[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKHT67DDBW456BYQM8RQQH":3,"skill-same:01M7BKHT67DDBW456BYQM8RQQH":118},{"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":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7BKHT67DDBW456BYQM8RQQH","autonomous-decisions",null,"Resolve a specified set of decisions through independent deliberation and evidence-based judgment.","BetoFrega\u002Fskills","BetoFrega","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F637874?v=4","01M7BKHP444BSK41T281GQDPM7","Beto Frega","01M7BKHP5863T6EC03B63D0Q4T",0,"MIT","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: autonomous-decisions\ndescription: Resolve a specified set of decisions through independent deliberation and evidence-based judgment.\n---\n\n# Autonomous Decisions\n\nActivate only on the user's explicit instruction, for the specified decision set.\nExpansion to all decisions in the task requires an explicit user instruction.\nAn accepted decision permits the coordinator to act within existing task\nauthorization; deliberation creates no additional execution permission.\n\n## Standing rules\n\n- Bring high-risk or irreversible choices, conflicts with previous directions or\n  established values, and unresolved material uncertainty about these boundaries\n  to the user. Apply this gate whenever relevant facts change.\n- Use this process for choices between viable alternatives that materially affect\n  behavior, experience, cost, or maintenance. Carry out mechanically determined\n  choices directly within the authorized task.\n- Before **every** subagent dispatch, apply the available `model-selection` skill\n  independently to that assignment and follow its delegation rules.\n  Resolve it from the skill catalog;\n  in this repository, use [model-selection](..\u002Fmodel-selection\u002FSKILL.md). Set the\n  actual model and reasoning effort explicitly and disclose them at dispatch.\n- Give every subagent a fresh context, its current role instructions, necessary\n  evidence, and only the authorized read-only resources. Use read-only tool\n  restrictions when supported; otherwise enforce the boundary in the assignment\n  and describe isolation accurately. Subagents return findings without mutations,\n  external messages, or further delegation. Keep each decider isolated from peer\n  deliberations; give judges and verifiers only their explicitly assigned artifacts.\n- Complete at most two initial decider assignments and one additional decider\n  assignment per decision. The coordinator owns execution and verification.\n\nUse the same decision protocol in Codex and Claude Code. Native isolated agents\nand fresh CLI sessions are execution options. Before using a CLI, read only its\nadapter: [Codex](references\u002Fcodex.md) or [Claude](references\u002Fclaude.md).\n\n## Begin\n\nFor multiple activated decisions, begin with [batch.md](references\u002Fbatch.md).\nFor one decision, begin with [prepare.md](references\u002Fprepare.md).\nLoad each subsequent reference only when\nthe current stage's completion criterion names it. Give subagents their role and\ninputs rather than the coordinator's routing documents. Splitting files controls\ndisclosure; fresh subagent contexts provide the actual context boundary.\n","# Autonomous Decisions\n\nActivate only on the user's explicit instruction, for the specified decision set.\nExpansion to all decisions in the task requires an explicit user instruction.\nAn accepted decision permits the coordinator to act within existing task\nauthorization; deliberation creates no additional execution permission.\n\n## Standing rules\n\n- Bring high-risk or irreversible choices, conflicts with previous directions or\n  established values, and unresolved material uncertainty about these boundaries\n  to the user. Apply this gate whenever relevant facts change.\n- Use this process for choices between viable alternatives that materially affect\n  behavior, experience, cost, or maintenance. Carry out mechanically determined\n  choices directly within the authorized task.\n- Before **every** subagent dispatch, apply the available `model-selection` skill\n  independently to that assignment and follow its delegation rules.\n  Resolve it from the skill catalog;\n  in this repository, use [model-selection](..\u002Fmodel-selection\u002FSKILL.md). Set the\n  actual model and reasoning effort explicitly and disclose them at dispatch.\n- Give every subagent a fresh context, its current role instructions, necessary\n  evidence, and only the authorized read-only resources. Use read-only tool\n  restrictions when supported; otherwise enforce the boundary in the assignment\n  and describe isolation accurately. Subagents return findings without mutations,\n  external messages, or further delegation. Keep each decider isolated from peer\n  deliberations; give judges and verifiers only their explicitly assigned artifacts.\n- Complete at most two initial decider assignments and one additional decider\n  assignment per decision. The coordinator owns execution and verification.\n\nUse the same decision protocol in Codex and Claude Code. Native isolated agents\nand fresh CLI sessions are execution options. Before using a CLI, read only its\nadapter: [Codex](references\u002Fcodex.md) or [Claude](references\u002Fclaude.md).\n\n## Begin\n\nFor multiple activated decisions, begin with [batch.md](references\u002Fbatch.md).\nFor one decision, begin with [prepare.md](references\u002Fprepare.md).\nLoad each subsequent reference only when\nthe current stage's completion criterion names it. Give subagents their role and\ninputs rather than the coordinator's routing documents. Splitting files controls\ndisclosure; fresh subagent contexts provide the actual context boundary.\n",{"name":5,"description":7},"main","b212a89a4ff3d13380a0ee75a91d99ee0aad2858","skills\u002Fautonomous-decisions","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills","https:\u002F\u002Fgithub.com\u002FBetoFrega","2026-11-14 02:43:03",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add BetoFrega\u002Fskills --skill autonomous-decisions",{"tool":36,"command":37},"bunx","bunx skills add BetoFrega\u002Fskills --skill autonomous-decisions",{"tool":39,"command":40},"pnpm","pnpm dlx skills add BetoFrega\u002Fskills --skill autonomous-decisions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002FSKILL.md",true,[44,50,56,60,64,68,72,76,80,84,88,92,96,100,104,108,114],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},".gitignore","OTHER","其他",13,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002F.gitignore",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"agents\u002Fclaude.settings.json","REFERENCE","参考文档",80,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Fagents\u002Fclaude.settings.json",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"agents\u002Fopenai.yaml",43,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Fagents\u002Fopenai.yaml",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fadjudicate.md",2485,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fadjudicate.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fbatch.md",3257,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fbatch.md",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fclaude.md",2686,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fclaude.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fcli.md",2443,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fcli.md",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fcodex.md",1768,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fcodex.md",{"path":81,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fdecider.md",1980,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fdecider.md",{"path":85,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fdeliberate.md",998,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fdeliberate.md",{"path":89,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fjudge.md",2712,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fjudge.md",{"path":93,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fmajority-challenge.md",1226,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fmajority-challenge.md",{"path":97,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fprepare.md",2264,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fprepare.md",{"path":101,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Freconsider.md",1597,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Freconsider.md",{"path":105,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fverify.md",1477,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Freferences\u002Fverify.md",{"path":109,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fdispatch.py","SCRIPT","脚本",10588,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Fscripts\u002Fdispatch.py",{"path":115,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":116,"sourceHtmlUrl":117},"tests\u002Ftest_dispatch.py",7937,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-decisions\u002Ftests\u002Ftest_dispatch.py",[119,126,134,141,149,156],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7BKPW918QFBHANWQRR8JXTA","writing-for-humans","Load before writing any reader-facing text, including messages, and follow its rules as you write. Also use to rewrite or audit existing prose for plain language, clarity, readability, or actionability.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-humans\u002FSKILL.md",[],[],{"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":130,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M7BKPSYAK48C7RBZXKQN805M","writing-for-agents","Write agent-facing documents. Use when creating or editing skills, AGENTS.md, or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":19},"01M7BKPQG1ZNVYYJVSGE69V5DZ","write-adr","Write, revise, or supersede architecture decision records (ADRs) documenting an architectural choice and its rationale.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-adr\u002FSKILL.md",[],[],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":145,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M7BKPMZC59QZ0G1746SCZ3S4","wizard","Wizard scripts for human-only provisioning, credential\u002FCI setup, unfamiliar dashboards, migrations, or cutovers; use only for steps the agent cannot perform.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":19},"01M7BKPHD7Y6X4BM9SV06PNKAC","verify","Check whether the current task's claimed outcome is confirmed.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M7BKPESBZ2WZYN1EWK6SGB67","verb-tense","Choose verb tense and mood by when each event happens and how certain it is. Use when writing or reviewing any text, and when a reader asks for a tense review.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverb-tense\u002FSKILL.md",[],[]]