[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79B0PD71JDTPVJR9Z3RN8VQ":3,"skill-same:01M79B0PD71JDTPVJR9Z3RN8VQ":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},"01M79B0PD71JDTPVJR9Z3RN8VQ","upgrade",null,"Upgrades installed aos capabilities by folding the user's uncaptured hand-edits into their MOD.md and re-applying it to fresh upstream, diff-gated before each render goes live. Use when the user says \"update\" or \"upgrade\" — the whole kit or one capability — or after a git pull of the aos upstream clone. Do NOT use for a capability that is not installed yet (that is capability-install) or to change what a capability does for this user (capability-evolve); this skill preserves existing personalization rather than adding any.","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\u002Fupgrade\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: upgrade\ndescription: \"Upgrades installed aos capabilities by folding the user's uncaptured hand-edits into their MOD.md and re-applying it to fresh upstream, diff-gated before each render goes live. Use when the user says \\\"update\\\" or \\\"upgrade\\\" — the whole kit or one capability — or after a git pull of the aos upstream clone. Do NOT use for a capability that is not installed yet (that is capability-install) or to change what a capability does for this user (capability-evolve); this skill preserves existing personalization rather than adding any.\"\n---\n\n# capability-upgrade\n\nNot in context yet? Load the `capability-lifecycle` skill first — the map, the\ncontract, the overlay doctrine, and the Experience rules. The model: **MOD.md states\nthe user's deltas; upgrade = re-apply them to fresh upstream, into\n`\u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>\u002F`.**\nThe current install is a drift source, never a merge input; the review gate is a diff of\nthe live render against the staged one, and only `aos-cap swap` puts a render live.\n\n1. Scope: the named capability, else every entry in `aos-cap list`.\n2. Kit-wide: pull `\u003Caos_home>\u002Fupstream` from the canonical remote (`git pull\n   upstream main` when an `upstream` remote exists, else `git pull`) — it cannot touch\n   `personal\u002F`, a different repo. On a non-`main` branch (a contributor dogfooding a\n   change, or a self-drafted cheat-sheet branch): skip the pull, say so, name the\n   branch, and say how to resume upstream updates\n   (`git -C \u003Caos_home>\u002Fupstream switch main`). A capability\n   needs work when its manifest version (`aos-cap manifest`) ≠ its lockfile version.\n   Migration note: overlay files found *inside* the clone (a pre-household install) →\n   offer the one-time move into `personal\u002F` before anything else. Referenced third-party\n   skills come along: for each recorded link into `\u003Caos_home>\u002Fvendor`, `git -C \u003Cvendor-clone>\n   pull --ff-only` (or the harness's plugin update), then re-`record` so the hashes match.\n   Offline or a dirty clone → say so and continue; a stale reference is never a blocker.\n   **Renders still in `personal\u002F`** (a household from before capability-lifecycle 0.7.0:\n   `aos-cap migrate rendered` lists moves) → upgrade `capability-lifecycle` alone first,\n   with the skill you have, then reload this skill and run the migration before anything\n   else — every later render goes to `rendered\u002F`, and the tool refuses an `--out` under\n   `personal\u002F`:\n   1. **Plan.** `aos-cap migrate rendered --scan \u003Charness home>…` with each harness home\n      and each `--ignore` glob of its skip list the cheat-sheet names. It writes nothing\n      but its state — the scan set and the old renders — which the next two steps read. Show the user the whole plan —\n      moves, link re-points, the text the copy rewrites, drift, outside references — and\n      get approval. Fold any drift first (step 3a); `--apply` refuses while any remains.\n      A recorded link that is missing or re-pointed may be the user's own change — a skill\n      taken back from a profile others can reach. Ask before re-creating it; the other fix\n      is to re-record the entry without it.\n   2. **Apply.** First pause any agent whose hook compares paths (a command wall), and\n      wait out a live guest session on it: between this step and the hook switch, its\n      walls would refuse legitimate work. Then `aos-cap migrate rendered --apply`. It copies\n      each render, re-points every link and rewrites the lockfile. The old renders stay in\n      place, so every old path still resolves.\n   3. **Fix each outside reference through its owner.** A `MOD.md` answer goes through\n      {{skill: evolve}}. One of the user's own packages that bakes the path gets the edit in\n      its source, then a re-render through staging and the gate. A harness file is changed\n      through the cheat-sheet's steps — its CLI, and only the consent file it names. A hook\n      is its own gate: show the user the old and new exact command and the approval you\n      will write, and wait. Then re-approve it by its new exact command before the config\n      points at it, check it, and revoke the old approval (the cheat-sheet's order). Change\n      hooks last, once their scripts are final.\n   4. **Prove the gates before anything old goes.** Run every security plugin's and\n      wall's own synthetic check against the new copies. Restart the harness, with the\n      user's go-ahead, once its work is idle, and confirm each plugin loaded from its\n      re-pointed link (the cheat-sheet's check). On any failure, re-point that link back:\n      its old render is still there.\n   5. **Finish.** `aos-cap migrate rendered --finish` refuses while anything still names\n      an old render path or links into one, and otherwise sends the old renders to the\n      trash. Resume what you paused, then commit `personal\u002F` (dated message) — the\n      renders' removal from it is that commit.\n3. Per capability needing work:\n   a. `aos-cap verify \u003Cid>` — two classes, two responses. *Artifact drift*\n      (a render file's hash changed = the user's hand-edit) → fold each into\n      MOD.md first per the `capability-lifecycle` skill's `reference\u002Foverlay.md` (edit the\n      statement that covers it — never\n      append a contradicting one) (\"you changed X — keeping it\").\n      *Link damage* (`MISSING LINK`, `NOT A LINK (copies are banned)`, `RELINKED`,\n      `DANGLING LINK`) is not a hand-edit and never folds: re-create the link from the\n      lockfile's recorded target, say what you repaired, and stop if the target itself\n      is gone (that is a broken install, not an upgrade). A\n      fold that reaches beyond the `{{mod}}` slots is mechanism-shaped — note it for\n      the promotion judgment (overlay.md, Promote and retire), end of conversation.\n   b. Name gate: `aos-cap --home \u003Caos_home> skills \u003Cdir> --check --harness-skills \u003Cdir> …`\n      (one `--harness-skills` per skills dir this harness reads). Upstream may have renamed or added a skill, so the installed\n      names can differ from the recorded links — a rename means link the new name and drop\n      the old one in step d. Exit 17 → stop and report; never rename locally. This\n      capability's own links are exempt, so a plain re-render is always clean. If it ships\n      `agents\u002F`, gate those too in the same breath: `aos-cap --home \u003Caos_home> agents \u003Cdir>\n      --check` — same flat namespace, same exit 17, same never-rename-locally. It checks\n      two of three sources and names the third (agents already in the harness — no\n      enumeration yet) in capitals.\n   c. **Re-render into staging.** A `.staging\u002F\u003Cid>` left by an abandoned gate goes first:\n      `aos-cap discard \u003Cid>`. Then `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). Then apply fresh upstream × this capability's MOD.md\n      (the `capability-lifecycle` skill's `reference\u002Foverlay.md`, Which MOD.md) — the same\n      transform as install, household rules included — to the staged copy. Interview only\n      new or `re_ask` questions. A household path you bake names `rendered\u002F\u003Cid>\u002F`, never\n      `.staging\u002F`. A skill whose installed name changed is simply absent from the staged\n      tree, and the gate shows it as removed. Then STAGE any native-plan changes per the\n      cheat-sheet (load it now if not in context).\n   d. GATE: `diff -ruN -x __pycache__ -x '*.pyc' \u003Caos_home>\u002Frendered\u002F\u003Cid>\n      \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>` — the live render against the staged one, per\n      file. It shows files the re-render added and files it dropped, including any file\n      the user added by hand inside the live render. Bytecode is left out: a live render\n      grows it as it runs. Show it with the native plan. Approve → `aos-cap swap \u003Cid>`: the\n      staged render goes live and the old one goes to the OS trash. Decline →\n      `aos-cap discard \u003Cid>`, and stop; the live render is untouched.\n   e. **Re-install the capability's own tool if it ships one**, before recording:\n      `uv tool install --force --from \u003Cdir>\u002Ftool \u003Cpackage>`. Nothing else in this flow updates\n      a binary, and `uv` will otherwise serve whatever it has cached — so an upgrade that\n      re-renders every skill can leave the executable those skills call several versions\n      behind, with the prose describing behaviour the binary does not have. `--force` is what\n      makes it re-resolve; the version in the tool's `pyproject.toml` tracks the capability's,\n      so a bumped capability is a bumped package.\n   f. **Reconcile links, then EXECUTE.** Compare the entry's recorded `links` and\n      `uses_links` with what the fresh manifest declares — each skill's `used_by`, each\n      `uses` row — plus the contract's default for an agent only the user talks to, the\n      cheat-sheet's standing links, and any link a MOD statement sanctions. Declared but missing → stage it. Recorded but not\n      declared → show it and ask; **never drop or move a link silently** — that is how a\n      provider's upgrade once broke a consumer for weeks. Another entry's `uses_links` into\n      this capability's render are that entry's: never touch them. A link this entry\n      records that another capability's `uses` now declares moves to that capability:\n      re-record this entry without it first, then the other with `--uses-link` (exit 19\n      enforces the order). Then EXECUTE the native plan (links survive a swap\n      untouched, because the path is the same — verify, don't assume); a hook whose command or script changed must be\n      re-approved and re-verified per the cheat-sheet — the consent was for the old one.\n      `aos-cap record \u003Cid>` with the full updated set\n      (start from `aos-cap show` — `record` replaces the entry wholesale, never call it\n      with a partial list; keep `--source-root`, `--link` and `--uses-link` records), then\n      `aos-cap verify` with no argument, so a link another entry depends on is checked\n      too.\n   g. Retirement pass (overlay.md, Promote and retire): fresh upstream now\n      covers a MOD statement — a new interview question over its subject, or the\n      behavior baked in → offer to retire it (diff-shown; written only through\n      {{skill: evolve}}).\n4. **Absorbed capabilities.** A lockfile entry whose capability no longer exists upstream\n   was folded into another one (0.3.0 absorbed `onboarding`, `importer`, and\n   `capability-builder` into `capability-lifecycle`). Say what happened, then: unlink that\n   entry's skill links, `aos-cap remove \u003Cabsorbed-id>`, and let the absorbing capability's\n   own upgrade render the replacements. Retired context-block markers\n   (`aos:onboarding@…`, `aos:capability-builder@…`) come out in the same pass — the\n   mode-boundary block carries its own marker. A pre-0.3.0 install also has an identity\n   block distilled from the global MOD: remove it, say why (the harness owns user context;\n   `MOD.md` remains the authoritative store), and write nothing in its place. `MOD.md` files never move on their own: if the absorbing\n   capability's interview covers the same questions, offer the merge; otherwise leave the\n   file and say it is now unused.\n5. Report per capability: upstream changes taken, MOD statements re-applied, statements\n   retired, anything folded in step a, any skill renamed or capability absorbed — and at\n   most one promotion offer, if a fold qualified.\n","# capability-upgrade\n\nNot in context yet? Load the `capability-lifecycle` skill first — the map, the\ncontract, the overlay doctrine, and the Experience rules. The model: **MOD.md states\nthe user's deltas; upgrade = re-apply them to fresh upstream, into\n`\u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>\u002F`.**\nThe current install is a drift source, never a merge input; the review gate is a diff of\nthe live render against the staged one, and only `aos-cap swap` puts a render live.\n\n1. Scope: the named capability, else every entry in `aos-cap list`.\n2. Kit-wide: pull `\u003Caos_home>\u002Fupstream` from the canonical remote (`git pull\n   upstream main` when an `upstream` remote exists, else `git pull`) — it cannot touch\n   `personal\u002F`, a different repo. On a non-`main` branch (a contributor dogfooding a\n   change, or a self-drafted cheat-sheet branch): skip the pull, say so, name the\n   branch, and say how to resume upstream updates\n   (`git -C \u003Caos_home>\u002Fupstream switch main`). A capability\n   needs work when its manifest version (`aos-cap manifest`) ≠ its lockfile version.\n   Migration note: overlay files found *inside* the clone (a pre-household install) →\n   offer the one-time move into `personal\u002F` before anything else. Referenced third-party\n   skills come along: for each recorded link into `\u003Caos_home>\u002Fvendor`, `git -C \u003Cvendor-clone>\n   pull --ff-only` (or the harness's plugin update), then re-`record` so the hashes match.\n   Offline or a dirty clone → say so and continue; a stale reference is never a blocker.\n   **Renders still in `personal\u002F`** (a household from before capability-lifecycle 0.7.0:\n   `aos-cap migrate rendered` lists moves) → upgrade `capability-lifecycle` alone first,\n   with the skill you have, then reload this skill and run the migration before anything\n   else — every later render goes to `rendered\u002F`, and the tool refuses an `--out` under\n   `personal\u002F`:\n   1. **Plan.** `aos-cap migrate rendered --scan \u003Charness home>…` with each harness home\n      and each `--ignore` glob of its skip list the cheat-sheet names. It writes nothing\n      but its state — the scan set and the old renders — which the next two steps read. Show the user the whole plan —\n      moves, link re-points, the text the copy rewrites, drift, outside references — and\n      get approval. Fold any drift first (step 3a); `--apply` refuses while any remains.\n      A recorded link that is missing or re-pointed may be the user's own change — a skill\n      taken back from a profile others can reach. Ask before re-creating it; the other fix\n      is to re-record the entry without it.\n   2. **Apply.** First pause any agent whose hook compares paths (a command wall), and\n      wait out a live guest session on it: between this step and the hook switch, its\n      walls would refuse legitimate work. Then `aos-cap migrate rendered --apply`. It copies\n      each render, re-points every link and rewrites the lockfile. The old renders stay in\n      place, so every old path still resolves.\n   3. **Fix each outside reference through its owner.** A `MOD.md` answer goes through\n      {{skill: evolve}}. One of the user's own packages that bakes the path gets the edit in\n      its source, then a re-render through staging and the gate. A harness file is changed\n      through the cheat-sheet's steps — its CLI, and only the consent file it names. A hook\n      is its own gate: show the user the old and new exact command and the approval you\n      will write, and wait. Then re-approve it by its new exact command before the config\n      points at it, check it, and revoke the old approval (the cheat-sheet's order). Change\n      hooks last, once their scripts are final.\n   4. **Prove the gates before anything old goes.** Run every security plugin's and\n      wall's own synthetic check against the new copies. Restart the harness, with the\n      user's go-ahead, once its work is idle, and confirm each plugin loaded from its\n      re-pointed link (the cheat-sheet's check). On any failure, re-point that link back:\n      its old render is still there.\n   5. **Finish.** `aos-cap migrate rendered --finish` refuses while anything still names\n      an old render path or links into one, and otherwise sends the old renders to the\n      trash. Resume what you paused, then commit `personal\u002F` (dated message) — the\n      renders' removal from it is that commit.\n3. Per capability needing work:\n   a. `aos-cap verify \u003Cid>` — two classes, two responses. *Artifact drift*\n      (a render file's hash changed = the user's hand-edit) → fold each into\n      MOD.md first per the `capability-lifecycle` skill's `reference\u002Foverlay.md` (edit the\n      statement that covers it — never\n      append a contradicting one) (\"you changed X — keeping it\").\n      *Link damage* (`MISSING LINK`, `NOT A LINK (copies are banned)`, `RELINKED`,\n      `DANGLING LINK`) is not a hand-edit and never folds: re-create the link from the\n      lockfile's recorded target, say what you repaired, and stop if the target itself\n      is gone (that is a broken install, not an upgrade). A\n      fold that reaches beyond the `{{mod}}` slots is mechanism-shaped — note it for\n      the promotion judgment (overlay.md, Promote and retire), end of conversation.\n   b. Name gate: `aos-cap --home \u003Caos_home> skills \u003Cdir> --check --harness-skills \u003Cdir> …`\n      (one `--harness-skills` per skills dir this harness reads). Upstream may have renamed or added a skill, so the installed\n      names can differ from the recorded links — a rename means link the new name and drop\n      the old one in step d. Exit 17 → stop and report; never rename locally. This\n      capability's own links are exempt, so a plain re-render is always clean. If it ships\n      `agents\u002F`, gate those too in the same breath: `aos-cap --home \u003Caos_home> agents \u003Cdir>\n      --check` — same flat namespace, same exit 17, same never-rename-locally. It checks\n      two of three sources and names the third (agents already in the harness — no\n      enumeration yet) in capitals.\n   c. **Re-render into staging.** A `.staging\u002F\u003Cid>` left by an abandoned gate goes first:\n      `aos-cap discard \u003Cid>`. Then `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). Then apply fresh upstream × this capability's MOD.md\n      (the `capability-lifecycle` skill's `reference\u002Foverlay.md`, Which MOD.md) — the same\n      transform as install, household rules included — to the staged copy. Interview only\n      new or `re_ask` questions. A household path you bake names `rendered\u002F\u003Cid>\u002F`, never\n      `.staging\u002F`. A skill whose installed name changed is simply absent from the staged\n      tree, and the gate shows it as removed. Then STAGE any native-plan changes per the\n      cheat-sheet (load it now if not in context).\n   d. GATE: `diff -ruN -x __pycache__ -x '*.pyc' \u003Caos_home>\u002Frendered\u002F\u003Cid>\n      \u003Caos_home>\u002Frendered\u002F.staging\u002F\u003Cid>` — the live render against the staged one, per\n      file. It shows files the re-render added and files it dropped, including any file\n      the user added by hand inside the live render. Bytecode is left out: a live render\n      grows it as it runs. Show it with the native plan. Approve → `aos-cap swap \u003Cid>`: the\n      staged render goes live and the old one goes to the OS trash. Decline →\n      `aos-cap discard \u003Cid>`, and stop; the live render is untouched.\n   e. **Re-install the capability's own tool if it ships one**, before recording:\n      `uv tool install --force --from \u003Cdir>\u002Ftool \u003Cpackage>`. Nothing else in this flow updates\n      a binary, and `uv` will otherwise serve whatever it has cached — so an upgrade that\n      re-renders every skill can leave the executable those skills call several versions\n      behind, with the prose describing behaviour the binary does not have. `--force` is what\n      makes it re-resolve; the version in the tool's `pyproject.toml` tracks the capability's,\n      so a bumped capability is a bumped package.\n   f. **Reconcile links, then EXECUTE.** Compare the entry's recorded `links` and\n      `uses_links` with what the fresh manifest declares — each skill's `used_by`, each\n      `uses` row — plus the contract's default for an agent only the user talks to, the\n      cheat-sheet's standing links, and any link a MOD statement sanctions. Declared but missing → stage it. Recorded but not\n      declared → show it and ask; **never drop or move a link silently** — that is how a\n      provider's upgrade once broke a consumer for weeks. Another entry's `uses_links` into\n      this capability's render are that entry's: never touch them. A link this entry\n      records that another capability's `uses` now declares moves to that capability:\n      re-record this entry without it first, then the other with `--uses-link` (exit 19\n      enforces the order). Then EXECUTE the native plan (links survive a swap\n      untouched, because the path is the same — verify, don't assume); a hook whose command or script changed must be\n      re-approved and re-verified per the cheat-sheet — the consent was for the old one.\n      `aos-cap record \u003Cid>` with the full updated set\n      (start from `aos-cap show` — `record` replaces the entry wholesale, never call it\n      with a partial list; keep `--source-root`, `--link` and `--uses-link` records), then\n      `aos-cap verify` with no argument, so a link another entry depends on is checked\n      too.\n   g. Retirement pass (overlay.md, Promote and retire): fresh upstream now\n      covers a MOD statement — a new interview question over its subject, or the\n      behavior baked in → offer to retire it (diff-shown; written only through\n      {{skill: evolve}}).\n4. **Absorbed capabilities.** A lockfile entry whose capability no longer exists upstream\n   was folded into another one (0.3.0 absorbed `onboarding`, `importer`, and\n   `capability-builder` into `capability-lifecycle`). Say what happened, then: unlink that\n   entry's skill links, `aos-cap remove \u003Cabsorbed-id>`, and let the absorbing capability's\n   own upgrade render the replacements. Retired context-block markers\n   (`aos:onboarding@…`, `aos:capability-builder@…`) come out in the same pass — the\n   mode-boundary block carries its own marker. A pre-0.3.0 install also has an identity\n   block distilled from the global MOD: remove it, say why (the harness owns user context;\n   `MOD.md` remains the authoritative store), and write nothing in its place. `MOD.md` files never move on their own: if the absorbing\n   capability's interview covers the same questions, offer the merge; otherwise leave the\n   file and say it is now unused.\n5. Report per capability: upstream changes taken, MOD statements re-applied, statements\n   retired, anything folded in step a, any skill renamed or capability absorbed — and at\n   most one promotion offer, if a fold qualified.\n",{"name":5,"description":7},"main","31f4199ef67a0cedbdab2404eb9012d0c6e60c79","capabilities\u002Fcapability-lifecycle\u002Fskills\u002Fupgrade",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 upgrade",{"tool":39,"command":40},"bunx","bunx skills add AlmogBaku\u002Faos --skill upgrade",{"tool":42,"command":43},"pnpm","pnpm dlx skills add AlmogBaku\u002Faos --skill upgrade","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAlmogBaku\u002Faos\u002Fblob\u002Fmain\u002Fcapabilities\u002Fcapability-lifecycle\u002Fskills\u002Fupgrade\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",[],[]]