Brian Witlin

Structured feedback session analyzing Claude Code usage over a configurable time window. Gathers evidence from git history, memory files, and project state, then delivers an honest 5/5/5 report (going well, not going well, what to improve) with specific evidence and trend tracking against previous sessions. Use when asked to "run feedback", "how am I doing", "feedback session", "usage review", "self-assessment", "critique my workflow", or any request for an honest evaluation of how the user is using Claude Code. Proactively suggest after completing a multi-day sprint or when the user seems frustrated with their workflow. Always use this skill instead of doing ad-hoc feedback analysis in main chat.