[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K1MPFENC3HFH3SXAKCS88":3,"skill-same:01M77K1MPFENC3HFH3SXAKCS88":95},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M77K1MPFENC3HFH3SXAKCS88","life-orchestrator",null,"Life orchestration — monthly reviews, weekly plans, daily focus briefs from priorities.md and project state","Flow-Research\u002Fharnessy-v2","Flow-Research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204254796?v=4","01M6GVJZH9ZV0XGZTVBJRNW5BQ","Flow Research","01M77JYBHV7WQEBVS6R0AQ4YT6",13,"MIT","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: life-orchestrator\ndescription: Life orchestration — monthly reviews, weekly plans, daily focus briefs from priorities.md and project state\ndisable-model-invocation: true\nallowed-tools: Read, Write, Edit, Bash, Grep, Glob\nargument-hint: \"monthly | weekly | daily | status | feedback \\\"...\\\"\"\n---\n\n# Life Orchestrator\n\n## Purpose\n\nYou are the user's practical planning partner. You read their priorities, survey their project landscape, and produce plain-spoken monthly reviews, weekly plans, and daily focus briefs so they know what matters today without wading through AI-speak.\n\n## Three Rhythms\n\n| Rhythm  | Input                              | Output                        | Cost      |\n|---------|-------------------------------------|-------------------------------|-----------|\n| Monthly | All project state + priorities.md   | Monthly review with goal-agent | Expensive |\n| Weekly  | Monthly review + current state      | Weekly plan via Harnessy AI runner | Medium |\n| Daily   | Priorities + weekly plan + prior brief + current state | Personal daily brief + Anytype journal via Harnessy AI runner | Cheap |\n\n## Data Flow\n\n```\npriorities.md (the user's voice — the primary input)\ncompetence-priorities.md (durable learning and development commitments)\n      |\n      v\ncollect-state script --> project context, meetings, notes, agent state\nwatched RSS\u002FAtom feeds + learning-research --> provenance-checked article candidates\n      |\n      v\nHarnessy AI runner (Claude, Codex, or OpenCode)\n      |\n      v\n~\u002F.agents\u002Flife\u002FYYYY\u002FMon\u002F  (structured output)\n      |\n      v\nAnytype journal (via Jarvis CLI)\n```\n\n## Key Principles\n\n1. **The user's voice is primary.** `priorities.md` is always read first. It sets the lens through which all project state is interpreted. An optional `competence-priorities.md` preserves long-term learning commitments without overruling immediate priorities.\n2. **Rhythms compound.** Monthly reviews feed weekly plans, which feed daily briefs. Each layer adds specificity without repeating context.\n3. **Cost-aware.** Monthly runs are expensive (full goal-agent). Weekly runs are moderate (focused AI synthesis). Daily runs use bounded context and one focused model call.\n4. **Journal integration.** Daily briefs and weekly executive packs may use separate Anytype spaces. Machine-private routing lives in `~\u002F.agents\u002Flife\u002Fconfig.json`.\n5. **Continuity without invention.** A prior brief can carry open threads forward, but newer priorities, meetings, notes, and project records always override it.\n6. **Dates come from evidence.** Weekly plans are matched by their stated date range when available, and daily briefs do not invent deadlines or treat missing records as proof.\n7. **Regeneration is idempotent.** A reviewed daily regeneration replaces today's existing Anytype journal body when a stable reference exists; it must not create a duplicate entry.\n\n## Provider Configuration\n\nDaily and weekly synthesis use `${AGENTS_SKILLS_ROOT}\u002F_shared\u002Fai_runner.py`.\n\n- `HARNESSY_AI_PROVIDER=auto|claude|codex|opencode` controls the runtime.\n- `HARNESSY_AI_PROVIDER_ORDER=codex,opencode,claude` controls fallback order when provider is `auto`.\n- `HARNESSY_AI_MODEL`, `HARNESSY_AI_FALLBACK_MODEL`, `HARNESSY_AI_TIMEOUT`, and `HARNESSY_AI_BUDGET_USD` tune model calls without editing scripts.\n\n## Inputs\n\n- Subcommand and arguments: `$ARGUMENTS`\n- Priorities file: `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Fpriorities.md` in the active project root, with `~\u002F.agents\u002Flife\u002Fpriorities.md` retained as a legacy fallback for weekly planning\n- Competence file: optional `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Fcompetence-priorities.md`, overrideable with `LIFE_COMPETENCE_PRIORITIES_FILE`\n- Learning-research steering: optional `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Flearning-research.md`; its `## Current Topics` list controls the scheduled research rotation\n- Templates: `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Ftemplates\u002F`\n- Scripts: `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Fscripts\u002F`\n- Runtime routing: `~\u002F.agents\u002Flife\u002Fconfig.json` with `journal_spaces.daily` and `journal_spaces.weekly`\n\n## Steps\n\n1. Parse `$ARGUMENTS` to determine the subcommand.\n2. Follow the command specification in `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Fcommands\u002Flife.md` exactly.\n3. Always read `priorities.md` before any project state collection.\n4. Write outputs to `~\u002F.agents\u002Flife\u002FYYYY\u002FMon\u002F` using the date-based naming convention.\n5. **Daily reading is useful, not filler.** Each brief should contain two or three relevant links. Discovery runs separately each morning; deterministic checks remove stale, malformed, and duplicate links; and the brief model may rank only supplied candidates. Previously surfaced, still-recent sources remain a fallback reserve. If fewer than two verified candidates exist after the wait and reserve checks, publication fails rather than inventing a source or publishing an empty section.\n6. **Research and publication share one clock.** Research defaults to a 90-minute cutoff. The daily brief waits up to 30 minutes for at least two verified links. The cutoff must fit between the research start and the end of that wait, with a safety margin. If fresh research fails, the brief may reuse recent provenance-checked sources; it must not silently publish an empty reading section.\n\n## Reading Timing Configuration\n\nPersist these values under `reading` in `~\u002F.agents\u002Flife\u002Fconfig.json`. The\nmatching environment variable overrides the file for one run.\n\n- `LIFE_RESEARCH_CUTOFF_SECONDS` — research hard cutoff; default `5400` (90 minutes)\n- `LIFE_READING_WAIT_SECONDS` — daily-brief wait; default `1800` (30 minutes)\n- `LIFE_READING_POLL_SECONDS` — readiness polling interval; default `15`\n- `LIFE_READING_MINIMUM` — minimum verified links required to publish; default `2`\n- `LIFE_RESEARCH_START` \u002F `LIFE_DAILY_BRIEF_START` — schedule clocks used to validate the cutoff; defaults `04:15` \u002F `05:30`\n- `LIFE_RESEARCH_SAFETY_MARGIN_SECONDS` — time reserved before publication; default `300`\n\nWatched feeds are configured under `reading.sources` in `~\u002F.agents\u002Flife\u002Fconfig.json`.\nEach source supports `name`, `url`, `enabled`, `tier`, `topic`,\n`max_per_brief`, `max_items_per_poll`, `evergreen_enabled`,\n`max_evergreen_per_poll`, `evergreen_min_score`, and `evergreen_keywords`.\nFeed items retain their publication date, source tier, and RSS provenance. Recent\nitems use publication-date freshness; older items may enter through the bounded\nevergreen lane when they match the configured vocabulary. The feed adapter stores\nonly feed-supplied content and never fetches or archives the linked article page.\n\n## Output\n\n- Rhythm-specific artifact in `~\u002F.agents\u002Flife\u002F`\n- Anytype journal entry (daily rhythm; weekly uses its separately configured space)\n- Desktop notification on completion (daily rhythm)\n- Trace capture for quality tracking\n","# Life Orchestrator\n\n## Purpose\n\nYou are the user's practical planning partner. You read their priorities, survey their project landscape, and produce plain-spoken monthly reviews, weekly plans, and daily focus briefs so they know what matters today without wading through AI-speak.\n\n## Three Rhythms\n\n| Rhythm  | Input                              | Output                        | Cost      |\n|---------|-------------------------------------|-------------------------------|-----------|\n| Monthly | All project state + priorities.md   | Monthly review with goal-agent | Expensive |\n| Weekly  | Monthly review + current state      | Weekly plan via Harnessy AI runner | Medium |\n| Daily   | Priorities + weekly plan + prior brief + current state | Personal daily brief + Anytype journal via Harnessy AI runner | Cheap |\n\n## Data Flow\n\n```\npriorities.md (the user's voice — the primary input)\ncompetence-priorities.md (durable learning and development commitments)\n      |\n      v\ncollect-state script --> project context, meetings, notes, agent state\nwatched RSS\u002FAtom feeds + learning-research --> provenance-checked article candidates\n      |\n      v\nHarnessy AI runner (Claude, Codex, or OpenCode)\n      |\n      v\n~\u002F.agents\u002Flife\u002FYYYY\u002FMon\u002F  (structured output)\n      |\n      v\nAnytype journal (via Jarvis CLI)\n```\n\n## Key Principles\n\n1. **The user's voice is primary.** `priorities.md` is always read first. It sets the lens through which all project state is interpreted. An optional `competence-priorities.md` preserves long-term learning commitments without overruling immediate priorities.\n2. **Rhythms compound.** Monthly reviews feed weekly plans, which feed daily briefs. Each layer adds specificity without repeating context.\n3. **Cost-aware.** Monthly runs are expensive (full goal-agent). Weekly runs are moderate (focused AI synthesis). Daily runs use bounded context and one focused model call.\n4. **Journal integration.** Daily briefs and weekly executive packs may use separate Anytype spaces. Machine-private routing lives in `~\u002F.agents\u002Flife\u002Fconfig.json`.\n5. **Continuity without invention.** A prior brief can carry open threads forward, but newer priorities, meetings, notes, and project records always override it.\n6. **Dates come from evidence.** Weekly plans are matched by their stated date range when available, and daily briefs do not invent deadlines or treat missing records as proof.\n7. **Regeneration is idempotent.** A reviewed daily regeneration replaces today's existing Anytype journal body when a stable reference exists; it must not create a duplicate entry.\n\n## Provider Configuration\n\nDaily and weekly synthesis use `${AGENTS_SKILLS_ROOT}\u002F_shared\u002Fai_runner.py`.\n\n- `HARNESSY_AI_PROVIDER=auto|claude|codex|opencode` controls the runtime.\n- `HARNESSY_AI_PROVIDER_ORDER=codex,opencode,claude` controls fallback order when provider is `auto`.\n- `HARNESSY_AI_MODEL`, `HARNESSY_AI_FALLBACK_MODEL`, `HARNESSY_AI_TIMEOUT`, and `HARNESSY_AI_BUDGET_USD` tune model calls without editing scripts.\n\n## Inputs\n\n- Subcommand and arguments: `$ARGUMENTS`\n- Priorities file: `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Fpriorities.md` in the active project root, with `~\u002F.agents\u002Flife\u002Fpriorities.md` retained as a legacy fallback for weekly planning\n- Competence file: optional `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Fcompetence-priorities.md`, overrideable with `LIFE_COMPETENCE_PRIORITIES_FILE`\n- Learning-research steering: optional `.jarvis\u002Fcontext\u002Fprivate\u002F$USER\u002Flearning-research.md`; its `## Current Topics` list controls the scheduled research rotation\n- Templates: `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Ftemplates\u002F`\n- Scripts: `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Fscripts\u002F`\n- Runtime routing: `~\u002F.agents\u002Flife\u002Fconfig.json` with `journal_spaces.daily` and `journal_spaces.weekly`\n\n## Steps\n\n1. Parse `$ARGUMENTS` to determine the subcommand.\n2. Follow the command specification in `${AGENTS_SKILLS_ROOT}\u002Flife-orchestrator\u002Fcommands\u002Flife.md` exactly.\n3. Always read `priorities.md` before any project state collection.\n4. Write outputs to `~\u002F.agents\u002Flife\u002FYYYY\u002FMon\u002F` using the date-based naming convention.\n5. **Daily reading is useful, not filler.** Each brief should contain two or three relevant links. Discovery runs separately each morning; deterministic checks remove stale, malformed, and duplicate links; and the brief model may rank only supplied candidates. Previously surfaced, still-recent sources remain a fallback reserve. If fewer than two verified candidates exist after the wait and reserve checks, publication fails rather than inventing a source or publishing an empty section.\n6. **Research and publication share one clock.** Research defaults to a 90-minute cutoff. The daily brief waits up to 30 minutes for at least two verified links. The cutoff must fit between the research start and the end of that wait, with a safety margin. If fresh research fails, the brief may reuse recent provenance-checked sources; it must not silently publish an empty reading section.\n\n## Reading Timing Configuration\n\nPersist these values under `reading` in `~\u002F.agents\u002Flife\u002Fconfig.json`. The\nmatching environment variable overrides the file for one run.\n\n- `LIFE_RESEARCH_CUTOFF_SECONDS` — research hard cutoff; default `5400` (90 minutes)\n- `LIFE_READING_WAIT_SECONDS` — daily-brief wait; default `1800` (30 minutes)\n- `LIFE_READING_POLL_SECONDS` — readiness polling interval; default `15`\n- `LIFE_READING_MINIMUM` — minimum verified links required to publish; default `2`\n- `LIFE_RESEARCH_START` \u002F `LIFE_DAILY_BRIEF_START` — schedule clocks used to validate the cutoff; defaults `04:15` \u002F `05:30`\n- `LIFE_RESEARCH_SAFETY_MARGIN_SECONDS` — time reserved before publication; default `300`\n\nWatched feeds are configured under `reading.sources` in `~\u002F.agents\u002Flife\u002Fconfig.json`.\nEach source supports `name`, `url`, `enabled`, `tier`, `topic`,\n`max_per_brief`, `max_items_per_poll`, `evergreen_enabled`,\n`max_evergreen_per_poll`, `evergreen_min_score`, and `evergreen_keywords`.\nFeed items retain their publication date, source tier, and RSS provenance. Recent\nitems use publication-date freshness; older items may enter through the bounded\nevergreen lane when they match the configured vocabulary. The feed adapter stores\nonly feed-supplied content and never fetches or archives the linked article page.\n\n## Output\n\n- Rhythm-specific artifact in `~\u002F.agents\u002Flife\u002F`\n- Anytype journal entry (daily rhythm; weekly uses its separately configured space)\n- Desktop notification on completion (daily rhythm)\n- Trace capture for quality tracking\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"disable-model-invocation":26},"Read, Write, Edit, Bash, Grep, Glob","monthly | weekly | daily | status | feedback \"...\"",true,"main","437c399aef1913dab00310feea6d7962d3684949","packages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator",6,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2","https:\u002F\u002Fgithub.com\u002FFlow-Research","2026-11-12 09:49:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Flow-Research\u002Fharnessy-v2 --skill life-orchestrator",{"tool":40,"command":41},"bunx","bunx skills add Flow-Research\u002Fharnessy-v2 --skill life-orchestrator",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Flow-Research\u002Fharnessy-v2 --skill life-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002FSKILL.md",[47,53,57,63,67,71,75,79,83,87,91],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"commands\u002Flife.md","REFERENCE","参考文档",14473,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fcommands\u002Flife.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"manifest.yaml",2691,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fmanifest.yaml",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fcollect-state","SCRIPT","脚本",50634,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Fcollect-state",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fdaily-brief",44997,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Fdaily-brief",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Flearning-research",19659,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Flearning-research",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fnotify",2451,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Fnotify",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fprepare-weekly-prompt",11517,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Fprepare-weekly-prompt",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fweekly-plan",9667,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Fscripts\u002Fweekly-plan",{"path":84,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":85,"sourceHtmlUrl":86},"templates\u002Fdaily-focus.md",410,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Ftemplates\u002Fdaily-focus.md",{"path":88,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":89,"sourceHtmlUrl":90},"templates\u002Fmonthly-review.md",535,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Ftemplates\u002Fmonthly-review.md",{"path":92,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":93,"sourceHtmlUrl":94},"templates\u002Fweekly-plan.md",1193,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcapability-harnessy-v1-full\u002Fresources\u002Fsource\u002Ftools\u002Fflow-install\u002Fskills\u002Flife-orchestrator\u002Ftemplates\u002Fweekly-plan.md",[96,103,110,117,124,131],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M77K5PBWD2KS3QRTWR7VHHXB","personal-knowledge","Save sources to the private Harnessy learning library, sync delivered readings, answer questions from saved evidence, browse its wiki, and generate weekly learning reviews.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fharnessy-core\u002Fresources\u002Fskills\u002Fpersonal-knowledge\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M77K5MNRTVCPCES38J7PGJCP","valid-skill","A valid skill for testing purposes.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fvalid-skill\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M77K5HQMHXFVQAWSJ9X90BDX","unknown-field","A skill with an unknown frontmatter field.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Funknown-field\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M77K5GNEGDBJ51MNS14A4N46","nested-child","Nested skill should be ignored.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Froot-skill-preferred\u002Fnested-child\u002FSKILL.md",[],[],{"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":130,"publishedAt":19},"01M77K5DY7RPPCFCEXV3AFH0R5","root-skill-preferred","Root skill should win.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Froot-skill-preferred\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":19},"01M77K5CYV52QQ7CWV1TAPG63J","no-frontmatter","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy-v2\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fno-frontmatter\u002FSKILL.md",[],[]]