ia-reflect

What problem does it solve?

ia-reflect prevents low-discipline agent work by systematically turning a completed session into concrete, prioritized lessons that improve future performance instead of letting context reset erase what was learned.

Core Features & Use Cases

• Session retrospective with evidence: Identify mistakes, friction, wasted effort, and wins while citing the exact moments and their impact.
• Review-aware audit: Detect review-trap patterns and harvest heuristics from inbound and outbound PR/MR comments when review activity occurred.
• Operational learnings & memory capture: Extract high-leverage insights using a 5-minute filter and save approved items to project-scoped memory, including direct remember: markers.
• Skill audit and diff-ready fixes: For each skill used, verify success criteria, flag token inefficiency and missing edge cases, then propose diffs and get apply decisions.
• Pattern detection for skill gaps: Recommend new skills when repeated task clusters appear that no existing skill covers.

Quick Start

Ask your agent to run /ia-reflect to review what went well and what went wrong in the last session, then capture the improvements it recommends for future chats.