ai testing best practices commands

paulbreuler/limps

Command Claude Code

Run a product-manager-style audit of a feature plan: scorecard by category, findings by severity, duplicate-feature detection across plans, and concrete next edits. Use after creating or updating a plan and before running agents; output is intended to feed back into the plan for iterative improvement.

paulbreuler/limps

Command Claude Code

Generate a TDD plan with verbose planning docs and minimal agent execution files using MCP planning tools.

paulbreuler/limps

Command Claude Code

Apply feedback to an existing plan, regenerate affected agent files, and commit after approval.