{"product_id":"rulebook-personalized-claude-md-amp-agents-md-compiler","title":"Rulebook — Personalized CLAUDE.md \u0026 AGENTS.md Compiler","description":"\u003cp\u003e\u003cstrong\u003eTurn your team's actual recurring agent mistakes — not generic advice — into a short, enforced CLAUDE.md\/AGENTS.md rulebook, then check every diff against it before merge.\u003c\/strong\u003e\u003c\/p\u003e\n\n\u003ch3\u003eWhat this Claude Skill does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eRuns a structured interview that pulls out this repo's real failure patterns — where the agent overreaches, what it keeps guessing wrong, which mistake has recurred more than once — instead of starting from a list of generic best practices\u003c\/li\u003e\n  \u003cli\u003eClassifies every answer into scope, assumption, regression, or verification, and drops anything that would apply equally to any codebase, so nothing in the output is filler\u003c\/li\u003e\n  \u003cli\u003eCompiles a rulebook under 60 lines using the included templates, with every rule ending in a concrete way to check it — a command, a pattern to grep, a file to inspect\u003c\/li\u003e\n  \u003cli\u003eShips a working diff-auditor script that reads the compiled rulebook, scans a diff, flags pattern-checkable violations automatically, and lists everything else as a manual check with the exact rule attached — so nothing gets silently skipped\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eBuilt for\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eTeams who installed a generic agent-instructions file and found it still doesn't catch their repo's specific recurring mistakes\u003c\/li\u003e\n  \u003cli\u003eEngineering leads who want agent output checked against agreed conventions before it merges, not just read once and forgotten\u003c\/li\u003e\n  \u003cli\u003eAnyone maintaining both CLAUDE.md and AGENTS.md across different tools who wants them compiled from the same source instead of drifting apart\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eWhat's inside\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eSKILL.md\u003c\/strong\u003e — the full skill file with frontmatter and the two-phase methodology: compile (interview → rulebook) and audit (diff → violation report)\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003escripts\/diff_auditor.py\u003c\/strong\u003e — a standard-library-only Python script that parses a compiled rulebook's verification lines and checks a diff against them\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003etemplates\/claude-md-template.md\u003c\/strong\u003e and \u003cstrong\u003etemplates\/agents-md-template.md\u003c\/strong\u003e — output templates so both files compile from one interview\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003ereference\/interview-questions.md\u003c\/strong\u003e — the structured interview the skill runs in Phase 1\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003ereference\/failure-pattern-library.md\u003c\/strong\u003e — 20 documented agent failure patterns across scope, assumption, regression, and verification, each mapped to the rule shape that fixes it\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eLICENSE.md\u003c\/strong\u003e — usage terms\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eHow a Claude Skill works\u003c\/h3\u003e\n\u003cp\u003eThis is a \u003ca href=\"https:\/\/platform.claude.com\/docs\/en\/agents-and-tools\/agent-skills\/overview\" rel=\"nofollow\"\u003eClaude Skill\u003c\/a\u003e — a single \u003ccode\u003eSKILL.md\u003c\/code\u003e file Claude reads as instructions for a specific kind of work. Drop it in your Claude Project, \u003ccode\u003e.claude\/skills\/\u003c\/code\u003e folder, or wherever Claude can read it. Claude triggers the skill automatically when your prompt matches its description, then runs the methodology end to end.\u003c\/p\u003e\n\n\u003ch3\u003eAuthor\u003c\/h3\u003e\n\u003cp\u003eBuilt by \u003cstrong\u003eUkiyo Productions\u003c\/strong\u003e — a strategy-led branding and growth agency. Part of a 100+ skill marketplace built for founders, operators, consultants, and agencies.\u003c\/p\u003e","brand":"Ukiyo Productions","offers":[{"title":"Default Title","offer_id":47517791879252,"sku":"UKIYO-RULEBOOK","price":19.0,"currency_code":"USD","in_stock":true}],"url":"https:\/\/ukiyoprod.com\/products\/rulebook-personalized-claude-md-amp-agents-md-compiler","provider":"Ukiyo","version":"1.0","type":"link"}