[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BH84RMMEZ0TE6SWP3HYZJS":3,"skill-same:01M7BH84RMMEZ0TE6SWP3HYZJS":46},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7BH84RMMEZ0TE6SWP3HYZJS","correct",null,"Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for \u002Fcorrect.","lovrozagar\u002Fgrunt","lovrozagar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F86857639?v=4","01M7B3T6X88HRBYP2A9ZEGQEMD","Lovro Zagar","01M7BGVF4JZBK92D0TSM09M44Q",2,"MIT","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Fcorrect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: correct\ndescription: \"Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for \u002Fcorrect.\"\n---\n# Correct\n\nThe operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't make them.\n\nFirst read `principle-encode-lessons-in-structure` and follow it. Encode the lesson in the repo, not in another paragraph.\n\nSlash `\u002Fcorrect` only. Not a session flag.\n\nAssume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.\n\n## Find the mistake classes\n\nFirst, read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. Also read `.rulesync\u002Flessons\u002FINDEX.md`: every lesson with `hits` of 2 or more is a class with its evidence. Group the mistakes into classes. A class counts once it has happened twice.\n\n## Fix each class at the highest level that works\n\n1. **Eliminate it with architecture.** Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.\n2. **Enforce it with types so the bad state can't be written.** If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more.\n3. **Test the behavior.** Fix or delete any test that still passes when the behavior it checks breaks, or that fails when only the internals change.\n4. **Write docs or agent rules last, only for judgment calls.** Nothing fails when an agent skips them.\n\n## Fix and prove\n\nThen fix the most frequent classes now, one commit each. When a fixed class came from a lesson, run `node .rulesync\u002Fscripts\u002Flessons.mjs rm \u003Cslug>` in the same commit: the check replaces the lesson. A correction you fix now but cannot encode yet goes in as a lesson (`lessons.mjs hit`, or write one). Prove each new check fails on a real past mistake. Run the same command locally and in CI. Exceptions go on the offending line with a reason, an expiry date, and a human's approval.\n\n## Keep the rule table\n\nLast, keep a table in `AGENTS.md` (SSOT: `.rulesync\u002Frules\u002Foverview.md`) that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, that's a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen.\n\n**Reply:** each class with its evidence, the level you picked, and why a higher level didn't work.\n","# Correct\n\nThe operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't make them.\n\nFirst read `principle-encode-lessons-in-structure` and follow it. Encode the lesson in the repo, not in another paragraph.\n\nSlash `\u002Fcorrect` only. Not a session flag.\n\nAssume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.\n\n## Find the mistake classes\n\nFirst, read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. Also read `.rulesync\u002Flessons\u002FINDEX.md`: every lesson with `hits` of 2 or more is a class with its evidence. Group the mistakes into classes. A class counts once it has happened twice.\n\n## Fix each class at the highest level that works\n\n1. **Eliminate it with architecture.** Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.\n2. **Enforce it with types so the bad state can't be written.** If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more.\n3. **Test the behavior.** Fix or delete any test that still passes when the behavior it checks breaks, or that fails when only the internals change.\n4. **Write docs or agent rules last, only for judgment calls.** Nothing fails when an agent skips them.\n\n## Fix and prove\n\nThen fix the most frequent classes now, one commit each. When a fixed class came from a lesson, run `node .rulesync\u002Fscripts\u002Flessons.mjs rm \u003Cslug>` in the same commit: the check replaces the lesson. A correction you fix now but cannot encode yet goes in as a lesson (`lessons.mjs hit`, or write one). Prove each new check fails on a real past mistake. Run the same command locally and in CI. Exceptions go on the offending line with a reason, an expiry date, and a human's approval.\n\n## Keep the rule table\n\nLast, keep a table in `AGENTS.md` (SSOT: `.rulesync\u002Frules\u002Foverview.md`) that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, that's a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen.\n\n**Reply:** each class with its evidence, the level you picked, and why a higher level didn't work.\n",{"name":5,"description":7},"main","91069c1955cc11def04b75dc2d3c4a99c9d5eb48",".rulesync\u002Fskills\u002Fcorrect",0,"https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt","https:\u002F\u002Fgithub.com\u002Flovrozagar","TypeScript Jedi Master ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ @workerstack ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ OSS & SaaS","2026-11-04 09:19:39",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lovrozagar\u002Fgrunt --skill correct",{"tool":38,"command":39},"bunx","bunx skills add lovrozagar\u002Fgrunt --skill correct",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lovrozagar\u002Fgrunt --skill correct","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Fcorrect\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7BHARD0SQTQ83H73E779A8E","write-roadmap","Write an ordered program of plans under .tmp\u002Fgrunt\u002Froadmaps\u002F. Use for \u002Fwrite-roadmap. Stops for y, which locks and runs it.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Fwrite-roadmap\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7BHAQ7M9Y790C7DW0RAKAQM","write-plan","Write a local checklist under .tmp\u002Fgrunt\u002Fplans\u002F. Then \u002Fimplement-plan {n}.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7BHANM3QZF2QP8P28WW9R3K","unslop","Cut AI tells from any writing. Use for \u002Funslop.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7BHAM1MSNX381EDKA5HN9XM","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file, or for \u002Ftypescript-best-practices.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7BHAJX7MG58JBGEAR0NCSXW","tmp","Dump a one-off convo artifact under .tmp\u002Fgrunt\u002F.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Ftmp\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BHAGFXSTF5E1DDSYEZF8ZD","teach","Explain a body of work plainly so a person actually understands it. Dig into how it works and why it is that way, then weave that into one clear explanation. Use for \u002Fteach, 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Flovrozagar\u002Fgrunt\u002Fblob\u002Fmain\u002F.rulesync\u002Fskills\u002Fteach\u002FSKILL.md",[],[]]