[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0T3KA0C2JQEEEEA599CVR":3,"skill-same:01M7C0T3KA0C2JQEEEEA599CVR":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7C0T3KA0C2JQEEEEA599CVR","principle-attack-the-premise",null,"Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.","MateuszRomek\u002Fskills","MateuszRomek","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F46934668?v=4","01M7C0PY1M3ENSCMRTV5QZJQG4","Mateusz Romek","01M7C0PY2JNPFD2DP2HQ0YW7BV",0,"MIT","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprinciple-attack-the-premise\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: principle-attack-the-premise\ndescription: \"Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.\"\ndisable-model-invocation: true\n---\n\n# Attack the Premise\n\nWhen two or more fixes that share one premise have failed the same gate, suspect the premise, not the fixes.\n\n**Why:** Each failed fix is evidence against the belief it assumed. A third fix on the same premise spends effort where the evidence already says the cause is not.\n\n**Pattern:**\n- **Write the premise down.** The premise is the one sentence that every failed fix assumed.\n- **Test the premise before the next fix.** Find an observation that would come out differently if the premise were false, and make it. Look at how the failures are distributed, not only at how large they are. Make the check rerunnable per [Build the Lever](..\u002Fprinciple-build-the-lever\u002FSKILL.md).\n- **Follow the evidence.** If it contradicts the premise, the cause is elsewhere. Look for what the failures have in common that the premise did not predict. If it confirms the premise, ask the next \"why\" per [Fix Root Causes](..\u002Fprinciple-fix-root-causes\u002FSKILL.md). The earlier fixes may have treated a consequence instead of the cause.\n- **Remove the condition instead of compensating for it**, per the [Laziness Protocol](..\u002Fprinciple-laziness-protocol\u002FSKILL.md). If the evidence shows that one part always lands on the losing side, change what puts it there. A mechanism that cleans up after it leaves the cause in place and adds work on every run.\n\n**Stop:** Do not start the next fix before the premise is written down and tested.\n\nThis principle is distinct from [Redesign from First Principles](..\u002Fprinciple-redesign-from-first-principles\u002FSKILL.md), which rebuilds a design around a new requirement. It questions a fact the current design assumes.\n","# Attack the Premise\n\nWhen two or more fixes that share one premise have failed the same gate, suspect the premise, not the fixes.\n\n**Why:** Each failed fix is evidence against the belief it assumed. A third fix on the same premise spends effort where the evidence already says the cause is not.\n\n**Pattern:**\n- **Write the premise down.** The premise is the one sentence that every failed fix assumed.\n- **Test the premise before the next fix.** Find an observation that would come out differently if the premise were false, and make it. Look at how the failures are distributed, not only at how large they are. Make the check rerunnable per [Build the Lever](..\u002Fprinciple-build-the-lever\u002FSKILL.md).\n- **Follow the evidence.** If it contradicts the premise, the cause is elsewhere. Look for what the failures have in common that the premise did not predict. If it confirms the premise, ask the next \"why\" per [Fix Root Causes](..\u002Fprinciple-fix-root-causes\u002FSKILL.md). The earlier fixes may have treated a consequence instead of the cause.\n- **Remove the condition instead of compensating for it**, per the [Laziness Protocol](..\u002Fprinciple-laziness-protocol\u002FSKILL.md). If the evidence shows that one part always lands on the losing side, change what puts it there. A mechanism that cleans up after it leaves the cause in place and adds work on every run.\n\n**Stop:** Do not start the next fix before the premise is written down and tested.\n\nThis principle is distinct from [Redesign from First Principles](..\u002Fprinciple-redesign-from-first-principles\u002FSKILL.md), which rebuilds a design around a new requirement. It questions a fact the current design assumes.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","b604251d9d562521f58b39a240910968f6564a89",".agents\u002Fskills\u002Fprinciple-attack-the-premise","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills","https:\u002F\u002Fgithub.com\u002FMateuszRomek","mateuszromek.com","2026-11-13 01:35:46",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add MateuszRomek\u002Fskills --skill principle-attack-the-premise",{"tool":38,"command":39},"bunx","bunx skills add MateuszRomek\u002Fskills --skill principle-attack-the-premise",{"tool":41,"command":42},"pnpm","pnpm dlx skills add MateuszRomek\u002Fskills --skill principle-attack-the-premise","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprinciple-attack-the-premise\u002FSKILL.md",[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7C0YZ4R20ZCCZVCSMETEX5S","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7C0YVJJ1SJD9A5Z9RVGZCHN","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7C0YR2G4WDJ6C0HE05G6MRD","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Searches available evidence sources and returns a cited account of decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7C0YND1NS2EFSS21JGC7EFX","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7C0YH23EQCKD3R92V3BCS91","unslop","Cut AI tells from prose. Use before writing or revising any reply, doc, PR description, commit message, or skill text another reader will see, or for \u002Funslop.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7C0YF7BZVR2VXKS425SFMY0","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FMateuszRomek\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[]]