Skip to content

mgiovani/ai-arsenal / skills/create-rule

create-rule

Verified

Create a new memory/instruction rule for whatever AI coding tool a project actually uses, a CLAUDE.md entry or .claude/rules/*.md file for Claude Code, an AGENTS.md entry for Codex/Cursor/Copilot/Gemini-CLI-style tools, or a .cursor/rules/*.mdc file for Cursor. Use when the user runs /create-rule or asks to add a project rule, user/personal rule, coding standard, style guide entry, or workflow instruction to memory, AGENTS.md, or CLAUDE.md. Not for creating skills or slash commands (use create-skill). Not for discovering or installing existing third-party skills (use find-skills).

FileKindSize
SKILL.mdskill md4.5 KB
evals/evals.jsonconfig3.2 KB
evals/trigger-eval.jsonconfig1.8 KB
references/memory-hierarchy.mdmarkdown4.9 KB
references/rule-examples.mdmarkdown4.3 KB

evals/trigger-eval.json

View on GitHub
[
  {"query": "add a rule that we always use 2-space indentation", "should_trigger": true},
  {"query": "create a CLAUDE.md entry for our API error handling convention", "should_trigger": true},
  {"query": "I want a project rule enforcing conventional commits format", "should_trigger": true},
  {"query": "add a .cursor/rules file for our React component conventions", "should_trigger": true},
  {"query": "write an AGENTS.md section about our testing conventions", "should_trigger": true},
  {"query": "/create-rule formatting", "should_trigger": true},
  {"query": "add a personal rule so I always prefer async/await over promises", "should_trigger": true},
  {"query": "we need a coding standard documented for state management", "should_trigger": true},
  {"query": "add a workflow instruction to CLAUDE.md about our PR review process", "should_trigger": true},
  {"query": "create a new rule file under .claude/rules for security guidelines", "should_trigger": true},
  {"query": "create a new skill that generates changelogs from commits", "should_trigger": false},
  {"query": "make a slash command for running our test suite", "should_trigger": false},
  {"query": "find a skill that can help with database migrations", "should_trigger": false},
  {"query": "is there an existing skill for checking i18n completeness", "should_trigger": false},
  {"query": "turn this workflow into a reusable skill", "should_trigger": false},
  {"query": "install a skill for reviewing pull requests", "should_trigger": false},
  {"query": "write a full CLAUDE.md summarizing the whole codebase from scratch", "should_trigger": false},
  {"query": "generate onboarding documentation for new engineers", "should_trigger": false},
  {"query": "review my code for style violations", "should_trigger": false},
  {"query": "write a commit message for these changes", "should_trigger": false}
]
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall