plan-approvallisted

# Plan-Approval Skill ## Purpose Enable user control over AI actions by requiring explicit approval for complex or risky changes, preventing mistakes and ensuring alignment with user intent. ## When to Use This Skill Automatically activates when you mention: - Creating or reviewing plans - Approval or confirmation needed - Proposed changes or approach - Want to see plan before execution - Complex or risky operations - Need user sign-off ## The Problem: No User Control **Without plan approval**: - ❌ AI jumps straight to implementation - ❌ No chance to review approach - ❌ Mistakes expensive to undo - ❌ User left out of decision process - ❌ No learning from rejections **With plan approval**: - ✅ User reviews before execution - ✅ Can modify or reject approach - ✅ Prevents costly mistakes - ✅ User maintains control - ✅ AI learns from feedback --- ## Core Principles ### 1. User is Always in Control **Never execute without approval for**: - Database schema changes - Breaking API changes - Dependency updates - Architecture refactors - File deletions - Deployment actions ### 2. Plans are Detailed **Good plans include**: - What will be done (specific files/changes) - Why this approach (rationale) - What alternatives were considered - What risks exist - What the impact is - How long it will take ### 3. Approval is Explicit **Require clear user response**: - ✅ "approve", "yes", "proceed", "looks good" - ❌ Silence, vague response, "maybe" - ⚠️ "modify: [changes]" triggers p