What problem does it solve? After a coding session, it is hard to know why an AI coding agent struggled, made mistakes, or wasted tool calls. This Skill reviews session logs and proposes concrete improvements to the agent's environment so future runs go better. ## Core Features & Use Cases - Session log analysis: Reads primary sources for a specified session (defaulting to the current one) to find friction points. - Categorized improvement candidates: Evaluates navigation, automated checks, coding standards, AGENTS.md size, tool economy, no-op instructions, and information access. - Prioritized recommendations: Presents improvement candidates to the user ordered by severity. - Use Case: After a long debugging session where the agent repeatedly failed to find a config file, run a retrospective to add a navigation pointer to AGENTS.md and a lint check that would have caught the error. ## Quick Start Ask the agent to run a retrospective on the current coding session and suggest environment improvements.