[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AZWCN0WPCXTYD95S6BT9D":3,"skill-same:01M79AZWCN0WPCXTYD95S6BT9D":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79AZWCN0WPCXTYD95S6BT9D","install",null,"Installs an aos capability into this harness: reads its briefing, gates the skill names it would claim, renders it against the user's MOD.md, and materializes agents, symlinks, cron jobs and context blocks behind a diff gate. Use when the user says \"install\" or \"set up\" and names a capability, offers a capability directory or CAPABILITY.md to install, or when another install needs a missing dependency installed first. Do NOT use to re-render an already-installed capability against fresher upstream — that is capability-upgrade — and not to change how an installed one behaves, which is capability-evolve. The interview it runs mid-install belongs to capability-onboard.","AlmogBaku\u002Faos","AlmogBaku","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F98982?v=4","01M79AYYMZE5E1BEVEP6P829C4","Almog Baku","01M79AYYP0D19RBK33EBYYR3F8",5,"MIT","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Fcapabilities\u002Fcapability-lifecycle\u002Fskills\u002Finstall\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: install\ndescription: \"Installs an aos capability into this harness: reads its briefing, gates the skill names it would claim, renders it against the user's MOD.md, and materializes agents, symlinks, cron jobs and context blocks behind a diff gate. Use when the user says \\\"install\\\" or \\\"set up\\\" and names a capability, offers a capability directory or CAPABILITY.md to install, or when another install needs a missing dependency installed first. Do NOT use to re-render an already-installed capability against fresher upstream — that is capability-upgrade — and not to change how an installed one behaves, which is capability-evolve. The interview it runs mid-install belongs to capability-onboard.\"\n---\n\n# capability-install\n\nNot in context yet? Load the `capability-lifecycle` skill first — the map, the contract,\nthe overlay doctrine, and the Experience rules. Then:\n\n1. Resolve the capability dir across the household — `personal\u002Fcapabilities\u002F\u003Cid>`\n   first, then `upstream\u002Fcapabilities\u002F\u003Cid>`, counting a directory as a source **only if it\n   holds a `CAPABILITY.md`** (a MOD-only directory is the user's overlay at its mirrored\n   path, not a package); both are real packages → say so loudly and ask which\n   (never silently prefer). Then `aos-cap manifest \u003Cdir>` → validated JSON. Validation\n   failure → show the tool's error, offer fix-or-report; never improvise a parse.\n   Then hold the briefing to the declarations: it may say *how* to wire things, never\n   *where* — a briefing that places something the manifest does not declare (\"a dedicated\n   profile\", \"every profile that calls me\") → stop and report a package defect (contract).\n2. `aos-cap show \u003Cid>`: installed at this version → say so, stop; older →\n   hand to {{skill: upgrade}}.\n3. Dependencies: each `depends.capabilities` missing from `aos-cap list` →\n   announce briefly (\"work-tracker needs kb — setting that up first\"), install it first,\n   its interview included. Every `uses` provider is a dependency, so it is installed by now;\n   its `uses[].installed_name` comes from the manifest JSON.\n4. Your harness is the program hosting you. When `aos-cap --home \u003Caos_home> harness show`\n   exits 20 (none recorded), record it: `aos-cap --home \u003Caos_home> harness set \u003Charness-runtime>`;\n   a household that records another harness keeps it (the one `aos-session` drives). Load your\n   harness's cheat-sheet **now** — it travels with the `capability-lifecycle`\n   skill as `reference\u002Fharness-\u003Charness-runtime>.md` (load that skill, then read the file).\n   The `depends.host` rows (`mapping.\u003Cword>`) first, read as what the *harness* can express,\n   not as what the user has wired today (contract): a `required` feature at `support: none`\n   → friendly stop with the reason; a supported-but-unconfigured channel → install, and say\n   what they still need to set up; `preferred` unsupported → note each cron job's declared\n   degraded mode for recording.\n5. **Name gate**, before anything is written:\n   `aos-cap --home \u003Caos_home> skills \u003Cdir> --check --harness-skills \u003Cdir> …` — one\n   `--harness-skills` per skills dir this harness reads, per the cheat-sheet's\n   `mapping.skill`. Read its `checked:` lines —\n   a source it could not reach is named in capitals, and \"clean\" against two of three\n   sources is not clean. Exit 17 → stop and report which name is\n   taken and by whom; a collision is fixed in the package ({{skill: contribute}}, or the\n   user's own source), never by renaming here. Clean → the printed installed names are\n   what every later step uses (the `capability-lifecycle` skill's `reference\u002Fnaming.md`).\n   In the same breath, if the capability ships `agents\u002F`:\n   `aos-cap --home \u003Caos_home> agents \u003Cdir> --check` — agents land in a flat per-harness\n   namespace too, so the same exit 17 and the same rule (fix the package, never rename\n   here). It checks two of three sources; the third — agents already in the harness — has\n   no enumeration yet and says so in capitals, so glance at what the harness already has.\n6. Interview, iff the capability ships ONBOARDING.md — run it per the\n   `capability-lifecycle` skill's `reference\u002Foverlay.md` (batched, typed validation, secrets → store per the\n   cheat-sheet's Secrets section) → write `\u003Caos_home>\u002Fpersonal\u002Fcapabilities\u002F\u003Cid>\u002FMOD.md`\n   (capability-lifecycle's own: `\u003Caos_home>\u002Fpersonal\u002FMOD.md` — the `capability-lifecycle` skill's\n   `reference\u002Foverlay.md`, Which MOD.md).\n7. Render into staging, then transform: `aos-cap render \u003Cdir> \u003Cskill-id> --out\n   \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>\u002Fskills` per declared skill, plus any other subtree the\n   briefing pins (`adapters\u002F`, say, leaving `__pycache__` and `*.pyc` behind) copied to `rendered\u002F.staging\u002F\u003Cid>\u002F` — mechanical:\n   installed name, frontmatter `name`, `metadata.aos.origin`. Then the transform per the\n   `capability-lifecycle` skill's `reference\u002Foverlay.md`, against this capability's MOD.md\n   (Which MOD.md): fill `{{mod}}` slots, weave its prose statements, bake `\u003Caos_home>` — and a\n   baked render path names `rendered\u002F\u003Cid>\u002F`, the live render, never `.staging\u002F`.\n   Source files stay untouched.\n8. **STAGE** per the cheat-sheet's Materialization guide: the render sits in\n   `rendered\u002F.staging\u002F\u003Cid>\u002F`, nothing live yet, plus the exact native command plan —\n   agents (an existing one is adopted only on positive evidence it is this capability's,\n   never re-created; none → stop and ask — contract), skill symlinks (the installed name → the render, per `used_by`; container\n   harness → verify the `\u003Caos_home>\u002Frendered` mount per the cheat-sheet), `uses` links (per\n   row: the provider's recorded render from `aos-cap show \u003Cprovider>` → each listed agent's\n   skills location, under `installed_name`; a path another entry or a stranger holds →\n   stop), cron jobs\n   (`aos:\u003Ccap>:\u003Ccron-id>`, single-owner check first), context blocks (markers), config\n   keys, the capability's own tool install line — plus, when the package does not declare\n   it, the default an agent only the user talks to gets (contract), the cheat-sheet's\n   standing links, and whatever the root MOD's household\n   rules add to each agent this install creates or adopts (the `capability-lifecycle` skill's\n   `reference\u002Foverlay.md`). Touch\n   no harness file yet.\n   Second-harness install: stage links + native plan only (the render already exists);\n   cron jobs stay with their current owner unless the user reassigns.\n9. **GATE**: show the full plan, payoff-framed — each artifact → what it does\n   for the user — with the staged render's contents (`diff -ruN -x __pycache__ -x '*.pyc'\n   \u003Can empty dir> \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>` lists every file). Wait (unless the\n   root MOD.md says auto-accept). Declined → `aos-cap discard \u003Cid>`, and stop.\n10. **EXECUTE** the approved plan: `aos-cap swap \u003Cid>` puts the render live at\n   `rendered\u002F\u003Cid>\u002F`, then create the symlinks into it and run the native plan; `kb:`\n   zones → draft grant rows into each target KB's `## Grants` table, user approves.\n   A capability's tool may write machine-local files under `\u003Caos_home>\u002F.aos\u002F` — kb writes\n   `kb-principal.yml` (`kb init --principal` fills in a missing one, `kb config set\n   principal.id=` changes it) and\n   `kb-registry.yaml` (on `kb init`\u002F`kb adopt`). Do **not** create them yourself: the tool\n   owns them, the same way `aos-cap` owns the lockfile. Say they exist in the summary so\n   the user is not surprised by files nobody mentioned, and leave them out of `record`\n   (machine-local state is not a materialized artifact — hashing it would report drift the\n   first time the tool touched it).\n11. `aos-cap record \u003Cid> --version \u003Cv> --source-root \u003Croot> --artifact\n    \u003Crender-file>… --link \u003Csymlink>… --uses-link \u003Csymlink>… --job \u003Cid>… --config-key \u003Ck>…`\n    (`--job` ids land in `cron_owned`)\n    — `uses` links go to `--uses-link`, never `--link` (exit 19: one owner per link) — `\u003Croot>` is\n    whichever root step 1 resolved the capability dir in (`upstream` for shipped\n    capabilities, `personal` for the user's own); render files go to `--artifact`\n    (hashed), symlinks to `--link` (a symlink passed as `--artifact` fails: exit 16 — so a\n    tool binary needs `readlink -f $(command -v \u003Ctool>)` first, since `uv tool install` puts a\n    link on PATH). **`record` replaces the entry\n    wholesale**: on a second-harness install, start from `aos-cap show \u003Cid>` and pass the\n    combined set (both harnesses' links), never just this harness's.\n12. `aos-cap verify \u003Cid>` — exit 13 means what you just recorded does not match what is\n    on disk (a link that is a copy, a missed render, a hash taken before the transform).\n    Fix it now: you still know what you wrote, and the next person to find out would be\n    {{skill: upgrade}}, months from now. Hooks get the same check from the harness side:\n    each one consented and active per the cheat-sheet (its doctor, where the harness has\n    one) — a hook the harness skips fails silently.\n13. Celebrate specifically: what, where, which cron jobs, degraded modes in effect.\n","# capability-install\n\nNot in context yet? Load the `capability-lifecycle` skill first — the map, the contract,\nthe overlay doctrine, and the Experience rules. Then:\n\n1. Resolve the capability dir across the household — `personal\u002Fcapabilities\u002F\u003Cid>`\n   first, then `upstream\u002Fcapabilities\u002F\u003Cid>`, counting a directory as a source **only if it\n   holds a `CAPABILITY.md`** (a MOD-only directory is the user's overlay at its mirrored\n   path, not a package); both are real packages → say so loudly and ask which\n   (never silently prefer). Then `aos-cap manifest \u003Cdir>` → validated JSON. Validation\n   failure → show the tool's error, offer fix-or-report; never improvise a parse.\n   Then hold the briefing to the declarations: it may say *how* to wire things, never\n   *where* — a briefing that places something the manifest does not declare (\"a dedicated\n   profile\", \"every profile that calls me\") → stop and report a package defect (contract).\n2. `aos-cap show \u003Cid>`: installed at this version → say so, stop; older →\n   hand to {{skill: upgrade}}.\n3. Dependencies: each `depends.capabilities` missing from `aos-cap list` →\n   announce briefly (\"work-tracker needs kb — setting that up first\"), install it first,\n   its interview included. Every `uses` provider is a dependency, so it is installed by now;\n   its `uses[].installed_name` comes from the manifest JSON.\n4. Your harness is the program hosting you. When `aos-cap --home \u003Caos_home> harness show`\n   exits 20 (none recorded), record it: `aos-cap --home \u003Caos_home> harness set \u003Charness-runtime>`;\n   a household that records another harness keeps it (the one `aos-session` drives). Load your\n   harness's cheat-sheet **now** — it travels with the `capability-lifecycle`\n   skill as `reference\u002Fharness-\u003Charness-runtime>.md` (load that skill, then read the file).\n   The `depends.host` rows (`mapping.\u003Cword>`) first, read as what the *harness* can express,\n   not as what the user has wired today (contract): a `required` feature at `support: none`\n   → friendly stop with the reason; a supported-but-unconfigured channel → install, and say\n   what they still need to set up; `preferred` unsupported → note each cron job's declared\n   degraded mode for recording.\n5. **Name gate**, before anything is written:\n   `aos-cap --home \u003Caos_home> skills \u003Cdir> --check --harness-skills \u003Cdir> …` — one\n   `--harness-skills` per skills dir this harness reads, per the cheat-sheet's\n   `mapping.skill`. Read its `checked:` lines —\n   a source it could not reach is named in capitals, and \"clean\" against two of three\n   sources is not clean. Exit 17 → stop and report which name is\n   taken and by whom; a collision is fixed in the package ({{skill: contribute}}, or the\n   user's own source), never by renaming here. Clean → the printed installed names are\n   what every later step uses (the `capability-lifecycle` skill's `reference\u002Fnaming.md`).\n   In the same breath, if the capability ships `agents\u002F`:\n   `aos-cap --home \u003Caos_home> agents \u003Cdir> --check` — agents land in a flat per-harness\n   namespace too, so the same exit 17 and the same rule (fix the package, never rename\n   here). It checks two of three sources; the third — agents already in the harness — has\n   no enumeration yet and says so in capitals, so glance at what the harness already has.\n6. Interview, iff the capability ships ONBOARDING.md — run it per the\n   `capability-lifecycle` skill's `reference\u002Foverlay.md` (batched, typed validation, secrets → store per the\n   cheat-sheet's Secrets section) → write `\u003Caos_home>\u002Fpersonal\u002Fcapabilities\u002F\u003Cid>\u002FMOD.md`\n   (capability-lifecycle's own: `\u003Caos_home>\u002Fpersonal\u002FMOD.md` — the `capability-lifecycle` skill's\n   `reference\u002Foverlay.md`, Which MOD.md).\n7. Render into staging, then transform: `aos-cap render \u003Cdir> \u003Cskill-id> --out\n   \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>\u002Fskills` per declared skill, plus any other subtree the\n   briefing pins (`adapters\u002F`, say, leaving `__pycache__` and `*.pyc` behind) copied to `rendered\u002F.staging\u002F\u003Cid>\u002F` — mechanical:\n   installed name, frontmatter `name`, `metadata.aos.origin`. Then the transform per the\n   `capability-lifecycle` skill's `reference\u002Foverlay.md`, against this capability's MOD.md\n   (Which MOD.md): fill `{{mod}}` slots, weave its prose statements, bake `\u003Caos_home>` — and a\n   baked render path names `rendered\u002F\u003Cid>\u002F`, the live render, never `.staging\u002F`.\n   Source files stay untouched.\n8. **STAGE** per the cheat-sheet's Materialization guide: the render sits in\n   `rendered\u002F.staging\u002F\u003Cid>\u002F`, nothing live yet, plus the exact native command plan —\n   agents (an existing one is adopted only on positive evidence it is this capability's,\n   never re-created; none → stop and ask — contract), skill symlinks (the installed name → the render, per `used_by`; container\n   harness → verify the `\u003Caos_home>\u002Frendered` mount per the cheat-sheet), `uses` links (per\n   row: the provider's recorded render from `aos-cap show \u003Cprovider>` → each listed agent's\n   skills location, under `installed_name`; a path another entry or a stranger holds →\n   stop), cron jobs\n   (`aos:\u003Ccap>:\u003Ccron-id>`, single-owner check first), context blocks (markers), config\n   keys, the capability's own tool install line — plus, when the package does not declare\n   it, the default an agent only the user talks to gets (contract), the cheat-sheet's\n   standing links, and whatever the root MOD's household\n   rules add to each agent this install creates or adopts (the `capability-lifecycle` skill's\n   `reference\u002Foverlay.md`). Touch\n   no harness file yet.\n   Second-harness install: stage links + native plan only (the render already exists);\n   cron jobs stay with their current owner unless the user reassigns.\n9. **GATE**: show the full plan, payoff-framed — each artifact → what it does\n   for the user — with the staged render's contents (`diff -ruN -x __pycache__ -x '*.pyc'\n   \u003Can empty dir> \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>` lists every file). Wait (unless the\n   root MOD.md says auto-accept). Declined → `aos-cap discard \u003Cid>`, and stop.\n10. **EXECUTE** the approved plan: `aos-cap swap \u003Cid>` puts the render live at\n   `rendered\u002F\u003Cid>\u002F`, then create the symlinks into it and run the native plan; `kb:`\n   zones → draft grant rows into each target KB's `## Grants` table, user approves.\n   A capability's tool may write machine-local files under `\u003Caos_home>\u002F.aos\u002F` — kb writes\n   `kb-principal.yml` (`kb init --principal` fills in a missing one, `kb config set\n   principal.id=` changes it) and\n   `kb-registry.yaml` (on `kb init`\u002F`kb adopt`). Do **not** create them yourself: the tool\n   owns them, the same way `aos-cap` owns the lockfile. Say they exist in the summary so\n   the user is not surprised by files nobody mentioned, and leave them out of `record`\n   (machine-local state is not a materialized artifact — hashing it would report drift the\n   first time the tool touched it).\n11. `aos-cap record \u003Cid> --version \u003Cv> --source-root \u003Croot> --artifact\n    \u003Crender-file>… --link \u003Csymlink>… --uses-link \u003Csymlink>… --job \u003Cid>… --config-key \u003Ck>…`\n    (`--job` ids land in `cron_owned`)\n    — `uses` links go to `--uses-link`, never `--link` (exit 19: one owner per link) — `\u003Croot>` is\n    whichever root step 1 resolved the capability dir in (`upstream` for shipped\n    capabilities, `personal` for the user's own); render files go to `--artifact`\n    (hashed), symlinks to `--link` (a symlink passed as `--artifact` fails: exit 16 — so a\n    tool binary needs `readlink -f $(command -v \u003Ctool>)` first, since `uv tool install` puts a\n    link on PATH). **`record` replaces the entry\n    wholesale**: on a second-harness install, start from `aos-cap show \u003Cid>` and pass the\n    combined set (both harnesses' links), never just this harness's.\n12. `aos-cap verify \u003Cid>` — exit 13 means what you just recorded does not match what is\n    on disk (a link that is a copy, a missed render, a hash taken before the transform).\n    Fix it now: you still know what you wrote, and the next person to find out would be\n    {{skill: upgrade}}, months from now. Hooks get the same check from the harness side:\n    each one consented and active per the cheat-sheet (its doctor, where the harness has\n    one) — a hook the harness skips fails silently.\n13. Celebrate specifically: what, where, which cron jobs, degraded modes in effect.\n",{"name":5,"description":7},"main","31f4199ef67a0cedbdab2404eb9012d0c6e60c79","capabilities\u002Fcapability-lifecycle\u002Fskills\u002Finstall",2,"https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos","https:\u002F\u002Fgithub.com\u002FAlmogBaku","http:\u002F\u002Fwww.AlmogBaku.com","LLM hacker","2026-11-15 03:54:12",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add AlmogBaku\u002Faos --skill install",{"tool":39,"command":40},"bunx","bunx skills add AlmogBaku\u002Faos --skill install",{"tool":42,"command":43},"pnpm","pnpm dlx skills add AlmogBaku\u002Faos --skill install","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Fcapabilities\u002Fcapability-lifecycle\u002Fskills\u002Finstall\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DZT1MJJHC87HQVK2D6RRFW","wt-update","Updates an existing commitment when the user reports progress: completion, a new deadline, a stall, or abandonment. Use when the user says \"I did that\", \"finished X\", \"still waiting on Y\", \"push that to next week\", \"I started it\", or \"forget it, I'm not doing X\". Finds the matching open action, applies the change, and routes any knowledge the report carries to the knowledge base. Do NOT use to file a new commitment (that is wt-capture) or to find time for one (wt-schedule).","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fwork-tracker\u002Fskills\u002Fwt-update\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DZSY8XSXBMD53Y5QKRX6CD","wt-steward","Maintains an existing commitments backlog: overdue, about to expire, stalled, and repeatedly-rescheduled commitments, and someday items gone cold. Use when the nightly cron job fires or the user asks to review or tidy their backlog ('review my backlog', 'what's gone stale on my list'). Does not capture or schedule new work — that happens when the user speaks, through wt-capture and wt-schedule.","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fwork-tracker\u002Fskills\u002Fwt-steward\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DZST40GEJQ67KZSTG1PM93","wt-schedule","Estimates a commitment, links it to its project, and blocks time for it on the user's calendar. Use when the user asks to find time for something — \"when can I do this?\", \"find me two hours for the CFP\", \"block time for that tomorrow\", \"I want to work on it today\" — and immediately after wt-capture files a commitment that needs real hours. Do NOT use for a commitment that needs only a deadline or a reminder, and do NOT use to change what the user committed to — that is wt-update.","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fwork-tracker\u002Fskills\u002Fwt-schedule\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DZSMTQT1CCMQ3MK984C7FS","wt-capture","Records something the user has said they must do themselves: classifies the commitment as next, waiting, someday or trivial, writes it as an action page in their commitments base, and hands off to wt-schedule when it needs real hours. Use when the user commits to work of their own — \"I need to find time to…\", \"I have to…\", \"remind me to…\", \"help me remember…\", \"put that on my list\", \"I should … at some point\". Do NOT use when the user asks the assistant to do the work (\"write the CFP\", \"research X\", \"email Sam\") — that is a request to act now, not a commitment to track. Do NOT use for thoughts, facts or notes carrying no commitment; those are knowledge and belong to kb-capture.","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fwork-tracker\u002Fskills\u002Fwt-capture\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DZSG76N1GGR9C82RFK37RJ","work-tracker","Answers questions about the user's own commitments by querying their commitments base, explains the four statuses (next, waiting, someday, done), routes a request to the right work-tracker skill, and states who may change what without asking. Use when the user asks what they should be working on, what is overdue, what they are waiting on, or how their task tracking works, and no narrower work-tracker skill matches. Do NOT use to file a commitment the user just made (that is wt-capture), to find time for one (wt-schedule), or to report progress on one (wt-update).","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fwork-tracker\u002Fskills\u002Fwork-tracker\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DZSBWW4AQ7J1BTZHCJERTJ","kb","Explains how the user's knowledge bases are laid out and which kb skill handles a given job — the tree, the one queue, expiry, links, base health, maintenance. Use when the user asks how their knowledge base works, what state a base is in, why something was or was not kept, or wants base maintenance run, and no narrower kb skill matches. Do NOT use to file something the user just said (that is kb-capture), to answer a question from stored knowledge (that is kb-recall), or to pick a destination base for a write already in hand (that is kb-route).","https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Ffull-install\u002Fhome\u002Frendered\u002Fkb\u002Fskills\u002Fkb\u002FSKILL.md",[],[]]