[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GVSQDFN5W9RJWDAW795CKA":3,"skill-same:01M6GVSQDFN5W9RJWDAW795CKA":74},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":67},"01M6GVSQDFN5W9RJWDAW795CKA","skill-promote",null,"Promote trace-driven improvements from the installed skill copy back to the shared Harnessy source.","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-promote\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"promote","skill promote","run","Bash","trace","grep","read","write","edit","back","shared","dry","driven","name","copy","true","2026-11-10 10:12:30",false,"---\nname: skill-promote\ndescription: Promote trace-driven improvements from the installed skill copy back to the shared Harnessy source.\ndisable-model-invocation: true\nallowed-tools: Read, Write, Edit, Bash, Grep, Glob\nargument-hint: \"\u003Cskill-name> [--dry-run] [--all]\"\n---\n\n# Skill Promote — Sync Improvements to Shared Source\n\n## Purpose\n\nAfter `\u002Fskill-improve` applies changes to the installed copy at `~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002F`, those improvements only exist locally. This skill promotes them back to the shared Harnessy source at `tools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F` so they become permanent and distributable.\n\n## Inputs\n\n- `skill-name` — the skill to promote (or `--all` to check all skills)\n- `--dry-run` — show what would change without applying\n- `--all` — scan all shared Harnessy skills for unpromoted improvements\n\nTemplate paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fskill-promote\u002F`.\n\n## Steps\n\n### 1. Detect unpromoted improvements\n\nCompare the installed and source versions:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Fpromote_check.py\" check \\\n    --skill \"\u003Cskill-name>\" \\\n    --installed-root \"${AGENTS_SKILLS_ROOT}\" \\\n    --source-root \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\"\n```\n\nThe script compares `manifest.yaml` versions at both paths. If installed version > source version, improvements exist that haven't been promoted.\n\nAlso read `~\u002F.agents\u002Ftraces\u002F\u003Cskill-name>\u002Fimprovements.ndjson` to identify which specific improvements are pending.\n\nIf no unpromoted improvements exist, report \"No unpromoted improvements for `\u003Cskill-name>`.\" and stop.\n\n### 2. Resolve Harnessy repo path\n\nFind the Harnessy repo root. Check in order:\n1. Current working directory — if it contains `tools\u002Fflow-install\u002Fskills\u002F`, use it\n2. `$FLOW_REPO_ROOT` environment variable\n3. `$HOME\u002F.cache\u002Fharnessy\u002F` (cached installer source)\n\nIf the Harnessy repo can't be found, report the error and ask the user to cd into it or set `FLOW_REPO_ROOT`.\n\n### 3. Diff installed vs source\n\nFor the skill being promoted, diff all files:\n\n```bash\ndiff -rq \"${AGENTS_SKILLS_ROOT}\u002F\u003Cskill-name>\u002F\" \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\"\n```\n\nPresent the diff to the user with context from `improvements.ndjson`:\n\n```\nUnpromoted improvements for issue-flow (installed: 0.8.3, source: 0.8.0):\n\n  imp_20260410_001 (2026-04-10): Added mobile\u002Fresponsive requirement to PRD phase\n    Evidence: 3 traces, pattern \"mobile experience\" in 2\u002F3\n    File: commands\u002Fissue-flow.md, section: Phase 2 — PRD\n\n  imp_20260412_001 (2026-04-12): Enforce measurable acceptance criteria\n    Evidence: 2 traces, category UNCLEAR_CRITERIA\n    File: commands\u002Fissue-flow.md, section: Phase 2 — PRD\n\nFiles changed:\n  M commands\u002Fissue-flow.md\n  M manifest.yaml\n```\n\nIf `--dry-run`, stop here.\n\n### 4. Confirm with user\n\nAsk: \"Apply these improvements to the shared Harnessy source? (yes \u002F no)\"\n\n### 5. Apply the promotion\n\nFor each changed file, copy from installed to source:\n\n```bash\ncp \"${AGENTS_SKILLS_ROOT}\u002F\u003Cskill-name>\u002F\u003Cfile>\" \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\u003Cfile>\"\n```\n\n### 6. Stage and show the diff\n\nStage the changes in the Harnessy repo:\n\n```bash\ngit add \"tools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\"\ngit diff --cached --stat\n```\n\nShow the user the staged diff for final review.\n\n### 7. Suggest commit and sync\n\nDo NOT commit automatically. Instead, suggest:\n\n```\nChanges staged in the Harnessy repo. Recommended next steps:\n\n1. Review: git diff --cached\n2. Commit:\n   git commit -m \"improve(\u003Cskill-name>): promote trace-driven improvements v\u003Cold> → v\u003Cnew>\n\n   Improvements promoted from installed copy based on decision trace evidence:\n   - \u003Cimp_id>: \u003Csummary>\n   - \u003Cimp_id>: \u003Csummary>\n\n   Trace evidence: \u003CN> traces across \u003CM> runs, patterns: \u003Clist>\"\n\n3. Push and sync:\n   - Push to remote branch\n   - Use \u002Fcontext-sync or manual PR for review\n```\n\n### 8. Mark improvements as promoted\n\nAfter the user confirms the commit happened, update `~\u002F.agents\u002Ftraces\u002F\u003Cskill-name>\u002Fimprovements.ndjson` by appending a promotion record:\n\n```json\n{\n  \"type\": \"promotion\",\n  \"timestamp\": \"\u003CISO 8601>\",\n  \"skill\": \"\u003Cskill-name>\",\n  \"improvements_promoted\": [\"imp_20260410_001\", \"imp_20260412_001\"],\n  \"promoted_to_version\": \"0.8.3\",\n  \"commit_branch\": \"\u003Cbranch>\"\n}\n```\n\n## `--all` mode\n\nWhen invoked with `--all`:\n\n1. Scan every skill directory under `${AGENTS_SKILLS_ROOT}\u002F` that also exists under `\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F`\n2. Compare versions\n3. Report a summary table:\n\n```\nSkill               Installed  Source  Unpromoted\nissue-flow          0.8.3      0.8.0  3 improvements\ncode-review         0.2.1      0.2.1  —\nprd                 0.3.0      0.2.0  1 improvement\n```\n\n4. Ask which skills to promote (all \u002F specific names \u002F none)\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 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_query.py\" recent \\\n    --skill \"skill-promote\" --gate \"\u003Cgate_name>\" --limit 5 --min-loops 1\n```\n\nIf patterns or recent feedback exist, incorporate them as additional constraints. Do not cite traces to the user unless asked.\n\n### Trace Capture (after gate resolution)\n\nAfter every gate resolves, capture a decision trace:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_capture.py\" capture \\\n    --skill \"skill-promote\" \\\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-promote run? (skip to finish)\"**\nIf provided, capture via trace_capture.py with gate \"run_retrospective\" and gate-type \"retrospective\".\n\n## Output\n\n- Diff summary with improvement evidence\n- Staged changes in Harnessy repo (not committed)\n- Suggested commit message with trace evidence\n- Promotion record in improvements.ndjson\n","# Skill Promote — Sync Improvements to Shared Source\n\n## Purpose\n\nAfter `\u002Fskill-improve` applies changes to the installed copy at `~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002F`, those improvements only exist locally. This skill promotes them back to the shared Harnessy source at `tools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F` so they become permanent and distributable.\n\n## Inputs\n\n- `skill-name` — the skill to promote (or `--all` to check all skills)\n- `--dry-run` — show what would change without applying\n- `--all` — scan all shared Harnessy skills for unpromoted improvements\n\nTemplate paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fskill-promote\u002F`.\n\n## Steps\n\n### 1. Detect unpromoted improvements\n\nCompare the installed and source versions:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Fpromote_check.py\" check \\\n    --skill \"\u003Cskill-name>\" \\\n    --installed-root \"${AGENTS_SKILLS_ROOT}\" \\\n    --source-root \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\"\n```\n\nThe script compares `manifest.yaml` versions at both paths. If installed version > source version, improvements exist that haven't been promoted.\n\nAlso read `~\u002F.agents\u002Ftraces\u002F\u003Cskill-name>\u002Fimprovements.ndjson` to identify which specific improvements are pending.\n\nIf no unpromoted improvements exist, report \"No unpromoted improvements for `\u003Cskill-name>`.\" and stop.\n\n### 2. Resolve Harnessy repo path\n\nFind the Harnessy repo root. Check in order:\n1. Current working directory — if it contains `tools\u002Fflow-install\u002Fskills\u002F`, use it\n2. `$FLOW_REPO_ROOT` environment variable\n3. `$HOME\u002F.cache\u002Fharnessy\u002F` (cached installer source)\n\nIf the Harnessy repo can't be found, report the error and ask the user to cd into it or set `FLOW_REPO_ROOT`.\n\n### 3. Diff installed vs source\n\nFor the skill being promoted, diff all files:\n\n```bash\ndiff -rq \"${AGENTS_SKILLS_ROOT}\u002F\u003Cskill-name>\u002F\" \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\"\n```\n\nPresent the diff to the user with context from `improvements.ndjson`:\n\n```\nUnpromoted improvements for issue-flow (installed: 0.8.3, source: 0.8.0):\n\n  imp_20260410_001 (2026-04-10): Added mobile\u002Fresponsive requirement to PRD phase\n    Evidence: 3 traces, pattern \"mobile experience\" in 2\u002F3\n    File: commands\u002Fissue-flow.md, section: Phase 2 — PRD\n\n  imp_20260412_001 (2026-04-12): Enforce measurable acceptance criteria\n    Evidence: 2 traces, category UNCLEAR_CRITERIA\n    File: commands\u002Fissue-flow.md, section: Phase 2 — PRD\n\nFiles changed:\n  M commands\u002Fissue-flow.md\n  M manifest.yaml\n```\n\nIf `--dry-run`, stop here.\n\n### 4. Confirm with user\n\nAsk: \"Apply these improvements to the shared Harnessy source? (yes \u002F no)\"\n\n### 5. Apply the promotion\n\nFor each changed file, copy from installed to source:\n\n```bash\ncp \"${AGENTS_SKILLS_ROOT}\u002F\u003Cskill-name>\u002F\u003Cfile>\" \"\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\u003Cfile>\"\n```\n\n### 6. Stage and show the diff\n\nStage the changes in the Harnessy repo:\n\n```bash\ngit add \"tools\u002Fflow-install\u002Fskills\u002F\u003Cskill-name>\u002F\"\ngit diff --cached --stat\n```\n\nShow the user the staged diff for final review.\n\n### 7. Suggest commit and sync\n\nDo NOT commit automatically. Instead, suggest:\n\n```\nChanges staged in the Harnessy repo. Recommended next steps:\n\n1. Review: git diff --cached\n2. Commit:\n   git commit -m \"improve(\u003Cskill-name>): promote trace-driven improvements v\u003Cold> → v\u003Cnew>\n\n   Improvements promoted from installed copy based on decision trace evidence:\n   - \u003Cimp_id>: \u003Csummary>\n   - \u003Cimp_id>: \u003Csummary>\n\n   Trace evidence: \u003CN> traces across \u003CM> runs, patterns: \u003Clist>\"\n\n3. Push and sync:\n   - Push to remote branch\n   - Use \u002Fcontext-sync or manual PR for review\n```\n\n### 8. Mark improvements as promoted\n\nAfter the user confirms the commit happened, update `~\u002F.agents\u002Ftraces\u002F\u003Cskill-name>\u002Fimprovements.ndjson` by appending a promotion record:\n\n```json\n{\n  \"type\": \"promotion\",\n  \"timestamp\": \"\u003CISO 8601>\",\n  \"skill\": \"\u003Cskill-name>\",\n  \"improvements_promoted\": [\"imp_20260410_001\", \"imp_20260412_001\"],\n  \"promoted_to_version\": \"0.8.3\",\n  \"commit_branch\": \"\u003Cbranch>\"\n}\n```\n\n## `--all` mode\n\nWhen invoked with `--all`:\n\n1. Scan every skill directory under `${AGENTS_SKILLS_ROOT}\u002F` that also exists under `\u003Cflow-repo>\u002Ftools\u002Fflow-install\u002Fskills\u002F`\n2. Compare versions\n3. Report a summary table:\n\n```\nSkill               Installed  Source  Unpromoted\nissue-flow          0.8.3      0.8.0  3 improvements\ncode-review         0.2.1      0.2.1  —\nprd                 0.3.0      0.2.0  1 improvement\n```\n\n4. Ask which skills to promote (all \u002F specific names \u002F none)\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 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_query.py\" recent \\\n    --skill \"skill-promote\" --gate \"\u003Cgate_name>\" --limit 5 --min-loops 1\n```\n\nIf patterns or recent feedback exist, incorporate them as additional constraints. Do not cite traces to the user unless asked.\n\n### Trace Capture (after gate resolution)\n\nAfter every gate resolves, capture a decision trace:\n\n```bash\npython3 \"${AGENTS_SKILLS_ROOT}\u002F_shared\u002Ftrace_capture.py\" capture \\\n    --skill \"skill-promote\" \\\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-promote run? (skip to finish)\"**\nIf provided, capture via trace_capture.py with gate \"run_retrospective\" and gate-type \"retrospective\".\n\n## Output\n\n- Diff summary with improvement evidence\n- Staged changes in Harnessy repo (not committed)\n- Suggested commit message with trace evidence\n- Promotion record in improvements.ndjson\n",{"name":5,"description":7,"allowed-tools":45,"argument-hint":46,"disable-model-invocation":47},"Read, Write, Edit, Bash, Grep, Glob","\u003Cskill-name> [--dry-run] [--all]",true,"main","bae3fdddd99eabe649d0d53cea5d2a0b501aa8b3","tools\u002Fflow-install\u002Fskills\u002Fskill-promote",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":56,"prompt":66,"zipAvailable":47},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Flow-Research\u002Fharnessy --skill skill-promote",{"tool":61,"command":62},"bunx","bunx skills add Flow-Research\u002Fharnessy --skill skill-promote",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Flow-Research\u002Fharnessy --skill skill-promote","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fskill-promote\u002FSKILL.md",[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"manifest.yaml","REFERENCE","参考文档",917,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fskill-promote\u002Fmanifest.yaml",[75,101,126,153,174,189],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":84,"publishedAt":40},"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",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[85,86,87,88,89,90,91,27,92,30,31,93,94,95,96,97,98,99,100,39],"research","wiki","wiki research","web","compile","autoresearch","pipeline","find","web tools","autonomous","orchestrator","domain","domains","sources","Autonomous Research","with",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":40},"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",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,111,112,113,114,115,116,30,117,118,119,120,121,122,123,37,124,39,125],"tmux","launcher","tmux agent launcher","codex","launch","workflows","command line","command","session","opencode","default","runner","options","permission","agent workflows","line","mode",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":135,"publishedAt":40},"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",[132],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[136,137,138,139,140,141,142,27,143,30,31,144,145,146,147,148,149,150,151,152],"test","quality","validator","test quality validator","qa","browser","api","regression","context","coverage","generated","only","delivery","green","false","canonical","hand",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":40},"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",[],[160,161,162,163,164,165,166,29,167,30,31,168,169,170,39,171,172,173],"spec","tech spec","tech","review","generate","product","Production","technical","ready","specifications","folder","websearch","path","production-ready",{"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":40},"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",[],[163,160,181,161,162,182,183,29,167,30,31,184,185,186,187,188,39,171,172],"spec review","tech spec review","engineering","simplicity","files","gate","lens","quick",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":200,"publishedAt":40},"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",[195],{"categoryNo":196,"categoryName":197,"taxonomyType":198,"taxonomyTypeDesc":199},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[160,143,201,164,141,165,202,142,27,203,29,167,30,31,148,204,205,150,37,206],"spec to regression","flow","json","artifact","contract","EPIC"]