[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73A0WJC1FNMSQTS248A85A7":3,"skill-same:01M73A0WJC1FNMSQTS248A85A7":58},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M73A0WJC1FNMSQTS248A85A7","optional-ok",null,"every optional field, well formed","ChBrain\u002FKAAL.experiment","ChBrain","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14736649?v=4","01M739YWZ1Z36DSNA6282QKXNJ","01M739YX02XZPTXJDTR35ZM4XA",0,"MIT","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Frequirements\u002Fstandard-v1\u002Ffixtures\u002Ffields\u002Foptional-ok\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: optional-ok\ndescription: \"every optional field, well formed\"\nlicense: MIT\ncompatibility: Requires node 22 and git\nallowed-tools: Read Bash(git:*)\nmetadata:\n  author: the league\n  version: \"0.0.1\"\n---\n\n# optional-ok\n","# optional-ok\n",{"name":5,"license":14,"metadata":23,"description":7,"allowed-tools":26,"compatibility":27},{"author":24,"version":25},"the league","0.0.1","Read Bash(git:*)","Requires node 22 and git","main","ae56b7b5258066d013425c1b9f0eb7064bc76e23","requirements\u002Fstandard-v1\u002Ffixtures\u002Ffields\u002Foptional-ok","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment","https:\u002F\u002Fgithub.com\u002FChBrain","2026-09-19 23:32:56",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add ChBrain\u002FKAAL.experiment --skill optional-ok",{"tool":40,"command":41},"bunx","bunx skills add ChBrain\u002FKAAL.experiment --skill optional-ok",{"tool":43,"command":44},"pnpm","pnpm dlx skills add ChBrain\u002FKAAL.experiment --skill optional-ok","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Frequirements\u002Fstandard-v1\u002Ffixtures\u002Ffields\u002Foptional-ok\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"fixtures\u002Fadversarial-scope\u002Fask.md","REFERENCE","参考文档",53,"https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Frequirements\u002Fstandard-v1\u002Ffixtures\u002Ffields\u002Foptional-ok\u002Ffixtures\u002Fadversarial-scope\u002Fask.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"fixtures\u002Fadversarial-scope\u002Fexpect.md",40,"https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Frequirements\u002Fstandard-v1\u002Ffixtures\u002Ffields\u002Foptional-ok\u002Ffixtures\u002Fadversarial-scope\u002Fexpect.md",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M73A1NRWWN3VWZKMPC02MCKC","test","In test mode you carry the discipline of the proof, the one skill every seat loads and no seat owns. You take a want at your own layer (a criterion, a seam, a unit, a release) and produce the pair: the want restated as a test that can fail, and its proof that the test fails for the right reason and passes for the right reason, blind to every layer below yours, declared as a wall or a rubric or a manual step. You never write another seat's tests, never skip or disable one, and never turn a judgement into a gate. Use whenever any seat writes, runs, or declares a test.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Ftest\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M73A1K2NRSCC9H3X2X3KD1XB","retro-4ls","Facilitates a 4 L's retrospective (Liked, Learned, Lacked, Longed for) on a completed period of work. Two modes: facilitated (asks the human each lens in turn) or self-diagnosis (AI reads available context and fills all four lenses itself). Use after any sprint, project, session, or review.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Fretro-4ls\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M73A1EXFYTKC8C3RERERJ5AX","operate","In operate mode you become the operator, in the limited form the league ships first: release, smoke, rollback, and nothing beyond. You take code that is green on every layer and the human's key for one release, and produce the pair every seat owes: the want (this version reaches this target and answers) and its proof (the deploy script's own unit tests seen red then green, the smoke run, the rollback rehearsed). You never deploy to production without the human's explicit key for that release, never change code, and do not yet carry observability. Use when a task is green and the release is the next thing missing.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Foperate\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M73A1AD3WTGVJRZG8AX1YYYX","code","In code mode you become the developer and build within the drawing until the tests above you are green. You take an approved drawing with its red contract tests and the red acceptance tests, and produce the pair every seat owes: the want (each unit of code, stated first as the unit test that says what it does) and its proof (those unit tests seen red then green, and the acceptance and contract suites green, with nothing in the diff that no test holds). You do not change the drawing, the criteria, or another seat's tests. Use when a task is drawn and approved and the code is the next thing missing.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Fcode\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M73A1666XGSKZ58EGBJ76P7R","architect","In architect mode you become the architect and draw the space a task runs in. You take a requirement with its acceptance tests and produce the pair every seat owes: the want (the drawing: structure, seams, what is fixed and what is free, one decision record per door you close) and its proof (one contract test per seam, blind to the code behind it, seen red before handoff). You do not write production code, change the requirement, or design what the ask did not need. Use when a requirement is ready for design, when seams and interfaces must be decided, or when a change needs contract tests before anyone builds it.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Farchitect\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M73A11M90SN1AJFVBFEK1HKD","analyse","In analyse mode you become the analyst and turn a human ask into a task that can fail. You produce the pair every seat owes: the requirement (goal, assumptions, constraints, acceptance criteria, open questions) and its proof (one acceptance test per criterion, written against the surface the ask names and blind to how anything is built). You do not design, write code, or invent scope. Use when an ask arrives, when a request needs requirements, acceptance criteria, or acceptance tests, or when a task must be made testable before anyone designs or builds it.","https:\u002F\u002Fgithub.com\u002FChBrain\u002FKAAL.experiment\u002Fblob\u002Fmain\u002Fskills\u002Fanalyse\u002FSKILL.md",[],[]]