[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69A7MSG727DZRF44ND8GV30":3,"skill-same:01M69A7MSG727DZRF44ND8GV30":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M69A7MSG727DZRF44ND8GV30","pilotswarm-perf",null,"Run and analyze PilotSwarm performance workflows, starting with SDK sub-agent spawn perf. Use when collecting fresh perf baselines, comparing runs, generating stable perf reports, or updating perf memory and next steps.","microsoft\u002FPilotSwarm","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69A6RNK492A5JSNBTXANKX5",16,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpilotswarm-perf\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"pilotswarm perf","perf","use","agent spawn","when","sub-agent","next steps","with","fresh","next","reports","sdk","spawn","analyze","run","workflows","performance","memory","2026-11-10 10:12:30",false,"---\nname: pilotswarm-perf\ndescription: Run and analyze PilotSwarm performance workflows, starting with SDK sub-agent spawn perf. Use when collecting fresh perf baselines, comparing runs, generating stable perf reports, or updating perf memory and next steps.\n---\n\n# PilotSwarm Perf\n\nUse this skill when the user wants performance numbers or follow-up analysis for this repository.\n\nKeep the workflow deterministic. Fresh numbers should come from repo-owned runners, and conclusions should be written back into repo memory.\n\n## Canonical Files\n\n- Perf agent memory: `perf\u002Fmemory\u002Fperf-agent-memory.md`\n- Spawn perf runner: `scripts\u002Fperf\u002Frun-sdk-spawn-perf.mjs`\n- Spawn perf command: `npm run perf:spawn`\n- Raw spawn perf test: `packages\u002Fsdk\u002Ftest\u002Fperf\u002Fspawn.perf.test.js`\n- Perf Vitest config: `packages\u002Fsdk\u002Fvitest.perf.config.js`\n- Latest generated report: `perf\u002Freports\u002Fspawn\u002Flatest.md`\n- Latest generated metrics: `perf\u002Freports\u002Fspawn\u002Flatest.json`\n- Historical run index: `perf\u002Freports\u002Fspawn\u002Fhistory\u002Findex.json`\n\n## Workflow\n\n1. Read `perf\u002Fmemory\u002Fperf-agent-memory.md`.\n2. If the user wants fresh numbers, run `npm run perf:spawn` from repo root.\n3. Treat `npm run perf:spawn` as the source of truth: it must generate `latest.*`, append history, and update `perf\u002Fmemory\u002Fperf-agent-memory.md` automatically.\n4. Base the analysis on `perf\u002Freports\u002Fspawn\u002Flatest.json` and `perf\u002Freports\u002Fspawn\u002Flatest.md`, not on terminal snippets alone.\n5. Compare the latest run against the prior latest run if the generated report includes a comparison section.\n6. If you add deeper interpretation beyond the generated memory, refine `perf\u002Fmemory\u002Fperf-agent-memory.md` so the next run starts from the updated hypotheses and next steps.\n7. In the user-facing summary, include exact measurements, notable comparisons, and the next recommended experiment or optimization.\n\n## Rules\n\n- Prefer repo scripts over ad hoc shell pipelines.\n- Do not change perf assertions just to make results look better.\n- Treat `latest.*` files as generated outputs.\n- Keep memory concise and cumulative. Replace stale hypotheses with confirmed findings when possible.\n- If worktree changes may affect perf validity, call that out explicitly in both the response and the memory file.\n\n## Extending Perf Coverage\n\nIf you add another perf surface later, give it all of the following:\n\n- a dedicated perf test under `packages\u002F*\u002Ftest\u002Fperf\u002F`\n- a deterministic runner under `scripts\u002Fperf\u002F`\n- generated outputs under `perf\u002Freports\u002F\u003Csurface>\u002F`\n- a memory update in `perf\u002Fmemory\u002Fperf-agent-memory.md`\n","# PilotSwarm Perf\n\nUse this skill when the user wants performance numbers or follow-up analysis for this repository.\n\nKeep the workflow deterministic. Fresh numbers should come from repo-owned runners, and conclusions should be written back into repo memory.\n\n## Canonical Files\n\n- Perf agent memory: `perf\u002Fmemory\u002Fperf-agent-memory.md`\n- Spawn perf runner: `scripts\u002Fperf\u002Frun-sdk-spawn-perf.mjs`\n- Spawn perf command: `npm run perf:spawn`\n- Raw spawn perf test: `packages\u002Fsdk\u002Ftest\u002Fperf\u002Fspawn.perf.test.js`\n- Perf Vitest config: `packages\u002Fsdk\u002Fvitest.perf.config.js`\n- Latest generated report: `perf\u002Freports\u002Fspawn\u002Flatest.md`\n- Latest generated metrics: `perf\u002Freports\u002Fspawn\u002Flatest.json`\n- Historical run index: `perf\u002Freports\u002Fspawn\u002Fhistory\u002Findex.json`\n\n## Workflow\n\n1. Read `perf\u002Fmemory\u002Fperf-agent-memory.md`.\n2. If the user wants fresh numbers, run `npm run perf:spawn` from repo root.\n3. Treat `npm run perf:spawn` as the source of truth: it must generate `latest.*`, append history, and update `perf\u002Fmemory\u002Fperf-agent-memory.md` automatically.\n4. Base the analysis on `perf\u002Freports\u002Fspawn\u002Flatest.json` and `perf\u002Freports\u002Fspawn\u002Flatest.md`, not on terminal snippets alone.\n5. Compare the latest run against the prior latest run if the generated report includes a comparison section.\n6. If you add deeper interpretation beyond the generated memory, refine `perf\u002Fmemory\u002Fperf-agent-memory.md` so the next run starts from the updated hypotheses and next steps.\n7. In the user-facing summary, include exact measurements, notable comparisons, and the next recommended experiment or optimization.\n\n## Rules\n\n- Prefer repo scripts over ad hoc shell pipelines.\n- Do not change perf assertions just to make results look better.\n- Treat `latest.*` files as generated outputs.\n- Keep memory concise and cumulative. Replace stale hypotheses with confirmed findings when possible.\n- If worktree changes may affect perf validity, call that out explicitly in both the response and the memory file.\n\n## Extending Perf Coverage\n\nIf you add another perf surface later, give it all of the following:\n\n- a dedicated perf test under `packages\u002F*\u002Ftest\u002Fperf\u002F`\n- a deterministic runner under `scripts\u002Fperf\u002F`\n- generated outputs under `perf\u002Freports\u002F\u003Csurface>\u002F`\n- a memory update in `perf\u002Fmemory\u002Fperf-agent-memory.md`\n",{"name":5,"description":7},"main","cecafe1ca7a9f2778a6166abdd12f6165d99f777",".github\u002Fskills\u002Fpilotswarm-perf",10,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-13 16:15:33",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add microsoft\u002FPilotSwarm --skill pilotswarm-perf",{"tool":57,"command":58},"bunx","bunx skills add microsoft\u002FPilotSwarm --skill pilotswarm-perf",{"tool":60,"command":61},"pnpm","pnpm dlx skills add microsoft\u002FPilotSwarm --skill pilotswarm-perf","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpilotswarm-perf\u002FSKILL.md",true,[],[66,88,109,124,151,174],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":37},"01M69A9CY8CXHED3AFC8DAT9G0","pilotswarm-three-tier","Reference for adding a Tier 3 worker AKS cluster to a PilotSwarm deployment. Covers provisioning, identity, Dockerfile changes, entrypoint, manifests, and verification.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-three-tier\u002FSKILL.md",[],[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87],"pilotswarm three tier","three","entrypoint","manifests","for","changes","aks","verification","deployment","reference","dockerfile","identity","provisioning","worker","cluster",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":37},"01M69A9B6R5H88HJFEYC0P4R57","pilotswarm-sdk-builder","Use when creating or updating an SDK-first app on top of PilotSwarm. Covers the client\u002Fworker split, plugin layering, tool registration, tests, and the DevOps sample structure.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-sdk-builder\u002FSKILL.md",[],[30,95,96,97,98,99,21,100,23,101,102,103,104,86,105,106,107,108],"pilotswarm sdk builder","builder","tool","first","plugin","client","top","split","app","tests","sample","structure","registration","devops",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":37},"01M69A99A43M97VTYZBCN1JQ1H","pilotswarm-portal-builder","Use when creating or updating a browser portal on top of PilotSwarm. Covers portal branding, plugin.json.portal, named-agent exposure, auth add-ons, and remote deployment wiring.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-portal-builder\u002FSKILL.md",[],[116,96,117,23,118,101,119,120,21,121,122,81,99,123],"pilotswarm portal builder","remote","wiring","branding","add","json","browser","auth",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":135,"publishedAt":37},"01M69A97JZY10V1VE12NF4JR5A","pilotswarm-knowledge-harvester","Use when an SDK or CLI app needs to ingest external sources into durable, searchable knowledge and an open knowledge graph. Covers enabling the EnhancedFactStore + GraphStore providers, authoring a crawler:true agent, the crawl→graph→reader flow, ACL\u002FscopeKey evidence, and tests.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-knowledge-harvester\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[136,137,21,23,138,139,140,141,103,142,104,143,144,145,146,147,148,149,30,150],"knowledge","pilotswarm knowledge harvester","cli app","true","crawler","sources","authoring","crawl","ingest","evidence","reader","open","flow","knowledge graph","cli",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":37},"01M69A95Y3EWHSZ1TDFMXWAKX3","pilotswarm-hybrid-datastore","Use when a PilotSwarm app needs stock PostgreSQL for runtime storage plus HorizonDB for enhanced facts, semantic\u002Flexical search, and the knowledge graph. Covers env topology, horizonConfigFromEnv wiring, harvester agents, Azure secret\u002Fresource guidance, and the rule that Docker defaults remain stock Postgres.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-hybrid-datastore\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":133,"taxonomyTypeDesc":134},"01JBSEEDCAT000000000000011","运维与部署",[161,162,163,103,164,165,166,167,21,136,149,168,169,170,171,172,23,118,77,173],"hybrid","pilotswarm hybrid datastore","storage","runtime","stock","postgres","guidance","search","postgresql","azure","env","docker","facts",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":37},"01M69A94F4WR5CXDZ73N658DV0","pilotswarm-duroxide-versioning","Use when changing PilotSwarm durable orchestration behavior, continue-as-new state, or replay-sensitive control flow.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FPilotSwarm\u002Fblob\u002Fmain\u002Ftemplates\u002Fbuilder-agents\u002Fskills\u002Fpilotswarm-duroxide-versioning\u002FSKILL.md",[],[181,182,183,184,23,185,186,187,21,188,189,148,190],"pilotswarm duroxide versioning","versioning","orchestration","new","as","control","replay","behavior","continue","state"]