[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71SBXY8K4DRC54QVE4P9VMS":3,"skill-same:01M71SBXY8K4DRC54QVE4P9VMS":91},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":72},"01M71SBXY8K4DRC54QVE4P9VMS","runtime-diagnostics",null,"Investigate Pioneer Gateway or desktop CPU, memory, slow work, queues, and runtime stalls using process metrics, local snapshots, bounded native profiles, and exact release symbols. Use for Pioneer performance diagnosis and interpreting its diagnostic artifacts.","pioneerdotai\u002Fpioneer","pioneerdotai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F267592302?v=4","01M71SB358NQ2T40CJFEXCAZKV","01M71SB35YBM3GPT0PWWSPMPF7",21,"MIT","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\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],"runtime","runtime diagnostics","diagnostics","true","profiles","for","gateway","metrics","bounded","queues","release","diagnosis","CPU","native","work","snapshots","false","local","performance","memory","2026-11-10 13:02:02",false,"---\nname: runtime-diagnostics\nslug: runtime-diagnostics\nowner: pioneer\ndescription: \"Investigate Pioneer Gateway or desktop CPU, memory, slow work, queues, and runtime stalls using process metrics, local snapshots, bounded native profiles, and exact release symbols. Use for Pioneer performance diagnosis and interpreting its diagnostic artifacts.\"\nversion: \"0.1.0\"\nuser-invocable: true\ndisable-model-invocation: false\nimplicit-invocation: user-controlled\n---\n\n# Pioneer Runtime Diagnostics\n\nFind which process consumes resources, what work initiated it, where it waits,\nand which functions run during the problem. Use the existing `pioneer diagnostics`\ncommands and telemetry before proposing new instrumentation or changing code.\n\n## Protect the session that is doing the investigation\n\nThe investigating agent may run inside the Gateway, desktop, or a child of the\nprocess it is investigating. Treat that dependency as present unless verified\notherwise. **Never stop, restart, replace, upgrade, or relaunch those processes\nfrom the agent's tools.** Do not run `pioneer stop`, `pioneer start`,\n`gateway-service`, `launch-memory`, service-manager mutations, quit commands, or\nsignals against them. Do not stop their containers, remote hosts, or supervisors.\nA detached shell, background task, or subagent does not make a restart safe.\n\nSnapshot, bundle, symbol download\u002Fvalidation, and a bounded native attach capture\ncan usually run autonomously under an authorized diagnostic request. Preserve the\nuser's telemetry preference and OS attach permissions. If a restart is required,\nprepare the complete user handoff in [references\u002Frestart-memory.md](references\u002Frestart-memory.md):\nexact paths and commands, what to reproduce, when to stop, how to restore ordinary\nlaunch, and how to continue this investigation. The **user** executes that handoff\nfrom a terminal outside Pioneer. Do not execute its restart blocks yourself.\n\n## Four capabilities\n\n1. **Process resources and identity:** one run\u002Fbuild identity; CPU and OS memory\u002FIO\n   snapshots for the target and registered children, with freshness and coverage.\n2. **Native CPU and memory captures:** bounded on-demand profiles, manifests,\n   private artifacts, and exact Mach-O UUID \u002F ELF build ID \u002F PE GUID+age symbols.\n3. **Work ownership:** parent\u002Flinked work, trigger, attempt, executor and available\n   trace\u002Fspan context carried across instrumented execution boundaries.\n4. **Live diagnosis:** active work and waits, queue accounting, database pool\n   state, runtime\u002Fforeground responsiveness, export health and bounded prehistory.\n\nThese are complementary signals. A long span is not measured CPU. An allocation\nstack is not an ownership\u002Fretainer graph. A successful export is not proof that\nthe backend retained every event.\n\n## Normal autonomous workflow\n\n1. Discover the actual installed CLI, OS\u002Farchitecture, runtime home, live runs,\n   process ownership and available tools. Read [references\u002Fsignals-and-triage.md](references\u002Fsignals-and-triage.md).\n   The skill may be available before a binary supporting diagnostics is installed;\n   report that mismatch instead of installing or restarting the hosting app.\n2. Save an initial snapshot, a later snapshot after a few normal sample periods,\n   and a bundle for the exact run. Keep capture output in a private case directory.\n   Prefer exact run IDs over `gateway`\u002F`desktop` when several instances exist.\n3. Separate target CPU\u002Fmemory from registered children and profiler cost. Check\n   freshness, consent generation, unknown fields, queue\u002Fliveness evidence and\n   instrumentation loss before naming a cause.\n4. If function-level evidence is needed, read [references\u002Fcaptures.md](references\u002Fcaptures.md)\n   and take the smallest relevant supported capture. Use attach first. Prepare\n   user instructions for macOS allocation history only when attach cannot answer\n   the question; read the restart reference before planning it.\n5. Read [references\u002Fsymbols.md](references\u002Fsymbols.md) to download the matching private\n   `Build Debug Symbols` artifact for the exact producing release, validate it\n   against the capture and executable, and resolve addresses. Prefer existing\n   artifacts; local LLVM builds and release rebuilds are not a normal diagnostic step.\n6. Follow the evidence to the initiating work and concrete functions. Give a\n   short verdict, evidence paths\u002Ftime window, missing coverage and a scoped next\n   action. A single failed native capture is not proof that ordinary telemetry\n   failed. Finish when the requested question is answered; do not launch a broad\n   benchmark or repeated capture campaign without a reason.\n\n## Operating bounds\n\n- Keep at least **5 GiB free** on every volume holding inputs, symbols, profiles,\n  or temporary logs. Check before downloads and capture and during large work;\n  leave headroom for growth between checks. The product's artifact quotas are\n  not a whole-disk free-space guard. Stop diagnostic work before crossing the floor.\n- Native profilers can consume several GiB of RAM and substantial CPU\u002FIO. Report\n  their cost separately from the target. Do not promise free or zero-overhead diagnosis.\n- Run one capture per target at a time. Use `diagnostics cancel --target RUN_ID`\n  to stop the native capture worker, never kill the Gateway\u002Fdesktop to cancel it.\n- Preserve private endpoint tokens, paths, native output and symbol artifacts.\n  Do not print endpoint descriptor JSON or upload raw bundles to public services.\n  A request to investigate does not authorize publishing diagnostic data.\n- Cleanup only case-owned files after identifying the exact path, size, ownership,\n  active readers\u002Fwriters and evidence that must remain. Never remove a shared\n  Cargo target, running preparation logs, retained release inputs, or unrelated\n  files merely to make room.\n- Use only callable tools and installed commands. Skill references are accessed\n  through the same package\u002Fauthority as this file, or relative to its filesystem\n  directory when exported locally. Do not treat a `skill:\u002F\u002F` identifier as a path.\n","# Pioneer Runtime Diagnostics\n\nFind which process consumes resources, what work initiated it, where it waits,\nand which functions run during the problem. Use the existing `pioneer diagnostics`\ncommands and telemetry before proposing new instrumentation or changing code.\n\n## Protect the session that is doing the investigation\n\nThe investigating agent may run inside the Gateway, desktop, or a child of the\nprocess it is investigating. Treat that dependency as present unless verified\notherwise. **Never stop, restart, replace, upgrade, or relaunch those processes\nfrom the agent's tools.** Do not run `pioneer stop`, `pioneer start`,\n`gateway-service`, `launch-memory`, service-manager mutations, quit commands, or\nsignals against them. Do not stop their containers, remote hosts, or supervisors.\nA detached shell, background task, or subagent does not make a restart safe.\n\nSnapshot, bundle, symbol download\u002Fvalidation, and a bounded native attach capture\ncan usually run autonomously under an authorized diagnostic request. Preserve the\nuser's telemetry preference and OS attach permissions. If a restart is required,\nprepare the complete user handoff in [references\u002Frestart-memory.md](references\u002Frestart-memory.md):\nexact paths and commands, what to reproduce, when to stop, how to restore ordinary\nlaunch, and how to continue this investigation. The **user** executes that handoff\nfrom a terminal outside Pioneer. Do not execute its restart blocks yourself.\n\n## Four capabilities\n\n1. **Process resources and identity:** one run\u002Fbuild identity; CPU and OS memory\u002FIO\n   snapshots for the target and registered children, with freshness and coverage.\n2. **Native CPU and memory captures:** bounded on-demand profiles, manifests,\n   private artifacts, and exact Mach-O UUID \u002F ELF build ID \u002F PE GUID+age symbols.\n3. **Work ownership:** parent\u002Flinked work, trigger, attempt, executor and available\n   trace\u002Fspan context carried across instrumented execution boundaries.\n4. **Live diagnosis:** active work and waits, queue accounting, database pool\n   state, runtime\u002Fforeground responsiveness, export health and bounded prehistory.\n\nThese are complementary signals. A long span is not measured CPU. An allocation\nstack is not an ownership\u002Fretainer graph. A successful export is not proof that\nthe backend retained every event.\n\n## Normal autonomous workflow\n\n1. Discover the actual installed CLI, OS\u002Farchitecture, runtime home, live runs,\n   process ownership and available tools. Read [references\u002Fsignals-and-triage.md](references\u002Fsignals-and-triage.md).\n   The skill may be available before a binary supporting diagnostics is installed;\n   report that mismatch instead of installing or restarting the hosting app.\n2. Save an initial snapshot, a later snapshot after a few normal sample periods,\n   and a bundle for the exact run. Keep capture output in a private case directory.\n   Prefer exact run IDs over `gateway`\u002F`desktop` when several instances exist.\n3. Separate target CPU\u002Fmemory from registered children and profiler cost. Check\n   freshness, consent generation, unknown fields, queue\u002Fliveness evidence and\n   instrumentation loss before naming a cause.\n4. If function-level evidence is needed, read [references\u002Fcaptures.md](references\u002Fcaptures.md)\n   and take the smallest relevant supported capture. Use attach first. Prepare\n   user instructions for macOS allocation history only when attach cannot answer\n   the question; read the restart reference before planning it.\n5. Read [references\u002Fsymbols.md](references\u002Fsymbols.md) to download the matching private\n   `Build Debug Symbols` artifact for the exact producing release, validate it\n   against the capture and executable, and resolve addresses. Prefer existing\n   artifacts; local LLVM builds and release rebuilds are not a normal diagnostic step.\n6. Follow the evidence to the initiating work and concrete functions. Give a\n   short verdict, evidence paths\u002Ftime window, missing coverage and a scoped next\n   action. A single failed native capture is not proof that ordinary telemetry\n   failed. Finish when the requested question is answered; do not launch a broad\n   benchmark or repeated capture campaign without a reason.\n\n## Operating bounds\n\n- Keep at least **5 GiB free** on every volume holding inputs, symbols, profiles,\n  or temporary logs. Check before downloads and capture and during large work;\n  leave headroom for growth between checks. The product's artifact quotas are\n  not a whole-disk free-space guard. Stop diagnostic work before crossing the floor.\n- Native profilers can consume several GiB of RAM and substantial CPU\u002FIO. Report\n  their cost separately from the target. Do not promise free or zero-overhead diagnosis.\n- Run one capture per target at a time. Use `diagnostics cancel --target RUN_ID`\n  to stop the native capture worker, never kill the Gateway\u002Fdesktop to cancel it.\n- Preserve private endpoint tokens, paths, native output and symbol artifacts.\n  Do not print endpoint descriptor JSON or upload raw bundles to public services.\n  A request to investigate does not authorize publishing diagnostic data.\n- Cleanup only case-owned files after identifying the exact path, size, ownership,\n  active readers\u002Fwriters and evidence that must remain. Never remove a shared\n  Cargo target, running preparation logs, retained release inputs, or unrelated\n  files merely to make room.\n- Use only callable tools and installed commands. Skill references are accessed\n  through the same package\u002Fauthority as this file, or relative to its filesystem\n  directory when exported locally. Do not treat a `skill:\u002F\u002F` identifier as a path.\n",{"name":5,"slug":5,"owner":48,"version":49,"description":7,"user-invocable":50,"implicit-invocation":51,"disable-model-invocation":44},"pioneer","0.1.0",true,"user-controlled","main","16f100cf66fa2614fbb4112d4b27cf8d792012e0","resources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics",3,"https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer","https:\u002F\u002Fgetpioneer.dev","https:\u002F\u002Fgithub.com\u002Fpioneerdotai","2026-11-12 03:48:45",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":50},[62,65,68],{"tool":63,"command":64},"npx","npx skills add pioneerdotai\u002Fpioneer --skill runtime-diagnostics",{"tool":66,"command":67},"bunx","bunx skills add pioneerdotai\u002Fpioneer --skill runtime-diagnostics",{"tool":69,"command":70},"pnpm","pnpm dlx skills add pioneerdotai\u002Fpioneer --skill runtime-diagnostics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\u002FSKILL.md",[73,79,83,87],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fcaptures.md","REFERENCE","参考文档",15028,"https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\u002Freferences\u002Fcaptures.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Frestart-memory.md",13033,"https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\u002Freferences\u002Frestart-memory.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fsignals-and-triage.md",15053,"https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\u002Freferences\u002Fsignals-and-triage.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fsymbols.md",12806,"https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fruntime-diagnostics\u002Freferences\u002Fsymbols.md",[92,115,136,156,178,201],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":99,"publishedAt":43},"01M71SC6J236HF21HBM63EBPYJ","threads","Use this skill to find and read accessible conversations, follow saved sources and child threads, read saved tool results, create a conversation, send a message, or start a permitted thread turn.","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fthreads\u002FSKILL.md",[98],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[94,100,101,102,103,39,104,105,106,107,108,109,26,110,111,112,113,114],"conversation","sources","conversations","send","create","child","message","read","start","tool","use","thread","saved","results","find",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":43},"01M71SC3B8PGF9J54B4N1R1NR5","tasks","Use this skill when Pioneer should create, inspect, update, reschedule, pause, resume, finish, cancel, troubleshoot, or configure delivery for durable tasks, scheduled tasks, recurring tasks, interval tasks, cron jobs, background work, or existing task state.","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Ftasks\u002FSKILL.md",[121],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[117,123,124,39,125,126,104,37,127,128,129,130,131,132,133,134,28,26,110,135],"inspect","scheduled","when","configure","delivery","update","troubleshoot","finish","cron","cron jobs","recurring","pause","Existing",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":43},"01M71SC0H4QYYZD9THQZ5VAB02","subagents","Use this skill when Pioneer should delegate current-turn work to attached task-backed subagents, coordinate parallel child agents, wait for child results, review\u002Frevise\u002Faccept\u002Fcancel\u002Fdetach attached work, or synthesize accepted child results into the parent answer.","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fsubagents\u002FSKILL.md",[142],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[138,144,145,146,39,125,147,148,37,105,149,150,151,28,152,26,110,153,154,155],"coordinate","wait for","delegate","synthesize","review","wait","revise","parallel","answer","accept","cancel","task",{"skillNo":157,"name":42,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":43},"01M71SBV7Q5A9QZCHKK66W7R9J","Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user\u002Fproject facts, request memory tools, search\u002Flist\u002Fget stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or recover from memory tool failures.","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fmemory\u002FSKILL.md",[161],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[42,163,164,165,166,167,168,169,170,39,125,171,172,173,174,175,176,177,152,109],"get","project","decide","search","up","clean","improve","memory tools","audit","request","list","Tools","context","save","memories",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":182,"sourceHtmlUrl":183,"categories":184,"keywords":189,"publishedAt":43},"01M71SBRZTY2Q7QDYG1SNBHJDV","html","Create inline HTML documents with CSS and embedded JavaScript in Pioneer messages, including interactive calculators, charts, and small working interfaces. Do not use for ordinary application edits merely involving HTML.","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fhtml\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fhtml\u002FSKILL.md",[185,188],{"categoryNo":186,"categoryName":187,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[180,190,191,192,39,193,104,194,195,28,26,110,196,197,198,199,200],"css","Charts","messages","documents","inline","do","interactive","javascript","with","embedded","application",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":205,"licenseFileUrl":206,"sourceHtmlUrl":207,"categories":208,"keywords":210,"publishedAt":43},"01M71SBNVQPVE7XH2Q50VPJQ3S","browser","Use agent-browser to interact with websites, inspect rendered pages, fill forms, extract data, capture screenshots or PDFs, and test web interfaces. Includes browser-backed QA and CDP-enabled Electron app workflows.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fbrowser\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fpioneerdotai\u002Fpioneer\u002Fblob\u002Fmain\u002Fresources\u002Fskills\u002Fpioneer\u002Fbrowser\u002FSKILL.md",[209],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[203,211,212,213,123,214,39,215,216,217,218,219,220,221,222,223,26,224,110,225],"app","cdp","agent-browser","qa","workflows","references","cli","test web","forms","data","screenshots","target","pdfs","pages","electron"]