code-judo
Skill2 starsChanged 22 days agoNo licenceView on GitHub
A harsh maintainability review that hunts for restructurings that delete complexity instead of moving it: special cases bolted into unrelated flows, files growing past ~1k lines, shallow wrappers, silent fallbacks over unclear invariants, logic in the wrong layer. Use for "code judo", "thermo-nuclear review", a deep code-quality audit, the weekly hardening pass alongside CRAP and mutation testing, or before merging a large agent-written change.
In this repository78 other files it gives its agents.
- aaa-hillclimbSkill
- actorkit-storybook-testingSkill
- actorkit-tanstack-startSkill
- adr-keeperSkill
- agent-teamsSkill
- ai-art-assetsSkill
- ai-sdk-testingSkill
- arch-agentSkill
- architectSkill
- arenaSkill
- autodesignSkill
- auto-grill-meSkill
- autoresearchSkill
- babysit-prSkill
- bug-bashSkill
- cast-party-gameSkill
- chrome-cdpSkill
- client-telemetrySkill
- cmuxSkill
- codex-goalSkill
- codex-reviewSkill
- crapSkill
- create-claude-mdSkill
- debug-runbookSkill
- decodable-readingSkill
- deploy-verifySkill
- design-hillclimbSkill
- design-principle-enforcerSkill
- dont-use-use-effectSkill
- emulateSkill
- evals-firstSkill
- expo-testingSkill
- game-design-stagesSkill
- game-qaSkill
- game-rigSkill
- game-studioSkill
- goal-makerSkill
- grill-meSkill
- hard-cutSkill
- hillclimbSkill
- howSkill
- interrogateSkill
- mcp-setupSkill
- missionsSkill
- mutation-testingSkill
- nightshiftSkill
- offensive-typesafetySkill
- ogs-gameSkill
- ogs-shell-appSkill
- orwell-rulesSkill
- parse-at-boundarySkill
- principlesSkill
- procedural-3d-web-gameSkill
- product-design-criticSkill
- prune-testsSkill
- qa-agentSkill
- ralph-creatorSkill
- react-composable-componentsSkill
- react-render-performanceSkill
- reflectSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.