion. Note the tool limits up front: `logs` takes only `--history \u003Cn>` (a COUNT, not a time window), `--success`, `--jsonl`, `--prod`, `--deployment` — there is NO server-side status\u002Ffunction\u002FrequestId\u002Ftime filter; `insights` has no function filter and is cloud dev\u002Fprod + user-auth only. So you fetch a recent window and filter CLIENT-SIDE.\n3. PICK ONE OF THREE VIEWS and fetch the raw window, then filter locally:\n   - failures view → `logs --history \u003Cn> --jsonl`, then locally keep failures + group by function + error message, returning counts + the first stack per group. Answers 'what's erroring', 'what failed after deploy'.\n   - health view → `insights` (cloud only): the typed 72h read-limit \u002F OCC events. Surface + rank them, but hand perf\u002Fcost ROOT-CAUSING and fixes to convex-advisor — emit those as pointer findings, do not own the perf-fix framing here.\n   - trace view → `logs --history \u003Cn> --jsonl` then locally filter to one requestId\u002Ffunction to read the full execution. Answers 'why did THIS call fail'.\n4. SCOPE by fetching a bounded recent window (a sensible `--history` count) and filtering client-side to the function\u002Fstatus\u002FrequestId asked about; when the window is large, aggregate (counts by function\u002Fmessage) rather than dumping lines.\n5. ANSWER with (a) the one-line finding, (b) the evidence (counts + one representative stack\u002Flog line), and (c) WHEN POSSIBLE an agent-constructed dashboard deep link (dashboard.convex.dev, the deployment's Logs\u002FFunctions view) for human verification — no tool returns the link, so build it from the deployment name + function; never a raw log dump as the answer.\n6. CROSS-CHECK deploy causality when asked 'did my deploy break this': compare the failure onset (from the log timestamps) against the deployment version from `status`; correlate, don't assert.\n7. HAND OFF, don't fix here: a perf\u002Fcost cause → convex-advisor (which owns those fixes); a code defect → convex-reviewer\u002Fconvex-authz; a live error to react to going forward → monitor\u002Fsentinel. Emit findings on the bus (specs\u002Ffinding.schema.json) — primarily `observability`, with perf\u002Fcost as pointer findings to advisor — so a composite pass can pick them up.\n\n## Rules\n\n- Discover real function\u002Ffield names (functionSpec\u002Fstatus) before filtering — never guess identifiers, never return a confusing empty result for a name the app doesn't have.\n- `logs` and `insights` have NO server-side status\u002Ffunction\u002FrequestId\u002Ftime-window filter (logs takes only a --history COUNT; insights is cloud-only) — fetch a bounded recent window and filter CLIENT-SIDE; say so rather than implying params that don't exist.\n- One of three views per question (failures \u002F health \u002F trace) — don't fan out into many speculative tool calls.\n- No tool returns a dashboard link — construct it from the deployment name + function when possible for human verification; never answer with a raw log dump.\n- Read-only always: an insights pass runs no mutation and never enables prod mutation flags (deploy-guard discipline).\n- Stay a reader and defer perf\u002Fcost fixes to convex-advisor: emit primarily `observability`, route perf\u002Fcost as POINTER findings so advisor uniquely owns the perf-fix framing; forward-looking reaction goes to monitor\u002Fsentinel.\n","\u003C!-- GENERATED from convex-agents content\u002Fcapabilities\u002Fconvex-insights.json — do not edit by hand. -->\n\n# Query logs + health in natural language\n\nThe deployment already records what happened; the agent just has to ask well. This capability is a disciplined wrapper over the official Convex MCP's read tools (`logs`, `insights`, `functionSpec`, `status`) that turns operational questions into narrow, evidence-returning queries and hands back answers a human can one-click verify in the dashboard. The discipline is copied from the observability MCP surface that works best in the wild: discover fields before querying, three views not fifteen tools, token-frugal output, and a dashboard deep link on every answer.\n\n## Workflow\n\n1. GUARD: deploy-guard step 0-1 — identify + announce which deployment is being read. Reading logs\u002Finsights is read-only; never enable prod mutation flags for an insights pass.\n2. DISCOVER before you query — never guess identifiers. Use `functionSpec` to list the real function names and `status` for the deployment\u002Fversion. Note the tool limits up front: `logs` takes only `--history \u003Cn>` (a COUNT, not a time window), `--success`, `--jsonl`, `--prod`, `--deployment` — there is NO server-side status\u002Ffunction\u002FrequestId\u002Ftime filter; `insights` has no function filter and is cloud dev\u002Fprod + user-auth only. So you fetch a recent window and filter CLIENT-SIDE.\n3. PICK ONE OF THREE VIEWS and fetch the raw window, then filter locally:\n   - failures view → `logs --history \u003Cn> --jsonl`, then locally keep failures + group by function + error message, returning counts + the first stack per group. Answers 'what's erroring', 'what failed after deploy'.\n   - health view → `insights` (cloud only): the typed 72h read-limit \u002F OCC events. Surface + rank them, but hand perf\u002Fcost ROOT-CAUSING and fixes to convex-advisor — emit those as pointer findings, do not own the perf-fix framing here.\n   - trace view → `logs --history \u003Cn> --jsonl` then locally filter to one requestId\u002Ffunction to read the full execution. Answers 'why did THIS call fail'.\n4. SCOPE by fetching a bounded recent window (a sensible `--history` count) and filtering client-side to the function\u002Fstatus\u002FrequestId asked about; when the window is large, aggregate (counts by function\u002Fmessage) rather than dumping lines.\n5. ANSWER with (a) the one-line finding, (b) the evidence (counts + one representative stack\u002Flog line), and (c) WHEN POSSIBLE an agent-constructed dashboard deep link (dashboard.convex.dev, the deployment's Logs\u002FFunctions view) for human verification — no tool returns the link, so build it from the deployment name + function; never a raw log dump as the answer.\n6. CROSS-CHECK deploy causality when asked 'did my deploy break this': compare the failure onset (from the log timestamps) against the deployment version from `status`; correlate, don't assert.\n7. HAND OFF, don't fix here: a perf\u002Fcost cause → convex-advisor (which owns those fixes); a code defect → convex-reviewer\u002Fconvex-authz; a live error to react to going forward → monitor\u002Fsentinel. Emit findings on the bus (specs\u002Ffinding.schema.json) — primarily `observability`, with perf\u002Fcost as pointer findings to advisor — so a composite pass can pick them up.\n\n## Rules\n\n- Discover real function\u002Ffield names (functionSpec\u002Fstatus) before filtering — never guess identifiers, never return a confusing empty result for a name the app doesn't have.\n- `logs` and `insights` have NO server-side status\u002Ffunction\u002FrequestId\u002Ftime-window filter (logs takes only a --history COUNT; insights is cloud-only) — fetch a bounded recent window and filter CLIENT-SIDE; say so rather than implying params that don't exist.\n- One of three views per question (failures \u002F health \u002F trace) — don't fan out into many speculative tool calls.\n- No tool returns a dashboard link — construct it from the deployment name + function when possible for human verification; never answer with a raw log dump.\n- Read-only always: an insights pass runs no mutation and never enables prod mutation flags (deploy-guard discipline).\n- Stay a reader and defer perf\u002Fcost fixes to convex-advisor: emit primarily `observability`, route perf\u002Fcost as POINTER findings so advisor uniquely owns the perf-fix framing; forward-looking reaction goes to monitor\u002Fsentinel.\n",{"name":5,"description":7},"main","fd6beef619775fe02dd2548b0658bf88b46d7740",".agents\u002Fskills\u002Fconvex-insights",1492,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub","https:\u002F\u002Fclawhub.ai","https:\u002F\u002Fgithub.com\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","Your personal, open source AI assistant.","2026-11-15 03:03:27",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add openclaw\u002Fclawhub --skill convex-insights",{"tool":64,"command":65},"bunx","bunx skills add openclaw\u002Fclawhub --skill convex-insights",{"tool":67,"command":68},"pnpm","pnpm dlx skills add openclaw\u002Fclawhub --skill convex-insights","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-insights\u002FSKILL.md",true,[],[73,81,88,108,134,149],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M7415W7GWE5XEH7ETJ1YWCF2","notes","Turn user-provided notes into a concise agenda.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002Fscripts\u002Fsecurity\u002Ffixtures\u002Ftemplate-qualification\u002Fskills\u002Fnotes\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":80},"01M7415V57FG63ZGV9W35MV3TH","hosted-research","Read approved reference material for the hosted proof.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002Ffixtures\u002Ftemplates\u002Fhosted-e2e\u002Fpackage\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":43},"01M698QE868QCJ1HN5H03NAKCZ","convex-advisor","Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf\u002Fcost findings with fixes.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-advisor\u002FSKILL.md",[],[95,96,24,29,97,98,37,99,100,101,102,103,104,25,105,106,107],"convex advisor","advisor","cost","perf","limits","fixes","event","deployment","read","report","code","root","root-cause",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":115,"publishedAt":43},"01M698QD01M039DZ8WCRE8J6WY","convex-add","Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs \u002Fadd, or asks to add hosting\u002Fpublishing or any backend capability to an existing Convex app.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-add\u002FSKILL.md",[114],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[116,24,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,31,132,133],"add","convex add","publishing","user","when","Existing","dev","auth","hosting","catalog","trigger","search","for","back","capability","backend","billing","component",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":43},"01M698QBS5JVY310XM3RGFZCK4","convex-acquire-domain","Find and buy a domain for the current Convex app through Convex, then bind it (labs; spend action).","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-acquire-domain\u002FSKILL.md",[],[24,141,142,143,144,31,128,145,146,147,148],"domain","acquire","convex acquire domain","bind","find","buy","action","it",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":43},"01M698Q9P74GJAVDMCP33QBBWX","controlling-costs","Analyzes Axiom query patterns to find unused data, then builds dashboards and monitors for cost optimization. Use when asked to reduce Axiom costs, find unused columns or field values, identify data waste, or track ingest spend.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcontrolling-costs\u002FSKILL.md",[],[156,157,128,158,159,160,161,162,120,163,33,97,164,165,166,145,167,168,169],"controlling costs","data","Optimization","cost optimization","ingest","unused","use","reduce","track","values","axiom","columns","patterns","dashboards"]