[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JYWH1PED9N1B2DXYH8KCY":3,"skill-same:01M71JYWH1PED9N1B2DXYH8KCY":106},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M71JYWH1PED9N1B2DXYH8KCY","skill-evolution",null,"Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.","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\u002Fskill-evolution\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"skill evolution","evolution","self","a skill","running","when","request","self-evolution","proposal","how to","as","merge","next","cycle","branch","loop","why","how","Meta","pull","2026-11-10 10:12:30",false,"---\nname: skill-evolution\ndescription: \"Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.\"\ndomain: meta\n---\n\n# Skill Evolution\n\nA cycle that improves this repository's own skills from observed use, and proposes every\nchange for a human to merge. It never writes to `main` and never merges.\n\n**Status:** the scripts this file documents, `scripts\u002Fevolve.py` and the steps it runs, are\nnot on `main` yet, so the commands below do not run today. They land with plan tasks 2 to 9\nin `.metagpt\u002Fplan.md`: task 2 `ledger.py` through task 8 `evolve.py`, and task 9\n`run_fixtures.sh` with the CI join.\n\n## The one rule\n\n**The loop proposes. The owner decides.** There is no confidence level, budget or green gate\nthat lets it land a change on its own. This is a design invariant, not a setting: a system\nthat edits the repository that measures it has no natural stopping point.\n\n## What a cycle does\n\nFive steps, and only the second one calls a model.\n\n| Step | Script | Model? | Output |\n| --- | --- | --- | --- |\n| 1. Observe | `scripts\u002Fobserve.py` | no | `signals\u002F\u003Ccycle>.json`, pinned to one commit |\n| 2. Propose | `scripts\u002Fpropose.py` | yes, one lane | `proposals\u002F\u003Cid>.json` and `proposals\u002F\u003Cid>.patch` |\n| 3. Validate | `scripts\u002Fvalidate.py` | no | accept or refuse, with a reason |\n| 4. Open | `scripts\u002Fevolve.py` | no | one branch, one pull request |\n| 5. Record | `scripts\u002Fledger.py` | no | a ledger row per event, and `CYCLE.md` |\n\nRun it:\n\n```\npython3 scripts\u002Fevolve.py run --window 30d            # the real cycle, needs credentials\npython3 scripts\u002Fevolve.py run --window 30d --dry-run   # stops before opening a branch\npython3 scripts\u002Fevolve.py run --window 30d --lane stub # no network at all\npython3 scripts\u002Fevolve.py status                       # last cycle, open proposals\n```\n\n## What the guard refuses\n\n`validate.py` is the only thing standing between a model's output and a branch. It refuses,\nwith the reason named, when any of these hold:\n\n- **Out of scope.** v1 may change a skill's `description` frontmatter, its `references\u002F` and\n  its `SKILL.md` prose, and may add or remove example blocks. A persona file, a command file,\n  a count file, a workflow or this skill's own scripts are all out of bounds.\n- **An unresolvable citation.** Every proposal cites its evidence by file and line, or by\n  receipt id, and the citation must resolve at the pinned commit.\n- **Over a cap.** Proposals per cycle and diff size per proposal are both capped in\n  `references\u002Flanes.json`. A cycle that hits the cap states the remainder rather than\n  truncating silently.\n- **Already rejected.** A diff whose hash a ledger row rejected inside the two cycle window\n  is not proposed again.\n- **A count that moved alone.** If a proposal changes a published number, the coupled files\n  must move with it, checked by running the repository's own checkers rather than a private\n  copy of their rules. See `docs\u002Frules.md` R7.\n\n## Exit codes\n\nThree valued, like every gate in this repository: **0** pass, **1** blocked by a guard,\n**2** unrunnable or unmeasured. An empty cycle is exit 0 with nothing to propose, which is a\nvalid result and not a failure.\n\n## Cost\n\nEvery model call goes through `scripts\u002Flane.py`, which reads `references\u002Flanes.json`, checks\nthe cycle budget **before** spending, obeys the model routing policy, and records the lane id\nand token count on the proposal it produced. The expensive review lane refuses unless the\nowner has explicitly authorised it for that cycle.\n\n## Where things live\n\n- `references\u002Flanes.json` - the allowed lanes and their budgets.\n- `references\u002Fproposal-schema.json` - the proposal shape, and the only fields a proposal may carry.\n- `references\u002Fsignal-sources.md` - what `observe.py` reads and what it deliberately does not.\n- `state\u002Fledger.jsonl` - the committed ledger. Append only. One record per event, and the\n  record of why something was rejected is the part that matters.\n- `state\u002FCYCLE.md` - the rendered human artifact for the most recent cycle.\n\n## Testing\n\n`bash scripts\u002Frun_fixtures.sh` runs every suite and prints `N\u002FN passed`. Every case uses the\nstub lane, so the suite needs no network and no model. CI runs the same command, so a\nproposal pipeline that stops working fails the build rather than shipping quietly.\n\n## Changing this skill\n\nChanging the loop's own scripts is out of scope for a loop proposal by design, which means a\nchange here is an ordinary pull request from a human or an agent working under review. If a\nchange alters a rule in this file, say so in the PR title and update `docs\u002Frules.md` in the\nsame commit.\n","# Skill Evolution\n\nA cycle that improves this repository's own skills from observed use, and proposes every\nchange for a human to merge. It never writes to `main` and never merges.\n\n**Status:** the scripts this file documents, `scripts\u002Fevolve.py` and the steps it runs, are\nnot on `main` yet, so the commands below do not run today. They land with plan tasks 2 to 9\nin `.metagpt\u002Fplan.md`: task 2 `ledger.py` through task 8 `evolve.py`, and task 9\n`run_fixtures.sh` with the CI join.\n\n## The one rule\n\n**The loop proposes. The owner decides.** There is no confidence level, budget or green gate\nthat lets it land a change on its own. This is a design invariant, not a setting: a system\nthat edits the repository that measures it has no natural stopping point.\n\n## What a cycle does\n\nFive steps, and only the second one calls a model.\n\n| Step | Script | Model? | Output |\n| --- | --- | --- | --- |\n| 1. Observe | `scripts\u002Fobserve.py` | no | `signals\u002F\u003Ccycle>.json`, pinned to one commit |\n| 2. Propose | `scripts\u002Fpropose.py` | yes, one lane | `proposals\u002F\u003Cid>.json` and `proposals\u002F\u003Cid>.patch` |\n| 3. Validate | `scripts\u002Fvalidate.py` | no | accept or refuse, with a reason |\n| 4. Open | `scripts\u002Fevolve.py` | no | one branch, one pull request |\n| 5. Record | `scripts\u002Fledger.py` | no | a ledger row per event, and `CYCLE.md` |\n\nRun it:\n\n```\npython3 scripts\u002Fevolve.py run --window 30d            # the real cycle, needs credentials\npython3 scripts\u002Fevolve.py run --window 30d --dry-run   # stops before opening a branch\npython3 scripts\u002Fevolve.py run --window 30d --lane stub # no network at all\npython3 scripts\u002Fevolve.py status                       # last cycle, open proposals\n```\n\n## What the guard refuses\n\n`validate.py` is the only thing standing between a model's output and a branch. It refuses,\nwith the reason named, when any of these hold:\n\n- **Out of scope.** v1 may change a skill's `description` frontmatter, its `references\u002F` and\n  its `SKILL.md` prose, and may add or remove example blocks. A persona file, a command file,\n  a count file, a workflow or this skill's own scripts are all out of bounds.\n- **An unresolvable citation.** Every proposal cites its evidence by file and line, or by\n  receipt id, and the citation must resolve at the pinned commit.\n- **Over a cap.** Proposals per cycle and diff size per proposal are both capped in\n  `references\u002Flanes.json`. A cycle that hits the cap states the remainder rather than\n  truncating silently.\n- **Already rejected.** A diff whose hash a ledger row rejected inside the two cycle window\n  is not proposed again.\n- **A count that moved alone.** If a proposal changes a published number, the coupled files\n  must move with it, checked by running the repository's own checkers rather than a private\n  copy of their rules. See `docs\u002Frules.md` R7.\n\n## Exit codes\n\nThree valued, like every gate in this repository: **0** pass, **1** blocked by a guard,\n**2** unrunnable or unmeasured. An empty cycle is exit 0 with nothing to propose, which is a\nvalid result and not a failure.\n\n## Cost\n\nEvery model call goes through `scripts\u002Flane.py`, which reads `references\u002Flanes.json`, checks\nthe cycle budget **before** spending, obeys the model routing policy, and records the lane id\nand token count on the proposal it produced. The expensive review lane refuses unless the\nowner has explicitly authorised it for that cycle.\n\n## Where things live\n\n- `references\u002Flanes.json` - the allowed lanes and their budgets.\n- `references\u002Fproposal-schema.json` - the proposal shape, and the only fields a proposal may carry.\n- `references\u002Fsignal-sources.md` - what `observe.py` reads and what it deliberately does not.\n- `state\u002Fledger.jsonl` - the committed ledger. Append only. One record per event, and the\n  record of why something was rejected is the part that matters.\n- `state\u002FCYCLE.md` - the rendered human artifact for the most recent cycle.\n\n## Testing\n\n`bash scripts\u002Frun_fixtures.sh` runs every suite and prints `N\u002FN passed`. Every case uses the\nstub lane, so the suite needs no network and no model. CI runs the same command, so a\nproposal pipeline that stops working fails the build rather than shipping quietly.\n\n## Changing this skill\n\nChanging the loop's own scripts is out of scope for a loop proposal by design, which means a\nchange here is an ordinary pull request from a human or an agent working under review. If a\nchange alters a rule in this file, say so in the PR title and update `docs\u002Frules.md` in the\nsame commit.\n",{"name":5,"domain":49,"description":7},"meta","main","cd89f013b617f7eea982a9bbc60e992974fda2aa","skills\u002Fskill-evolution",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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add coco-research\u002Fcoco --skill skill-evolution",{"tool":66,"command":67},"bunx","bunx skills add coco-research\u002Fcoco --skill skill-evolution",{"tool":69,"command":70},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill skill-evolution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002FSKILL.md",true,[74,80,84,88,94,98,102],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Flanes.json","REFERENCE","参考文档",3232,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Freferences\u002Flanes.json",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fproposal-schema.json",4463,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Freferences\u002Fproposal-schema.json",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fsignal-sources.md",2883,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Freferences\u002Fsignal-sources.md",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Ffixtures\u002Fledger\u002Fchain.jsonl","SCRIPT","脚本",2463,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Fscripts\u002Ffixtures\u002Fledger\u002Fchain.jsonl",{"path":95,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Ffixtures\u002Fledger\u002Fmalformed.jsonl",684,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Fscripts\u002Ffixtures\u002Fledger\u002Fmalformed.jsonl",{"path":99,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fledger.py",15181,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Fscripts\u002Fledger.py",{"path":103,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":104,"sourceHtmlUrl":105},"state\u002FREADME.md",1730,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fskill-evolution\u002Fstate\u002FREADME.md",[107,132,142,160,195,214],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":44},"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",[113],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"super","trading super intelligence","intelligence","trading","validator","personas","local","composites","studio","team","across","world","first","gated","2026","lm studio","local-first",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":44},"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",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[140,115,141,117,119,120,121,122,123,124,125,126,127,128,129,130,131],"strategy","strategy super intelligence",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":154,"publishedAt":44},"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",[148,149],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[155,115,156,157,158,117,119,120,121,122,159,123,124,125,126,127,128,129,130,131],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":179,"publishedAt":44},"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",[166,169,172,173,176],{"categoryNo":167,"categoryName":168,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":170,"categoryName":171,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":174,"categoryName":175,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":177,"categoryName":178,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000032","设计师",[180,181,117,182,115,183,184,185,186,187,188,124,125,189,190,129,191,192,193,194],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":203,"publishedAt":44},"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",[201,202],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":152,"taxonomyTypeDesc":153},[204,115,205,117,206,207,194,208,120,209,210,211,140,124,125,212,157,213,129,191],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":44},"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",[220],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[222,115,223,224,117,207,194,225,226,120,227,228,140,124,125,229,230,231,232,129],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]