[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GVSWNHWYDS8A2V5NTHGPS9":3,"skill-same:01M6GVSWNHWYDS8A2V5NTHGPS9":71},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":64},"01M6GVSWNHWYDS8A2V5NTHGPS9","skill-publish",null,"Publish a skill after validation and approvals; updates the catalog and logs the publish event.","Flow-Research\u002Fharnessy","Flow-Research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204254796?v=4","01M6GVJZH9ZV0XGZTVBJRNW5BQ","Flow Research","01M6GVJZNSWAHPXW43628F7X76",30,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fskill-publish\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36],"publish","skill publish","validation","logs","grep","read","write","catalog","name","approvals","event","true","updates","2026-11-10 10:12:30",false,"---\nname: skill-publish\ndescription: Publish a skill after validation and approvals; updates the catalog and logs the publish event.\ndisable-model-invocation: true\nallowed-tools: Read, Grep, Glob, ApplyPatch, Write\nargument-hint: \"[skill-name]\"\n---\n\n# Skill Publish — Controlled Release\n\n## Purpose\nPublish a validated skill with proper approvals, then update catalog metadata and log the publish event.\n\n## Inputs\n- Skill name\n- Evidence of test gates\n- Explicit approver (required for high blast radius)\n\n- Template paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fskill-publish\u002F`.\n\n## Steps\n1. **Run `\u002Fskill-validate \u003Cskill-name>`** and confirm PASS.\n2. **Enforce approval gate**\n   - If `blast_radius: high`, require explicit approval from an authorized maintainer. If missing, STOP.\n3. **Update catalog entry**\n   - Increment version if needed\n   - Update `updated` date\n4. **Write publish log** to `.jarvis\u002Fcontext\u002Fskills\u002Fpublish-log.md` with:\n   - Skill name, version, owner, blast radius\n   - Approver (if required)\n   - Date and summary\n5. **Return confirmation**\n\n## Decision Trace Protocol\n\nThis skill participates in the skill evolution system by capturing decision traces at gate resolutions and consulting accumulated feedback.\n\n### Trace Consultation (short loop)\n\nBefore executing any step with a quality or human gate, query accumulated decision traces:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_query.py\" recent \\\n    --skill \"skill-publish\" --gate \"\u003Cgate_name>\" --limit 5 --min-loops 1\n```\n\nIf patterns or recent feedback exist, incorporate them as additional constraints. Do not cite traces to the user unless asked.\n\n### Trace Capture (after gate resolution)\n\nAfter every gate resolves, capture a decision trace:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_capture.py\" capture \\\n    --skill \"skill-publish\" \\\n    --gate \"\u003Cgate_name>\" --gate-type \"\u003Chuman|quality>\" \\\n    --outcome \"\u003Capproved|rejected|passed|failed>\" \\\n    --refinement-loops \u003CN> \\\n    [--feedback \"\u003Cuser's feedback text>\"] \\\n    [--category \u003CCATEGORY>]\n```\n\n### Post-Run Retrospective\n\nAfter completion, ask: **\"Any feedback on this skill-publish run? (skip to finish)\"**\nIf provided, capture via trace_capture.py with gate \"run_retrospective\" and gate-type \"retrospective\".\n\n## Output\n- Confirmation message\n- Link to catalog entry + publish log\n","# Skill Publish — Controlled Release\n\n## Purpose\nPublish a validated skill with proper approvals, then update catalog metadata and log the publish event.\n\n## Inputs\n- Skill name\n- Evidence of test gates\n- Explicit approver (required for high blast radius)\n\n- Template paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fskill-publish\u002F`.\n\n## Steps\n1. **Run `\u002Fskill-validate \u003Cskill-name>`** and confirm PASS.\n2. **Enforce approval gate**\n   - If `blast_radius: high`, require explicit approval from an authorized maintainer. If missing, STOP.\n3. **Update catalog entry**\n   - Increment version if needed\n   - Update `updated` date\n4. **Write publish log** to `.jarvis\u002Fcontext\u002Fskills\u002Fpublish-log.md` with:\n   - Skill name, version, owner, blast radius\n   - Approver (if required)\n   - Date and summary\n5. **Return confirmation**\n\n## Decision Trace Protocol\n\nThis skill participates in the skill evolution system by capturing decision traces at gate resolutions and consulting accumulated feedback.\n\n### Trace Consultation (short loop)\n\nBefore executing any step with a quality or human gate, query accumulated decision traces:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_query.py\" recent \\\n    --skill \"skill-publish\" --gate \"\u003Cgate_name>\" --limit 5 --min-loops 1\n```\n\nIf patterns or recent feedback exist, incorporate them as additional constraints. Do not cite traces to the user unless asked.\n\n### Trace Capture (after gate resolution)\n\nAfter every gate resolves, capture a decision trace:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_capture.py\" capture \\\n    --skill \"skill-publish\" \\\n    --gate \"\u003Cgate_name>\" --gate-type \"\u003Chuman|quality>\" \\\n    --outcome \"\u003Capproved|rejected|passed|failed>\" \\\n    --refinement-loops \u003CN> \\\n    [--feedback \"\u003Cuser's feedback text>\"] \\\n    [--category \u003CCATEGORY>]\n```\n\n### Post-Run Retrospective\n\nAfter completion, ask: **\"Any feedback on this skill-publish run? (skip to finish)\"**\nIf provided, capture via trace_capture.py with gate \"run_retrospective\" and gate-type \"retrospective\".\n\n## Output\n- Confirmation message\n- Link to catalog entry + publish log\n",{"name":5,"description":7,"allowed-tools":42,"argument-hint":43,"disable-model-invocation":44},"Read, Grep, Glob, ApplyPatch, Write","[skill-name]",true,"main","bae3fdddd99eabe649d0d53cea5d2a0b501aa8b3","tools\u002Fflow-install\u002Fskills\u002Fskill-publish",7,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy","https:\u002F\u002Fgithub.com\u002FFlow-Research","2026-08-15 01:06:37",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":44},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Flow-Research\u002Fharnessy --skill skill-publish",{"tool":58,"command":59},"bunx","bunx skills add Flow-Research\u002Fharnessy --skill skill-publish",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Flow-Research\u002Fharnessy --skill skill-publish","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fskill-publish\u002FSKILL.md",[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"manifest.yaml","REFERENCE","参考文档",594,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fskill-publish\u002Fmanifest.yaml",[72,99,124,151,172,187],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":81,"publishedAt":37},"01M6GVTWDZDG82G8GGGYXXCT5B","wiki-research","Autonomous research orchestrator for Jarvis Wiki domains. Spawns a Claude agent with web tools to find new sources, drops them into raw\u002F, runs the compile pipeline, and emits autoresearch traces for the autoflow ratchet.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fwiki-research\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[82,83,84,85,86,87,88,89,90,29,30,91,92,93,94,95,96,97,98,35],"research","wiki","wiki research","web","compile","autoresearch","pipeline","Bash","find","web tools","autonomous","orchestrator","domain","domains","sources","Autonomous Research","with",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":106,"publishedAt":37},"01M6GVTQWAPB46BPQ6TCKSYDDA","tmux-agent-launcher","Launch Claude, OpenCode, or Codex in a named tmux session from the command line or agent workflows.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftmux-agent-launcher\u002FSKILL.md",[105],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,108,109,110,111,112,113,114,29,115,116,117,118,119,120,121,32,122,35,123],"tmux","launcher","tmux agent launcher","codex","launch","workflows","command line","command","session","opencode","default","runner","options","permission","agent workflows","line","mode",{"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":133,"publishedAt":37},"01M6GVTJEW4N5BAT5AG1M58PF6","test-quality-validator","Validate generated or hand-written tests for coverage completeness, correctness, and false-green risks using the canonical QA runtime, regression artifacts, and optional delivery-profile rules.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftest-quality-validator\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[134,135,136,137,138,139,140,89,141,29,30,142,143,144,145,146,147,148,149,150],"test","quality","validator","test quality validator","qa","browser","api","regression","context","coverage","generated","only","delivery","green","false","canonical","hand",{"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":157,"publishedAt":37},"01M6GVTE4BYCYCFKK2PS83ATX4","tech-spec","Generate production-ready technical specifications from product specs.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftech-spec\u002FSKILL.md",[],[158,159,160,161,162,163,164,28,165,29,30,166,167,168,35,169,170,171],"spec","tech spec","tech","review","generate","product","Production","technical","ready","specifications","folder","websearch","path","production-ready",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":37},"01M6GVT9FPGF2ME475HPQWKPSC","tech-spec-review","Seven-lens engineering review for technical_spec.md files, including an explicit simplicity and architectural fitness gate.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftech-spec-review\u002FSKILL.md",[],[161,158,179,159,160,180,181,28,165,29,30,182,183,184,185,186,35,169,170],"spec review","tech spec review","engineering","simplicity","files","gate","lens","quick",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":198,"publishedAt":37},"01M6GVT3XTZ4W3P2XQRDNBPZ4M","spec-to-regression","Generate browser and API regression scenarios from approved product and technical specs using the Harnessy delivery profile and regression artifact contract.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fspec-to-regression\u002FSKILL.md",[193],{"categoryNo":194,"categoryName":195,"taxonomyType":196,"taxonomyTypeDesc":197},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[158,141,199,162,139,163,200,140,89,201,28,165,29,30,146,202,203,148,32,204],"spec to regression","flow","json","artifact","contract","EPIC"]