Command Cursor
Quick review of existing diffs without full PR context.
Command Cursor
Quick review of existing diffs without full PR context.
Command Cursor
Fix lint issues in the current file.
Command Cursor
Run project linters and fix findings repo-wide.
Command Cursor
Batch review, verify (Docker-first), and merge open PRs when green.
Command Cursor
Profile and optimize performance bottlenecks.
Command Cursor
Map the fog of war before building; separate fixed decisions from open frontiers and unknowns, tag each unknown with a next move, and lay out parallel tracks; plan-only, no execution in the same turn.
Command Cursor
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.
Command Cursor
Refactor for clarity without behavior change.
Command Cursor
Structured workflow from requirement through plan approval, implementation, verification, and documentation.
Command Cursor
Run full test suite and fix failures.
Command Cursor
Scoped, plan-first parallel audit of a large surface using capped subagents, with verification before reporting and an approval gate before any change.
Command Cursor
Security audit of codebase or change.
Command Cursor
SEO audit of pages or app.
Command Cursor
Scaffold a new feature across layers.
Command Cursor
Turn a rough request into a structured, production-grade prompt using applicable prompting dimensions (verification, structured detail, constraints, structure, search priority, internal-first).
Command Cursor
Canon TDD (specify, encode, fulfill) with one test at a time, approval gates, and kitchen-cleaning refactor when needed.
Command Cursor
Extremely strict maintainability review hunting for code-judo simplifications, giant files, and spaghetti-condition growth.
Command Cursor
Sync memory bank with repository state.
Command Cursor
Write meaningful unit tests for target code.
Skill Claude CodeCodexCursor
Audit UI for WCAG accessibility issues and fixes.
Skill Claude CodeCodexCursor
Add or improve code documentation for the current change.
Skill Claude CodeCodexCursor
Add consistent error handling to the targeted code.
Skill Claude CodeCodexCursor
Address review comments on the current GitHub PR.
Skill Claude CodeCodexCursor
Produces a one-page agent permission brief (allowed, approval-required, forbidden, limits, logging, rollback, first-week test plan) before granting an AI agent access to a system, tool, or account. Use for agent risk review, permission design, MCP/tool access planning, or "what should the agent be allowed to do?".