What problem does it solve? After a coding session, it is hard to know why the agent struggled, made mistakes, or wasted tokens. This Skill conducts a structured retrospective on a session and turns observed friction into concrete improvements for the agent's environment, such as navigation pointers, automated checks, and coding standards. ## Core Features & Use Cases - Session Analysis: Reads primary sources like session logs to reconstruct what happened during a coding session, defaulting to the current session when none is specified. - Improvement Categories: Evaluates navigation, automated checks, coding standards, global AGENTS.md bloat, tool economy, no-op instructions, and information access, then ranks candidates by severity. - File Placement Guidance: Directs findings to the right destination, keeping CLAUDE.md/AGENTS.md minimal, routing rules to CODING_STANDARDS.md for the review agent, and using docs and skills for reference material. - Use Case: After a long session where the agent repeatedly failed to find a config file and made a lint-catchable error, run a retrospective to add a navigation pointer and a lint check so future sessions avoid both problems. ## Quick Start Ask the agent to run a retrospective on the last coding session and suggest improvements to the agent environment.