[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RWH7HCJG1WD66EASS210P":3,"skill-same:01M79RWH7HCJG1WD66EASS210P":52},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79RWH7HCJG1WD66EASS210P","tk-studio-job",null,"Run declared jobs on the harness's own scheduling primitives — submit, status, cancel, and wake per the driver contract, with budget guards and stop conditions enforced. Use when the user says \"submit a job\", \"tk job\", \"job status\", \"cancel that job\", or wants recurring\u002Funattended work scheduled.","thkennedy\u002Ftk-studio","thkennedy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4164502?v=4","01M79QZ8DMP5FF2HC6GS3S6FDF","Tim Kennedy","01M79QZ8EM9JBWJ15R5JNC4PW3",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-job\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tk-studio-job\ndescription: Run declared jobs on the harness's own scheduling primitives — submit, status, cancel, and wake per the driver contract, with budget guards and stop conditions enforced. Use when the user says \"submit a job\", \"tk job\", \"job status\", \"cancel that job\", or wants recurring\u002Funattended work scheduled.\n---\n\n# tk-studio-job\n\nJobs are data (contracts\u002Fjob.schema.json, ST-6.1); this skill is the\nexecution wrapper (AD-10, O8 hybrid): it drives the §4 scheduler verbs and\nbinds recurring work to whatever the *harness* natively offers — scheduled\ntasks\u002Fcron for `cron` triggers, loop primitives for fixed `loop` cadence,\nself-paced wakeups for `self-paced` — never a bespoke runner. Run state\nlives in resumable run workspaces under the per-user store.\n\n## Behavior (both modes)\n\n1. Every verb goes through the deterministic core (the one §4 surface):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" submit  --directory \u003Croot> --id \u003Cjob-id>\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" status  --directory \u003Croot> --job-id \u003Cid> [--run-id \u003Crid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" resolve --directory \u003Croot> [--job-id \u003Cid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" cancel  --directory \u003Croot> --job-id \u003Cid> [--run-id \u003Crid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" wake    --directory \u003Croot> --job-id \u003Cid>\n   ```\n\n   `submit` validates (a job missing guards or stop conditions is rejected,\n   `accepted: false`), gates on stop conditions, and answers with a\n   **directive**. Core-target one-shots execute immediately, wall-clock\n   guarded. An `accepted`\u002F`woken` `false` is an answer — relay the reason.\n   `resolve` is read-only: it serves every declared job (or one, by id)\n   **fully resolved** — type extension applied by the one resolver — so a\n   substrate-side driver classifies recurring work from the trigger\u002Fcadence\n   served here and never raw-reads `.tk-studio\u002Fjobs\u002F\u003Cid>.json` (PROP-008);\n   an entry's problems ride it named in place, an unknown id is a named\n   refusal.\n\n2. **Bind the directive to the harness.** `{\"kind\": \"cron\", \"schedule\": ...}`\n   → the harness's scheduled-task primitive; `{\"kind\": \"loop\", ...}` \u002F\n   `{\"kind\": \"self-paced\", ...}` → its loop\u002Fwakeup primitives; `{\"kind\":\n   \"invoke-skill\", ...}` → invoke the named skill with the payload, then\n   report the outcome with `finish`. Each firing of a recurring job is one\n   `wake`. An `invoke-skill` directive also names the run's\n   provisional-knowledge artifacts (`knowledge`: spine\u002Fseed paths with\n   `present` flags — the §4 KB-injection directive, contract 0.1.7):\n   inject each present artifact's contents into the segment you invoke.\n   Aid, not gate — an absent artifact never skips or fails the run.\n\n3. **Skill-target runs stay honest.** While executing an `invoke-skill`\n   directive, call `account --run-id \u003Crid> --turns 1 [--tokens N]` every\n   iteration; the moment it answers `within_budget: false`, end the run\n   `partial` with the guard named:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" finish --directory \u003Croot> --run-id \u003Crid> --state partial --reason \"guard: max_turns\"\n   ```\n\n   Pass `--total-cost-usd \u003Cusd>` to `finish` when the worker reports one\n   (its `--output-format json` result); omit it otherwise, never guess.\n   `finish` records the terminal state and emits the run's `job-run` event —\n   this wrapper alone emits job-level events; the target skill emits its own\n   surface events, never both for one failure (AD-12). Every terminal\n   transition also captures the run's handoff deltas into the per-project\n   reconciliation queue (ST-9.4, `lib\u002Freconcile.py` — deduped, idempotent,\n   per-user store only); the capture evidence rides `summary.json` and the\n   `finish` response, and a capture problem is recorded there, never a\n   failed verb. `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Freconcile.py\" route\n   --directory \u003Croot>` renders the routing doc beside the queue — a pure\n   render that applies nothing (promotion is ST-9.5's PR membrane).\n\n4. **Durability is surfaced, never silently lost.** A `durable: true`\n   recurring job on this session-scoped substrate gets a\n   `durability_constraint` in the submit response: relay it verbatim\n   (attended) or include it in the status block `reason` context (headless).\n   Bind durable jobs to a cloud routine or an external harness via the\n   driver contract; otherwise they must be re-submitted each session.\n\n5. **Attended:** confirm before binding schedules; summarize directive,\n   guards, and stop conditions. **Headless:** everything arrives in the\n   payload; an unknown job id or invalid definition ends `blocked`, a guard\n   or stop condition hit ends `partial` with the reason named — never a\n   prompt (AD-11). End headless runs with the status block:\n\n   ```json\n   {\"status\": \"complete\", \"intent\": \"tk-studio-job\", \"artifacts\": [\"~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Fruns\u002F\u003Crun-id>\u002F\"], \"reason\": null}\n   ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- The job model is data; never invent, widen, or hot-patch a definition —\n  instances live in `.tk-studio\u002Fjobs\u002F\u003Cid>.json`, listed in config `jobs[]`.\n- Guards and stop conditions are contracts, not suggestions: obey `account`\n  verdicts immediately; a job never runs away (AD-10).\n- Run workspaces are the resumable truth: a fresh session continues a\n  `queued|running` run from `run.json` alone (snapshot + checkpoint).\n- Every terminal run leaves `summary.json` in its workspace (core runs also\n  land the full parsed result as `output.json`); point the operator there,\n  never paste whole reports into chat.\n- Long work splits at declared boundaries (ST-6.6; surface:\n  `tk-studio-session`, ST-9.2): at an epic\u002Fstory\u002Fphase boundary or a budget\n  trigger, land the handoff and END the session —\n  `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fsession.py\" handoff --directory \u003Croot>\n  --run-id \u003Crid> --boundary \u003Ckind> --name \u003Cid> --done ... --next ...`\n  (optionally `--delta` corrections against the workspace seed); a fresh\n  session continues via `session.py resume` from the workspace alone,\n  never by replaying history. Ending the session never ends the run.\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n","# tk-studio-job\n\nJobs are data (contracts\u002Fjob.schema.json, ST-6.1); this skill is the\nexecution wrapper (AD-10, O8 hybrid): it drives the §4 scheduler verbs and\nbinds recurring work to whatever the *harness* natively offers — scheduled\ntasks\u002Fcron for `cron` triggers, loop primitives for fixed `loop` cadence,\nself-paced wakeups for `self-paced` — never a bespoke runner. Run state\nlives in resumable run workspaces under the per-user store.\n\n## Behavior (both modes)\n\n1. Every verb goes through the deterministic core (the one §4 surface):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" submit  --directory \u003Croot> --id \u003Cjob-id>\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" status  --directory \u003Croot> --job-id \u003Cid> [--run-id \u003Crid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" resolve --directory \u003Croot> [--job-id \u003Cid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" cancel  --directory \u003Croot> --job-id \u003Cid> [--run-id \u003Crid>]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" wake    --directory \u003Croot> --job-id \u003Cid>\n   ```\n\n   `submit` validates (a job missing guards or stop conditions is rejected,\n   `accepted: false`), gates on stop conditions, and answers with a\n   **directive**. Core-target one-shots execute immediately, wall-clock\n   guarded. An `accepted`\u002F`woken` `false` is an answer — relay the reason.\n   `resolve` is read-only: it serves every declared job (or one, by id)\n   **fully resolved** — type extension applied by the one resolver — so a\n   substrate-side driver classifies recurring work from the trigger\u002Fcadence\n   served here and never raw-reads `.tk-studio\u002Fjobs\u002F\u003Cid>.json` (PROP-008);\n   an entry's problems ride it named in place, an unknown id is a named\n   refusal.\n\n2. **Bind the directive to the harness.** `{\"kind\": \"cron\", \"schedule\": ...}`\n   → the harness's scheduled-task primitive; `{\"kind\": \"loop\", ...}` \u002F\n   `{\"kind\": \"self-paced\", ...}` → its loop\u002Fwakeup primitives; `{\"kind\":\n   \"invoke-skill\", ...}` → invoke the named skill with the payload, then\n   report the outcome with `finish`. Each firing of a recurring job is one\n   `wake`. An `invoke-skill` directive also names the run's\n   provisional-knowledge artifacts (`knowledge`: spine\u002Fseed paths with\n   `present` flags — the §4 KB-injection directive, contract 0.1.7):\n   inject each present artifact's contents into the segment you invoke.\n   Aid, not gate — an absent artifact never skips or fails the run.\n\n3. **Skill-target runs stay honest.** While executing an `invoke-skill`\n   directive, call `account --run-id \u003Crid> --turns 1 [--tokens N]` every\n   iteration; the moment it answers `within_budget: false`, end the run\n   `partial` with the guard named:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fjobrun.py\" finish --directory \u003Croot> --run-id \u003Crid> --state partial --reason \"guard: max_turns\"\n   ```\n\n   Pass `--total-cost-usd \u003Cusd>` to `finish` when the worker reports one\n   (its `--output-format json` result); omit it otherwise, never guess.\n   `finish` records the terminal state and emits the run's `job-run` event —\n   this wrapper alone emits job-level events; the target skill emits its own\n   surface events, never both for one failure (AD-12). Every terminal\n   transition also captures the run's handoff deltas into the per-project\n   reconciliation queue (ST-9.4, `lib\u002Freconcile.py` — deduped, idempotent,\n   per-user store only); the capture evidence rides `summary.json` and the\n   `finish` response, and a capture problem is recorded there, never a\n   failed verb. `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Freconcile.py\" route\n   --directory \u003Croot>` renders the routing doc beside the queue — a pure\n   render that applies nothing (promotion is ST-9.5's PR membrane).\n\n4. **Durability is surfaced, never silently lost.** A `durable: true`\n   recurring job on this session-scoped substrate gets a\n   `durability_constraint` in the submit response: relay it verbatim\n   (attended) or include it in the status block `reason` context (headless).\n   Bind durable jobs to a cloud routine or an external harness via the\n   driver contract; otherwise they must be re-submitted each session.\n\n5. **Attended:** confirm before binding schedules; summarize directive,\n   guards, and stop conditions. **Headless:** everything arrives in the\n   payload; an unknown job id or invalid definition ends `blocked`, a guard\n   or stop condition hit ends `partial` with the reason named — never a\n   prompt (AD-11). End headless runs with the status block:\n\n   ```json\n   {\"status\": \"complete\", \"intent\": \"tk-studio-job\", \"artifacts\": [\"~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Fruns\u002F\u003Crun-id>\u002F\"], \"reason\": null}\n   ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- The job model is data; never invent, widen, or hot-patch a definition —\n  instances live in `.tk-studio\u002Fjobs\u002F\u003Cid>.json`, listed in config `jobs[]`.\n- Guards and stop conditions are contracts, not suggestions: obey `account`\n  verdicts immediately; a job never runs away (AD-10).\n- Run workspaces are the resumable truth: a fresh session continues a\n  `queued|running` run from `run.json` alone (snapshot + checkpoint).\n- Every terminal run leaves `summary.json` in its workspace (core runs also\n  land the full parsed result as `output.json`); point the operator there,\n  never paste whole reports into chat.\n- Long work splits at declared boundaries (ST-6.6; surface:\n  `tk-studio-session`, ST-9.2): at an epic\u002Fstory\u002Fphase boundary or a budget\n  trigger, land the handoff and END the session —\n  `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fsession.py\" handoff --directory \u003Croot>\n  --run-id \u003Crid> --boundary \u003Ckind> --name \u003Cid> --done ... --next ...`\n  (optionally `--delta` corrections against the workspace seed); a fresh\n  session continues via `session.py resume` from the workspace alone,\n  never by replaying history. Ending the session never ends the run.\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n",{"name":5,"description":7},"main","ecd23b3c0458cd511812f643d9111e3d7c8235f4","plugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-job","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio","https:\u002F\u002Fgithub.com\u002Fthkennedy","https:\u002F\u002Ftimothyhkennedy.com","Just a guy who loves making tools, automation and games.","2026-11-10 20:38:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add thkennedy\u002Ftk-studio --skill tk-studio-job",{"tool":38,"command":39},"bunx","bunx skills add thkennedy\u002Ftk-studio --skill tk-studio-job",{"tool":41,"command":42},"pnpm","pnpm dlx skills add thkennedy\u002Ftk-studio --skill tk-studio-job","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-job\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"customize.toml","OTHER","其他",557,"https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-job\u002Fcustomize.toml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79RYSQ8C3MWDFTDSRAYFJYA","tk-studio-track","Tracking verbs on the bound Jira project — `block` moves a story the loop cannot progress, and each dependent story, to \"Blocked - Awaiting User\" with a comment that @mentions the owner (or, with `--engagement`, one engagement's questions issue, which `close` later moves to \"Done\"); `reply` posts the owner's answer (or \"Done.\") with the owner's host-only token and moves the issue to \"Block Resolved\"; `validate` checks that resolution and passes the issue back to work or re-blocks it with a follow-up. Use when the user says \"block this story\", \"tk track block\", \"put it in the owner's inbox\", \"reply to the blocked issue\", \"validate the resolution\", or a supervisor or engagement payload names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-track\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79RYMVE0031EV5B64MBGD8V","tk-studio-session","Session discipline as a surface — land a boundary handoff (optionally carrying knowledge deltas) and end the session, or resume a fresh session from a run workspace alone. Use when the user says \"hand off this run\", \"tk session\", \"resume the run\", or a boundary\u002Fbudget trigger says the session must split.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-session\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79RYFM9ATWHM6HAXJ3D19WV","tk-studio-research","Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79RYA1AWZZF83KBHGR6JDN3","tk-studio-report","One-verb human defect report — \"the skill did the wrong thing\" — recorded as a report event in the local measurement ledger. Use when the user says \"tk report\", \"report a defect\", \"that skill misbehaved\", or \"log a studio issue\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-report\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79RY33VMYR5YNPVFKWRNW9S","tk-studio-playable-judge","The playable-verify leg's screenshot judge (Story 34.3) — reads only a playable run's report.json and its frames, answers the fixed rubric (scene loaded, player visible and framed, no magenta or error overlay, HUD reads, the named moments shown) with pass or fail and findings each naming a frame and a rubric line. Driven headless by the supervisor's host leg on the project's sandbox tier; use when the payload names a playable `media` folder, or the user says \"judge the playable frames\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-playable-judge\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79RXY4AM8JM6ZK2MAR3W3X2","tk-studio-plan-sync","Planning adapter — canonicalize BMad-native planning artifacts (normalize pass, sole id authority) and sync them with the bound planning backend. Use when the user says \"sync the plan\", \"normalize planning artifacts\", \"tk plan sync\", or after stock BMad planning flows produce or change epics\u002Fstories.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-plan-sync\u002FSKILL.md",[],[]]