[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CR3K7ZBP2ERY85JMKCGF7Q":3,"skill-same:01M6CR3K7ZBP2ERY85JMKCGF7Q":56},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6CR3K7ZBP2ERY85JMKCGF7Q","architecture-rules",null,"Check and uphold a project's deterministic architecture rules — who may import whom, and the code shapes that have caused repeat defects. Use before finishing a code change, when adding a module or a cross-package import, and whenever asked to verify the architecture. The project's AGENTS.md names its checks; this skill's project section repeats them.","maxjbarfuss\u002Fmax_llm","maxjbarfuss","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13053317?v=4","01M6CR3EGHV8C2C90PGAQEXZ27","Max Barfuss","01M6CR3EN0FXE8RZXAXCT7DWJG",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Farchitecture-rules\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"architecture","Rules","architecture rules","change","code","package","verify","check","use","deterministic","2026-11-10 10:12:30",false,"---\nname: architecture-rules\ndescription: \"Check and uphold a project's deterministic architecture rules — who may import whom, and the code shapes that have caused repeat defects. Use before finishing a code change, when adding a module or a cross-package import, and whenever asked to verify the architecture. The project's AGENTS.md names its checks; this skill's project section repeats them.\"\n---\n\n# Architecture rules — run the check, do not trust the prose\n\n\u003C!-- agent-sync:start architecture-rules -->\n*Vendor-neutral and machine-wide: canonical in `~\u002F.agents\u002Fskills\u002F`, copied\ninto each repository by agent-sync, followed by any coding agent or a person.*\n\nA project states its architecture in prose in `AGENTS.md` and, wherever a rule\nis mechanically decidable, enforces it with a deterministic check. The prose\nalone does not hold. Measured in Keep: a dataclass was rebuilt field by field\ndirectly underneath a comment warning that rebuilding a dataclass field by\nfield drops fields, and by the time anyone looked it had silently dropped two.\nSeveral agents work in these trees at once and none of them read the document\nrecently. Run the checks.\n\n## Find them, then run them\n\nThe project's `AGENTS.md` names its architecture checks, and the project's\nsection below this block repeats them. They belong to the project's normal\nchecks, so a change that breaks one does not merge — run them before handoff,\nnot after.\n\nA boundary stated in prose with no check behind it is a finding when the rule\nis decidable — an import direction, a banned call, a required marker. The\ncheck belongs in the test suite, and the prose should point at it.\n\n## When a check fires\n\nFix the code. These checks are not style; each one records a defect that\nreached a repository.\n\nIf the violation is genuinely correct, say so in the handoff and why, then\nchange the rule **and** the `AGENTS.md` passage that states it, in the same\ncommit, so the document and the check keep saying the same thing. Never\nsilence a check to get green — no `--ignore`, no per-file exemption, no\ncommented-out assertion. A rule turned off for one file is how a boundary is\nlost one file at a time.\n\nA new top-level package is an architectural act. A new condition edits a\nstage; it does not add a peer to one.\n\n## What to say at the end\n\nWhich architecture checks ran and their result, verbatim; and any rule you\nchanged, with the `AGENTS.md` passage you changed beside it.\n\u003C!-- agent-sync:end -->\n\u003C!-- Everything above is canonical and kept byte-identical across repos\n     by agent-sync; edit it in agent-sync\u002Fskills\u002F, not here. Anything\n     BELOW this note is this project's own — drift.sh counts it but\n     never flags it. -->\n","# Architecture rules — run the check, do not trust the prose\n\n\u003C!-- agent-sync:start architecture-rules -->\n*Vendor-neutral and machine-wide: canonical in `~\u002F.agents\u002Fskills\u002F`, copied\ninto each repository by agent-sync, followed by any coding agent or a person.*\n\nA project states its architecture in prose in `AGENTS.md` and, wherever a rule\nis mechanically decidable, enforces it with a deterministic check. The prose\nalone does not hold. Measured in Keep: a dataclass was rebuilt field by field\ndirectly underneath a comment warning that rebuilding a dataclass field by\nfield drops fields, and by the time anyone looked it had silently dropped two.\nSeveral agents work in these trees at once and none of them read the document\nrecently. Run the checks.\n\n## Find them, then run them\n\nThe project's `AGENTS.md` names its architecture checks, and the project's\nsection below this block repeats them. They belong to the project's normal\nchecks, so a change that breaks one does not merge — run them before handoff,\nnot after.\n\nA boundary stated in prose with no check behind it is a finding when the rule\nis decidable — an import direction, a banned call, a required marker. The\ncheck belongs in the test suite, and the prose should point at it.\n\n## When a check fires\n\nFix the code. These checks are not style; each one records a defect that\nreached a repository.\n\nIf the violation is genuinely correct, say so in the handoff and why, then\nchange the rule **and** the `AGENTS.md` passage that states it, in the same\ncommit, so the document and the check keep saying the same thing. Never\nsilence a check to get green — no `--ignore`, no per-file exemption, no\ncommented-out assertion. A rule turned off for one file is how a boundary is\nlost one file at a time.\n\nA new top-level package is an architectural act. A new condition edits a\nstage; it does not add a peer to one.\n\n## What to say at the end\n\nWhich architecture checks ran and their result, verbatim; and any rule you\nchanged, with the `AGENTS.md` passage you changed beside it.\n\u003C!-- agent-sync:end -->\n\u003C!-- Everything above is canonical and kept byte-identical across repos\n     by agent-sync; edit it in agent-sync\u002Fskills\u002F, not here. Anything\n     BELOW this note is this project's own — drift.sh counts it but\n     never flags it. -->\n",{"name":5,"description":7},"main","16426a8647c4bf341798845ddf222a5b8c1ac861",".agents\u002Fskills\u002Farchitecture-rules","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss","https:\u002F\u002Fwww.altavega.io","Software Engineer, AI, Robotics, Systems, Full-Stack","2026-09-29 21:59:21",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add maxjbarfuss\u002Fmax_llm --skill architecture-rules",{"tool":48,"command":49},"bunx","bunx skills add maxjbarfuss\u002Fmax_llm --skill architecture-rules",{"tool":51,"command":52},"pnpm","pnpm dlx skills add maxjbarfuss\u002Fmax_llm --skill architecture-rules","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Farchitecture-rules\u002FSKILL.md",true,[],[57,74,96,110,124,139],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":29},"01M6CR6B20826Y0PPVXJQ2D0QJ","train","Launch a new max_llm training run on both GPUs (RTX 4090 + RTX 3090 Ti) through torchrun DDP, resolving the TOML config by name or path. Use only when the user explicitly asks to start, launch or begin a run — \"resume\", \"continue\" or \"keep training\" mean the existing run; takes an optional config name or path.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftrain\u002FSKILL.md",[],[59,64,65,66,67,27,68,69,70,71,72,73],"config","max","resume","only","user","continue","start","run","training","launch",{"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":29},"01M6CR67YE4MW1R46KB8NV85ZT","serve-live","Before a person looks at a running service, make sure what is running IS the code in the checkout. Restart the services your change actually touched — not every service — and verify each is serving the current commit rather than merely answering; check the remaining dependencies are up without bouncing them. Use whenever you finish work a person will view in a browser or client, whenever you say a page or service is ready, after any commit that changes served code, and when asked to 'restart', 'refresh the services', 'is it live', or 'serve the latest'. Also covers waiting for lazy warm-up before calling a service ready.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fserve-live\u002FSKILL.md",[],[81,82,25,83,84,23,85,26,86,22,87,88,27,89,90,91,92,93,94,95],"serve live","services","page","browser","work","commit","view","refresh","dependencies","calling","restart","say","finish","up","ready",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":29},"01M6CR665ZD6GG1SQKD0XS4GJS","review","Review a local change, branch, pull request, or stack for correctness, regressions, security, tests, and unnecessary complexity. Use when asked to review rather than implement.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview\u002FSKILL.md",[],[98,103,22,27,104,105,106,107,108,109],"complexity","stack","pull","pull request","implement","security","branch",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":29},"01M6CR64DYZJFD4JM1QCKMCGFN","regression-coverage","Reshape a slow or brittle test suite around observable user journeys and published contracts. Use when pruning tests, repairing weak smoke coverage, or addressing repeated feature regressions.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fregression-coverage\u002FSKILL.md",[],[117,118,119,120,121,122,27,68,123],"regression","coverage","regression coverage","smoke","contracts","test suite","test",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":29},"01M6CR62A9C4BB3YR6XZPVBKY3","pr-babysit","Monitor selected pull requests and report or safely act on review, CI, mergeability, and stack state.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fpr-babysit\u002FSKILL.md",[],[131,132,133,134,135,98,136,104,137,105,138],"pr babysit","babysit","pr","monitor","pull requests","report","ci","state",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":29},"01M6CR5ZWFQFGJ6QY17DN0Q3NF","keel","Use a project's local keel code graph to assess change impact, find callers and reuse candidates, validate a plan, or check an edit. Applies only in a repository with a .keel\u002F directory; skip it for prose-only work.","https:\u002F\u002Fgithub.com\u002Fmaxjbarfuss\u002Fmax_llm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkeel\u002FSKILL.md",[],[141,146,147,67,27,148,26,85,149,150,151,23,152,22,153],"find","prose","edit","plan","repository","graph","validate","directory"]