[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7194KW97TRFQXZ1RVDJ677K":3,"skill-same:01M7194KW97TRFQXZ1RVDJ677K":50},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7194KW97TRFQXZ1RVDJ677K","evolve-select",null,"openplaybooks-dev\u002Fconverge","openplaybooks-dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F270560357?v=4","01M7191G17AHW5SXN63HJ0BEZV","01M7191G29922BDNWN8CFVG4PD",3,"MIT","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fexamples\u002Fevolutionary-optimization\u002F.converge\u002Fplaybooks\u002Fskills\u002Fevolve-select\u002FSKILL.md",[],[17,18,19,20,21],"select","evolve","evolve select","training","top","2026-11-10 10:12:30",false,"---\nid: evolve-select\ntitle: Select Top-K Training Configurations\n---\n\n# Select Top-K Training Configurations\n\nRank evaluated LLM training configurations and select the top-K as parents for the next generation.\n\n## Process\n\n1. Read the consolidated scores for the current generation\n2. Rank configurations by overall fitness (descending)\n3. Select the top-K configurations as parents\n4. Compare this generation's best to the all-time best\n5. Update `best-candidate.json` if a new best is found\n6. Advance the generation counter in `evolution-state.json`\n7. Write selection results for the crossover phase\n\n## Outputs\n\n- `selection.json`:\n  ```json\n  {\n    \"generation\": 0,\n    \"parents\": [\n      {\n        \"candidateId\": \"candidate-003\",\n        \"fitness\": 0.85,\n        \"specification\": {\n          \"architecture\": { \"attentionType\": \"GQA\", \"layers\": 32, \"...\" : \"...\" },\n          \"hyperparameters\": { \"learningRate\": 2e-4, \"...\" : \"...\" },\n          \"dataStrategy\": { \"mix\": { \"code\": 0.3, \"...\" : \"...\" }, \"...\" : \"...\" }\n        }\n      }\n    ],\n    \"populationStats\": { \"mean\": 0.7, \"max\": 0.85, \"min\": 0.55 }\n  }\n  ```\n- `best-candidate.json`:\n  ```json\n  {\n    \"candidateId\": \"candidate-003\",\n    \"generation\": 0,\n    \"fitness\": 0.85,\n    \"approach\": \"GQA architecture with code-heavy curriculum\",\n    \"specification\": { \"architecture\": {...}, \"hyperparameters\": {...}, \"dataStrategy\": {...} }\n  }\n  ```\n- `evolution-state.json` — generation counter incremented, status updated\n\n## Quality Criteria\n\n- Selection is strictly by fitness ranking\n- Best configuration is tracked across all generations (not just current)\n- Generation counter is advanced exactly by 1\n- Parent specifications are preserved in full (needed by crossover)\n","# Select Top-K Training Configurations\n\nRank evaluated LLM training configurations and select the top-K as parents for the next generation.\n\n## Process\n\n1. Read the consolidated scores for the current generation\n2. Rank configurations by overall fitness (descending)\n3. Select the top-K configurations as parents\n4. Compare this generation's best to the all-time best\n5. Update `best-candidate.json` if a new best is found\n6. Advance the generation counter in `evolution-state.json`\n7. Write selection results for the crossover phase\n\n## Outputs\n\n- `selection.json`:\n  ```json\n  {\n    \"generation\": 0,\n    \"parents\": [\n      {\n        \"candidateId\": \"candidate-003\",\n        \"fitness\": 0.85,\n        \"specification\": {\n          \"architecture\": { \"attentionType\": \"GQA\", \"layers\": 32, \"...\" : \"...\" },\n          \"hyperparameters\": { \"learningRate\": 2e-4, \"...\" : \"...\" },\n          \"dataStrategy\": { \"mix\": { \"code\": 0.3, \"...\" : \"...\" }, \"...\" : \"...\" }\n        }\n      }\n    ],\n    \"populationStats\": { \"mean\": 0.7, \"max\": 0.85, \"min\": 0.55 }\n  }\n  ```\n- `best-candidate.json`:\n  ```json\n  {\n    \"candidateId\": \"candidate-003\",\n    \"generation\": 0,\n    \"fitness\": 0.85,\n    \"approach\": \"GQA architecture with code-heavy curriculum\",\n    \"specification\": { \"architecture\": {...}, \"hyperparameters\": {...}, \"dataStrategy\": {...} }\n  }\n  ```\n- `evolution-state.json` — generation counter incremented, status updated\n\n## Quality Criteria\n\n- Selection is strictly by fitness ranking\n- Best configuration is tracked across all generations (not just current)\n- Generation counter is advanced exactly by 1\n- Parent specifications are preserved in full (needed by crossover)\n",{"id":5,"title":27},"Select Top-K Training Configurations","main","7d618d8bc059f1a0974706d1d15ec25f73cf1e1d","examples\u002Fevolutionary-optimization\u002F.converge\u002Fplaybooks\u002Fskills\u002Fevolve-select",1,"https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge","https:\u002F\u002Fplaybooks.to","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev","2026-06-13 10:11:21",{"source":7,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add openplaybooks-dev\u002Fconverge --skill evolve-select",{"tool":42,"command":43},"bunx","bunx skills add openplaybooks-dev\u002Fconverge --skill evolve-select",{"tool":45,"command":46},"pnpm","pnpm dlx skills add openplaybooks-dev\u002Fconverge --skill evolve-select","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fexamples\u002Fevolutionary-optimization\u002F.converge\u002Fplaybooks\u002Fskills\u002Fevolve-select\u002FSKILL.md",true,[],[51,79,88,110,135,162],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":62,"publishedAt":22},"01M71989MQF3GPZ7P5TX6S93PD","hello-checker","Use this skill when asked to \"verify\", \"check\", or \"validate\" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Ftests\u002Ftest-codex-real\u002F.converge\u002Fskills\u002Fhello-checker\u002FSKILL.md",[57],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78],"checker","hello checker","hello","it","use","content","validate","spec","verify","check","file","workflow","when","Meet","files","for",{"skillNo":80,"name":81,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":85,"publishedAt":22},"01M7198823W79B3S15TPV97TCB","ask-skill","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Ftests\u002Ftest-ask-autonomous\u002F.converge\u002Fplaybooks\u002Fdefault\u002Fskills\u002Fask-skill\u002FSKILL.md",[84],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[86,87],"ask skill","ask",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":98,"publishedAt":22},"01M71986EJ6VCM8YKGEM2YEDQV","html-review-artifact","Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fskills\u002Fhtml-review-artifact\u002FSKILL.md",[94,97],{"categoryNo":95,"categoryName":96,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[99,100,101,102,103,78,104,105,106,107,108,109],"html","artifact","review","html review artifact","as","framework","wide","guidance","markdown","human","artifacts",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":22},"01M719833M2XWXG1VPBW30GW7J","converge-planning","Design a Converge playbook end-to-end. Use when the user says \"plan a project\", \"design a playbook\", \"decompose into tasks\", \"scaffold a Converge workflow\", \"onboard to Converge\", or asks how to write TASK.md \u002F playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `\u002Fconverge-control` after producing the playbook structure.","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fskills\u002Fconverge-planning\u002FSKILL.md",[116],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[118,119,120,121,74,122,67,123,124,125,126,127,128,129,130,131,132,133,134,75],"converge","converge planning","planning","structure","tasks","decompose","hand","write","plan","how","update","playbook","new","design","how to","end","project",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":147,"publishedAt":22},"01M7197XZT1T9GDYAJGVGX1J60","converge-control","Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says \"run my playbook\", \"execute this\", \"monitor the run\", \"converge failed\", \"the run is stuck\", \"retry failures\", \"babysit this playbook\", \"what's the status?\", \"show me the gantt\", or asks how to use `converge run` \u002F `--select` \u002F `inspect` \u002F `doctor` \u002F `clean` \u002F `stop`. Also use it for `HTTP 401` \u002F `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fskills\u002Fconverge-control\u002FSKILL.md",[141,142],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[148,149,118,150,151,152,153,154,155,156,124,157,158,131,132,159,133,160,17,161],"converge control","control","operate","invalid","show","api","me","work","reset","show me","cleanup","clean","inspect","retry",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":22},"01M7197SCVN0QTD3CM4M83WYJH","repair-taskts","Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors","https:\u002F\u002Fgithub.com\u002Fopenplaybooks-dev\u002Fconverge\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fsrc\u002Fnavigator\u002Frepair\u002Fskill-templates\u002Frepair-taskts\u002FSKILL.md",[168],{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},[170,171,172,173,125,174,175,176,177,178,179,180,181,182,183,133,184,118,185,186],"repair taskts","repair","Bash","edit","read","line","at","spawn","code","analysis","number","errors","issues","fix","chain","definition","never"]