[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79D4HENCF44NASV6NJX2434":3,"skill-same:01M79D4HENCF44NASV6NJX2434":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79D4HENCF44NASV6NJX2434","task-and-project",null,"Track work as Tasks (the \u002Fapi\u002Ftasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.","PersonalClaw\u002FPersonalClaw","PersonalClaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F306824595?v=4","01M79D0KNQCPQXVH30C5PREVCW","01M79D0KPT5XDNEAW87TEYQW3V",9,"MIT","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Fsrc\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Ftask-and-project\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: task-and-project\ndescription: Track work as Tasks (the \u002Fapi\u002Ftasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.\nalways: false\ntriggers: task, tasks, create a task, track work, project, decompose, break down, plan the work, parallelize, work breakdown, goal loop, autonomous, organize work\n---\n\n# Tasks & Projects\n\nBigger work is delivered by **decomposing** it into small, independently\nverifiable units, **tracking** those units as Tasks, and then executing them —\nsome inline, some in parallel, some as an autonomous goal-driven loop.\n\n## Tasks — the unit of tracked work\n\nA **Task** is a tracked, persisted unit of work with a title, description,\nstatus, and dependency links. Tasks live in the Tasks entity, backed by the\nnative task provider and exposed over the `\u002Fapi\u002Ftasks` CRUD:\n\n- `GET \u002Fapi\u002Ftasks` \u002F `GET \u002Fapi\u002Ftasks\u002F{task_id}` — list \u002F fetch.\n- `POST \u002Fapi\u002Ftasks` — create a task.\n- `PATCH \u002Fapi\u002Ftasks\u002F{task_id}` — update title, description, or status.\n- `DELETE \u002Fapi\u002Ftasks\u002F{task_id}` — remove a task.\n- `GET \u002Fapi\u002Ftasks\u002F{task_id}\u002Fcomments` \u002F `POST` — task discussion.\n- `GET \u002Fapi\u002Ftasks\u002Fgraph` — the dependency graph (which tasks block which).\n\nThe dashboard Tasks page is the primary surface — create, organize, and watch\nstatus there. Use Tasks to make a decomposition **visible and durable**: one\ntask per atomic unit, dependencies recorded, status updated as work progresses\nso nothing is dropped.\n\n## Project decomposition discipline\n\nBefore executing anything non-trivial, **decompose**:\n\n1. **State the outcome** in one sentence — what \"done\" looks like for the whole\n   project.\n2. **Break it into atomic units** — each unit independently doable and\n   independently verifiable. If a unit can't be checked on its own, it's still\n   too big; split it. Record each as a **Task**.\n3. **Map dependencies** — which units block which. Independent units can run in\n   parallel; dependent ones must be sequenced. Record the edges in the task\n   graph so the order is explicit.\n4. **Assign an execution mode per unit:**\n   - trivial \u002F fast \u002F shared-context → do it **inline**.\n   - independent investigation or an isolated long task → `subagent_run`\n     (parallelize the independent ones).\n   - open-ended \"grind until the goal is met\" → a **goal loop** (see below).\n5. **Keep one coherent plan** — track units and their state as Tasks so progress\n   is visible. Integrate results back into the whole as units complete; don't\n   just accumulate fragments.\n\n## Goal loops — autonomous execution toward a goal\n\nWhen the work is **open-ended toward a definition of done** — \"grind on this\nuntil it's met\", a continuous-improvement target, a north-star objective — hand\nit to a **goal loop** rather than driving it step-by-step yourself. A goal loop\nclassifies the target, decomposes it, then runs one self-directed cycle per turn\nuntil a deterministic supervisor (or a separate judge) decides the goal is met,\nat which point it self-retires. Goal loops are the unified autonomous goal\nengine; manage them from the dashboard Goal Loops page. The per-cycle worker\nprotocol lives in the `loop-worker` skill.\n\nUse a goal loop instead of trying to specify every step up front: you set the\ngoal and the definition of done, the loop decides direction each cycle.\n\n## Parallel work with subagents\n\nWhen several units are **independent** (no shared mutable state, no ordering\ndependency), run them concurrently with `subagent_run` — e.g. investigate three\ncandidate root causes at once, or research several sub-questions in parallel —\nthen synthesize the returns. Keep each subagent's task self-contained with its\nown clear deliverable so the results compose cleanly. (See `delegation` for the\nspawn-vs-inline cost rule — don't spawn for trivial work.)\n\n## Discipline\n\n- **One unit = one verifiable step.** Resist doing \"the whole thing\" in a single\n  uncontrolled pass.\n- **Define done before starting** — for the project and for each unit.\n- **Track it as a Task** — a unit that isn't recorded gets dropped.\n- **Don't fan out work that shares mutable state** — parallel workers stepping on\n  the same files race. Parallelize only genuinely independent units.\n- **Re-plan when reality diverges** — if a unit reveals the breakdown was wrong,\n  update the plan and the tasks rather than forcing the old one.\n","# Tasks & Projects\n\nBigger work is delivered by **decomposing** it into small, independently\nverifiable units, **tracking** those units as Tasks, and then executing them —\nsome inline, some in parallel, some as an autonomous goal-driven loop.\n\n## Tasks — the unit of tracked work\n\nA **Task** is a tracked, persisted unit of work with a title, description,\nstatus, and dependency links. Tasks live in the Tasks entity, backed by the\nnative task provider and exposed over the `\u002Fapi\u002Ftasks` CRUD:\n\n- `GET \u002Fapi\u002Ftasks` \u002F `GET \u002Fapi\u002Ftasks\u002F{task_id}` — list \u002F fetch.\n- `POST \u002Fapi\u002Ftasks` — create a task.\n- `PATCH \u002Fapi\u002Ftasks\u002F{task_id}` — update title, description, or status.\n- `DELETE \u002Fapi\u002Ftasks\u002F{task_id}` — remove a task.\n- `GET \u002Fapi\u002Ftasks\u002F{task_id}\u002Fcomments` \u002F `POST` — task discussion.\n- `GET \u002Fapi\u002Ftasks\u002Fgraph` — the dependency graph (which tasks block which).\n\nThe dashboard Tasks page is the primary surface — create, organize, and watch\nstatus there. Use Tasks to make a decomposition **visible and durable**: one\ntask per atomic unit, dependencies recorded, status updated as work progresses\nso nothing is dropped.\n\n## Project decomposition discipline\n\nBefore executing anything non-trivial, **decompose**:\n\n1. **State the outcome** in one sentence — what \"done\" looks like for the whole\n   project.\n2. **Break it into atomic units** — each unit independently doable and\n   independently verifiable. If a unit can't be checked on its own, it's still\n   too big; split it. Record each as a **Task**.\n3. **Map dependencies** — which units block which. Independent units can run in\n   parallel; dependent ones must be sequenced. Record the edges in the task\n   graph so the order is explicit.\n4. **Assign an execution mode per unit:**\n   - trivial \u002F fast \u002F shared-context → do it **inline**.\n   - independent investigation or an isolated long task → `subagent_run`\n     (parallelize the independent ones).\n   - open-ended \"grind until the goal is met\" → a **goal loop** (see below).\n5. **Keep one coherent plan** — track units and their state as Tasks so progress\n   is visible. Integrate results back into the whole as units complete; don't\n   just accumulate fragments.\n\n## Goal loops — autonomous execution toward a goal\n\nWhen the work is **open-ended toward a definition of done** — \"grind on this\nuntil it's met\", a continuous-improvement target, a north-star objective — hand\nit to a **goal loop** rather than driving it step-by-step yourself. A goal loop\nclassifies the target, decomposes it, then runs one self-directed cycle per turn\nuntil a deterministic supervisor (or a separate judge) decides the goal is met,\nat which point it self-retires. Goal loops are the unified autonomous goal\nengine; manage them from the dashboard Goal Loops page. The per-cycle worker\nprotocol lives in the `loop-worker` skill.\n\nUse a goal loop instead of trying to specify every step up front: you set the\ngoal and the definition of done, the loop decides direction each cycle.\n\n## Parallel work with subagents\n\nWhen several units are **independent** (no shared mutable state, no ordering\ndependency), run them concurrently with `subagent_run` — e.g. investigate three\ncandidate root causes at once, or research several sub-questions in parallel —\nthen synthesize the returns. Keep each subagent's task self-contained with its\nown clear deliverable so the results compose cleanly. (See `delegation` for the\nspawn-vs-inline cost rule — don't spawn for trivial work.)\n\n## Discipline\n\n- **One unit = one verifiable step.** Resist doing \"the whole thing\" in a single\n  uncontrolled pass.\n- **Define done before starting** — for the project and for each unit.\n- **Track it as a Task** — a unit that isn't recorded gets dropped.\n- **Don't fan out work that shares mutable state** — parallel workers stepping on\n  the same files race. Parallelize only genuinely independent units.\n- **Re-plan when reality diverges** — if a unit reveals the breakdown was wrong,\n  update the plan and the tasks rather than forcing the old one.\n",{"name":5,"always":19,"triggers":23,"description":7},"task, tasks, create a task, track work, project, decompose, break down, plan the work, parallelize, work breakdown, goal loop, autonomous, organize work","main","cfba933d376f99978247a7d18b592232c649e87a","src\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Ftask-and-project",6,"https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw","https:\u002F\u002Fpersonalclaw.dev","https:\u002F\u002Fgithub.com\u002FPersonalClaw","Self-hosted personal AI agent — an agentic OS for one person: chat, goal loops, memory, knowledge, automation, apps. Local-first, zero telemetry, MIT.","2026-11-15 04:04:52",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add PersonalClaw\u002FPersonalClaw --skill task-and-project",{"tool":39,"command":40},"bunx","bunx skills add PersonalClaw\u002FPersonalClaw --skill task-and-project",{"tool":42,"command":43},"pnpm","pnpm dlx skills add PersonalClaw\u002FPersonalClaw --skill task-and-project","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Fsrc\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Ftask-and-project\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":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M79D5S4EBPTFGMRDY7AM7ERD","ledger-read","Read a ledger CSV","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal_formats_golden\u002Fskill-md\u002Fskills\u002Fledger-read\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M79D5QFEBGM2PTM21WVTA90K","budget-coach","Weekly spend review","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal_formats_golden\u002Fskill-md\u002Fskills\u002Fbudget-coach\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M79D5MTEV62YBKTNY874Y9C4","yt-transcript","Fetch the transcript of a YouTube video and summarise it with timestamps. Use when the user shares a youtube.com or youtu.be link and asks what it says.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Fyt-transcript\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M79D5JG2M47DS0X3GRZ94PXY","incident-writeup","Turn my incident notes, Slack excerpts and graphs into a blameless postmortem in Cartwheel's format. Use after an on-call incident once the mitigation is in.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Fincident-writeup\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M79D5DX9SWDFDAFW3AD5FATT","feedsmith-release","Cut a feedsmith release - bump the version, move the Unreleased changelog section, tag, and draft the GitHub release notes. Use when I say \"release feedsmith\" or \"cut 0.x\".","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Ffeedsmith-release\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M79D59Z7A0FEZSB5AEQYHNSR","feedsmith-bench","Benchmark feedsmith fetch against a real OPML, cold and warm, and compare with main. Use before merging anything that touches fetch.py or store.py.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_homes\u002Fnoor\u002F.codex\u002Fskills\u002Ffeedsmith-bench\u002FSKILL.md",[],[]]