Enable a skill in the project configuration. Checks for conflicts with existing skills. Use to add new capabilities to the project.

Disable a skill in the project configuration. Removes its rules from the next AGENTS.md generation. Use to remove unwanted capabilities.

Automated quality checks and enforcement for code commits. Use when validating code quality, running pre-commit checks, ensuring test coverage, or enforcing coding standards before commits and pushes.

MCP server overview and integration guide. Use this for setup, configuration, and discovering available MCP tools for task and skill management.

Git workflow standards including branching strategy, commit conventions, and PR guidelines. Use when creating branches, writing commit messages, preparing pull requests, or following git best practices.

Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.

Run a security audit on the project (dependencies, secrets, OWASP)

Output-verbosity compression. Cuts response tokens ~40-70% without losing technical accuracy. Four intensity levels (off/brief/terse/ultra) aligned with Rulebook's agent-tier system. Use when user says 'terse mode', 'be terse', 'less tokens please', or invokes /rulebook-terse. Auto-activates via SessionStart hook with tier-aware default.

Ultra-compressed code review comments. One line per finding: location, problem, fix. Use when user says 'review this PR', 'code review', 'review the diff', or invokes /rulebook-terse-review. Independent of the base rulebook-terse mode.

Terse Conventional Commits generator. Subject ≤50 chars (hard cap 72), body only when 'why' isn't obvious, no filler. Use when user says 'write a commit', 'generate commit', 'commit message', or invokes /rulebook-terse-commit. Independent of the base rulebook-terse mode.

Deep code review of recent changes or specified files

Explore codebase and gather context about a topic or area

Identify code smells and execute safe refactorings

Performance analysis, profiling, and optimization

Plan and execute migrations (database, API, framework)

Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.

Save session state to .rulebook/handoff/_pending.md for cross-session continuity

Generate or update project documentation based on recent changes

Prepare deployment artifacts and verify CI/CD readiness

Systematic debugging workflow for bugs and test failures

Database schema design, migrations, and query optimization

Diagnose and fix build failures or CI issues

Architecture review, design decisions, and ADR writing

Design or review API endpoints (REST/GraphQL)