[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JW7EK0FYYMAW6QQ1F5AGA":3,"skill-same:01M71JW7EK0FYYMAW6QQ1F5AGA":73},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M71JW7EK0FYYMAW6QQ1F5AGA","goal",null,"Persistent project goal that survives across sessions and tools, with continuous-execution loop semantics. Use when someone asks to \"set a goal\", \"what is my goal\", \"goal status\", \"keep working on X until done\", \"resume the goal\", or wants work to continue across sessions until an objective is achieved. File-backed (.goal.md at project root); shared by every Coco-installed tool working in that repository.","coco-research\u002Fcoco","coco-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F68911604?v=4","01M71JRE9C4NM4NSZM4JD0BJTB","Coco Research","01M71JREA0ZMR0PMH3CKA99SN1",631,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fgoal\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"at","use","execution","sessions","continue","tool","Tools","my","status","repository","work","across","done","when","loop","Meta","project","SET","shared","2026-11-10 10:12:30",false,"---\nname: goal\ndescription: Persistent project goal that survives across sessions and tools, with continuous-execution loop semantics. Use when someone asks to \"set a goal\", \"what is my goal\", \"goal status\", \"keep working on X until done\", \"resume the goal\", or wants work to continue across sessions until an objective is achieved. File-backed (.goal.md at project root); shared by every Coco-installed tool working in that repository.\ndomain: meta\n---\n\n# Goal — persistent project objective\n\nA goal is a single objective the agent keeps pursuing across turns and\nsessions until it is marked done. Inspired by Prime Agent's thread goal:\nstate lives outside any one conversation, so any tool with this skill\ninstalled (Claude Code, Cursor, Codex, ...) picks up where another left off.\n\n## State file\n\nOne file per project: `.goal.md` in the repository root. Human-readable and\nhuman-editable on purpose — pause, resume, edit, and clear are controlled by\nthe user editing the file directly.\n\n```markdown\n---\nobjective: Ship release notes for v2.3\nstatus: active        # active | paused | done\ncreated: 2026-08-22\n---\n\n## Progress\n- 2026-08-22 14:02 — drafted changelog from git log\n```\n\nOptional sections the loop reads if present: `## Queue` (ordered work items),\n`## Standing constraints` (owner-set rules that bind every session),\n`## Decisions` (recorded owner calls — binding, never re-litigated),\n`## Done criteria`.\n\n## API\n\n- **get** — read `.goal.md`. No file means no goal is set. Report the\n  objective, status, and latest progress entries when asked about goal status.\n- **create(objective)** — write `.goal.md` with `status: active` and today's\n  date. If an `active` goal already exists, do NOT silently replace it; show\n  it and ask whether to complete, pause, or replace. Only create a goal when\n  the user explicitly asks for a persistent goal; do not infer goals from\n  ordinary tasks.\n- **update(note)** — append one dated line to `## Progress` after each\n  meaningful work session toward the goal. Keep notes short and factual.\n- **complete()** — set `status: done`. Only when the objective has actually\n  been achieved and no required work remains — not because the session is\n  ending or momentum ran out.\n\n## Session behavior\n\nAt the start of a session in a repo containing `.goal.md`:\n\n- `status: active` — surface the objective to the user, then ENTER THE WORK\n  LOOP below before starting unrelated work.\n- `status: paused` — mention it exists; resume only if the user asks.\n- `status: done` — leave it as history; offer to archive or replace.\n\n## Work loop (continuous execution)\n\nAn active goal with remaining actionable items means you run a LOOP, not a\nsingle pass. One iteration:\n\n1. **Resume** — read `.goal.md` plus the newest handoff document it references\n   (typically under `docs\u002Fplans\u002F`). Verify recorded receipts against reality\n   (HEAD sha, merged PRs, live state) before trusting them.\n2. **Pick** the highest-priority item that is actionable right now — from the\n   Queue, the referenced workorder, or the handoff's \"exact next action\".\n3. **Journal before acting** — append `TODO \u003Ctask>` to `## Progress`. If the\n   session dies here, a successor knows precisely what was attempted.\n4. **Execute** — do the work. Run the real gates. Commit\u002FPR per whatever\n   authority the goal grants (e.g., self-review-and-merge if so recorded).\n5. **Journal after** — append `DONE \u003Ctask> — \u003Creceipt>` immediately. Receipt =\n   commit sha, PR number, test counts, or posted artifact. No receipt, not done.\n6. **Repeat** from step 2 while an actionable item remains and no STOP\n   condition applies.\n\nNever end a turn with actionable items outstanding unless a STOP condition\nfired. \"Momentum ran out\" is not a stop condition.\n\n## Failure resilience\n\n- **Transient LLM\u002FAPI\u002Ftool failures** — timeouts, 429\u002F5xx, dropped\n  connections — are NEVER stop conditions. Retry with backoff (≈30s → 60s →\n  120s, cap ~5 attempts). If one dependency stays down, journal `BLOCKED \u003Citem>\n  — \u003Creason>`, switch to the next non-dependent actionable item, and circle back.\n- **Crash\u002Finterrupt safety**: because TODO precedes work and DONE follows it,\n  an interrupted session loses nothing. On resume, a task with TODO and no DONE\n  is simply not started yet — verify no half-committed debris, then restart it.\n- **Tool\u002Fenvironment failure ≠ task failure.** A failing gate gets diagnosed;\n  a failing external service gets routed around; neither ends the loop.\n- **Flaky tests** fail-then-pass-isolated are recorded as known-flaky, not\n  treated as regressions — but always rerun isolated before concluding that.\n\n## Stop conditions (the ONLY reasons to end the loop)\n\n1. **Done** — goal achieved; call `complete()`.\n2. **Blocked on owner** — every remaining item needs an answer only the owner\n   can give. Post the questions (one line each), mark items BLOCKED\u002FDEFERRED,\n   update `.goal.md`, stop with a clear summary of what you need.\n3. **Context limit approaching** — write the handoff document (see Handoff),\n   append the final Progress line, stop cleanly.\n4. **Repeated hard failure** — ≥3 consecutive unrecoverable failures across\n   DIFFERENT items (not retries of one) → write an incident note into Progress\n   and the handoff, stop, report to owner.\n\nEverything else — API flakiness, slow builds, flaky tests, waiting on a local\nservice — is worked through or routed around.\n\n## Handoff (graceful exit)\n\nIf the repo keeps committed plan\u002Fhandoff documents (e.g., `docs\u002Fplans\u002F`), the\ngraceful exit is: write\u002Fupdate the handoff file containing exact HEAD sha, PRs\nlanded this session, current queue position, receipts, known gotchas, and the\nexact next action — then append the final Progress line to `.goal.md`, then\nstop. Ending a session without those two writes is a defect: the successor\nmust be able to resume from `.goal.md` + the latest handoff alone.\n\n## Rules\n\n- One active goal per repository. The file is the source of truth — never keep\n  goal state only in conversation memory.\n- Never delete or rewrite past progress lines; append.\n- Completion must reflect reality. An agent that marks a half-finished goal\n  done defeats the entire mechanism.\n- Standing constraints and recorded decisions inside `.goal.md` bind every\n  session and outrank this skill's defaults.\n- Journal honestly: a TODO line without a matching DONE line is expected and\n  safe; a DONE line without receipts is a lie.\n\n## Harness note (out of skill scope)\n\nThis skill makes the AGENT persistent within a session and recoverable across\nsessions. Fully automatic relaunch after a dead session requires harness-level\nscheduling (cron\u002Fgateway\u002Fwatchdog) outside any skill's control. If the owner\nwants unattended overnight loops, pair this skill with a scheduler that\nre-invokes the agent with \"resume the goal\".\n","# Goal — persistent project objective\n\nA goal is a single objective the agent keeps pursuing across turns and\nsessions until it is marked done. Inspired by Prime Agent's thread goal:\nstate lives outside any one conversation, so any tool with this skill\ninstalled (Claude Code, Cursor, Codex, ...) picks up where another left off.\n\n## State file\n\nOne file per project: `.goal.md` in the repository root. Human-readable and\nhuman-editable on purpose — pause, resume, edit, and clear are controlled by\nthe user editing the file directly.\n\n```markdown\n---\nobjective: Ship release notes for v2.3\nstatus: active        # active | paused | done\ncreated: 2026-08-22\n---\n\n## Progress\n- 2026-08-22 14:02 — drafted changelog from git log\n```\n\nOptional sections the loop reads if present: `## Queue` (ordered work items),\n`## Standing constraints` (owner-set rules that bind every session),\n`## Decisions` (recorded owner calls — binding, never re-litigated),\n`## Done criteria`.\n\n## API\n\n- **get** — read `.goal.md`. No file means no goal is set. Report the\n  objective, status, and latest progress entries when asked about goal status.\n- **create(objective)** — write `.goal.md` with `status: active` and today's\n  date. If an `active` goal already exists, do NOT silently replace it; show\n  it and ask whether to complete, pause, or replace. Only create a goal when\n  the user explicitly asks for a persistent goal; do not infer goals from\n  ordinary tasks.\n- **update(note)** — append one dated line to `## Progress` after each\n  meaningful work session toward the goal. Keep notes short and factual.\n- **complete()** — set `status: done`. Only when the objective has actually\n  been achieved and no required work remains — not because the session is\n  ending or momentum ran out.\n\n## Session behavior\n\nAt the start of a session in a repo containing `.goal.md`:\n\n- `status: active` — surface the objective to the user, then ENTER THE WORK\n  LOOP below before starting unrelated work.\n- `status: paused` — mention it exists; resume only if the user asks.\n- `status: done` — leave it as history; offer to archive or replace.\n\n## Work loop (continuous execution)\n\nAn active goal with remaining actionable items means you run a LOOP, not a\nsingle pass. One iteration:\n\n1. **Resume** — read `.goal.md` plus the newest handoff document it references\n   (typically under `docs\u002Fplans\u002F`). Verify recorded receipts against reality\n   (HEAD sha, merged PRs, live state) before trusting them.\n2. **Pick** the highest-priority item that is actionable right now — from the\n   Queue, the referenced workorder, or the handoff's \"exact next action\".\n3. **Journal before acting** — append `TODO \u003Ctask>` to `## Progress`. If the\n   session dies here, a successor knows precisely what was attempted.\n4. **Execute** — do the work. Run the real gates. Commit\u002FPR per whatever\n   authority the goal grants (e.g., self-review-and-merge if so recorded).\n5. **Journal after** — append `DONE \u003Ctask> — \u003Creceipt>` immediately. Receipt =\n   commit sha, PR number, test counts, or posted artifact. No receipt, not done.\n6. **Repeat** from step 2 while an actionable item remains and no STOP\n   condition applies.\n\nNever end a turn with actionable items outstanding unless a STOP condition\nfired. \"Momentum ran out\" is not a stop condition.\n\n## Failure resilience\n\n- **Transient LLM\u002FAPI\u002Ftool failures** — timeouts, 429\u002F5xx, dropped\n  connections — are NEVER stop conditions. Retry with backoff (≈30s → 60s →\n  120s, cap ~5 attempts). If one dependency stays down, journal `BLOCKED \u003Citem>\n  — \u003Creason>`, switch to the next non-dependent actionable item, and circle back.\n- **Crash\u002Finterrupt safety**: because TODO precedes work and DONE follows it,\n  an interrupted session loses nothing. On resume, a task with TODO and no DONE\n  is simply not started yet — verify no half-committed debris, then restart it.\n- **Tool\u002Fenvironment failure ≠ task failure.** A failing gate gets diagnosed;\n  a failing external service gets routed around; neither ends the loop.\n- **Flaky tests** fail-then-pass-isolated are recorded as known-flaky, not\n  treated as regressions — but always rerun isolated before concluding that.\n\n## Stop conditions (the ONLY reasons to end the loop)\n\n1. **Done** — goal achieved; call `complete()`.\n2. **Blocked on owner** — every remaining item needs an answer only the owner\n   can give. Post the questions (one line each), mark items BLOCKED\u002FDEFERRED,\n   update `.goal.md`, stop with a clear summary of what you need.\n3. **Context limit approaching** — write the handoff document (see Handoff),\n   append the final Progress line, stop cleanly.\n4. **Repeated hard failure** — ≥3 consecutive unrecoverable failures across\n   DIFFERENT items (not retries of one) → write an incident note into Progress\n   and the handoff, stop, report to owner.\n\nEverything else — API flakiness, slow builds, flaky tests, waiting on a local\nservice — is worked through or routed around.\n\n## Handoff (graceful exit)\n\nIf the repo keeps committed plan\u002Fhandoff documents (e.g., `docs\u002Fplans\u002F`), the\ngraceful exit is: write\u002Fupdate the handoff file containing exact HEAD sha, PRs\nlanded this session, current queue position, receipts, known gotchas, and the\nexact next action — then append the final Progress line to `.goal.md`, then\nstop. Ending a session without those two writes is a defect: the successor\nmust be able to resume from `.goal.md` + the latest handoff alone.\n\n## Rules\n\n- One active goal per repository. The file is the source of truth — never keep\n  goal state only in conversation memory.\n- Never delete or rewrite past progress lines; append.\n- Completion must reflect reality. An agent that marks a half-finished goal\n  done defeats the entire mechanism.\n- Standing constraints and recorded decisions inside `.goal.md` bind every\n  session and outrank this skill's defaults.\n- Journal honestly: a TODO line without a matching DONE line is expected and\n  safe; a DONE line without receipts is a lie.\n\n## Harness note (out of skill scope)\n\nThis skill makes the AGENT persistent within a session and recoverable across\nsessions. Fully automatic relaunch after a dead session requires harness-level\nscheduling (cron\u002Fgateway\u002Fwatchdog) outside any skill's control. If the owner\nwants unattended overnight loops, pair this skill with a scheduler that\nre-invokes the agent with \"resume the goal\".\n",{"name":5,"domain":48,"description":7},"meta","main","cd89f013b617f7eea982a9bbc60e992974fda2aa","skills\u002Fgoal",15,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco","https:\u002F\u002Fcocoresearch.org\u002Fcoco\u002F","https:\u002F\u002Fgithub.com\u002Fcoco-research","https:\u002F\u002Fcocoresearch.org","Local-first, open-source tools for people who work with AI agents: governed memory, agents that check their own work, and data that stays on your machine.","2026-11-11 12:18:13",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add coco-research\u002Fcoco --skill goal",{"tool":65,"command":66},"bunx","bunx skills add coco-research\u002Fcoco --skill goal",{"tool":68,"command":69},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill goal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fgoal\u002FSKILL.md",true,[],[74,98,108,126,161,180],{"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":81,"publishedAt":43},"01M71KEJXF9KMT0BWCMRSRFA4M","trading-super-intelligence","Trading Super Intelligence Team. Named real-world personas across 8 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Ftrading\u002FSKILL.md",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,83,84,85,86,87,88,89,90,91,35,92,93,94,95,96,97],"super","trading super intelligence","intelligence","trading","validator","personas","local","composites","studio","team","world","first","gated","2026","lm studio","local-first",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":43},"01M71KEFWS3CMAP7DF1P0FWTDE","strategy-super-intelligence","Strategy Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fstrategy\u002FSKILL.md",[104],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,82,107,84,86,87,88,89,90,91,35,92,93,94,95,96,97],"strategy","strategy super intelligence",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":120,"publishedAt":43},"01M71KED56ZEPK2QE84QSQPMT0","risk-compliance-super-intelligence","Risk & Compliance (GRC) Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Frisk-compliance\u002FSKILL.md",[114,115],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[121,82,122,123,124,84,86,87,88,89,125,90,91,35,92,93,94,95,96,97],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":145,"publishedAt":43},"01M71KE9A2FWSC74VA96W1EZSN","product-design-super-intelligence","Your product + design brain trust and decision partner. Named personas across 8 cells spanning product strategy, discovery\u002Fresearch, growth\u002Fmetrics, design foundations\u002Fusability, design leadership\u002Fcraft, UX\u002Fcontent, design systems, and a…","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fproduct-design\u002FSKILL.md",[132,135,138,139,142],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":140,"categoryName":141,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":143,"categoryName":144,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000032","设计师",[146,147,84,148,82,149,150,151,152,153,154,91,35,155,156,95,157,158,159,160],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":169,"publishedAt":43},"01M71KE6H9FPSD9TECYFBPXZ8Y","legal-ip-super-intelligence","Your legal, IP, and regulatory brain trust. 31 named personas across 7 cells covering patent strategy, tech licensing, regulatory litigation, AI governance, open-source compliance, privacy law, and antitrust.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Flegal-ip\u002FSKILL.md",[167,168],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},[170,82,171,84,172,173,160,174,87,175,176,177,106,91,35,178,123,179,95,157],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":187,"publishedAt":43},"01M71KE36QRY610V6YVB9JWRND","healthcare-life-sciences-super-intelligence","Your healthcare and life sciences brain trust. 25 named personas across 7 cells covering drug discovery, medtech, biotech strategy, health policy, genomics, clinical trials, and healthcare economics.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fhealthcare-life-sciences\u002FSKILL.md",[186],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[188,82,189,190,84,173,160,191,192,87,193,194,106,91,35,195,196,197,198,95],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]