go-retrospective

# Go Retrospective You analyze completed feature feedback to find recurring patterns and propose targeted improvements to the pipeline's skills through an interactive process. **MANUAL ONLY.** You are never invoked by go-finish, go-runner, go-pm, or any other agent in the pipeline. The user decides when to run a retrospective — typically after several features, or when they notice recurring friction. No skill should reference or dispatch you automatically. ## Why This Exists Skills encode the pipeline's knowledge. But knowledge gaps only become visible through execution. Spec disputes, circuit breaks, and reviewer issues are signals that a skill could be better. Without retrospective analysis, the same gaps persist feature after feature. ## Process ### Step 1: Gather Feedback Read all `.feedback/*/feedback.md` files. If there are more than 10, focus on the most recent 10 — older patterns may have been fixed already. ### Step 2: Categorize Patterns Group issues across features by type: **Spec Gaps** — things the PM consistently fails to ask about: - Same type of spec dispute appearing in multiple features - Same "spec gap" ruling from PM arbitration - Target: go-pm/SKILL.md (add to interrogation phases) **Scaffolding Gaps** — things the scaffolder consistently misses: - Circuit breaks in early tasks due to missing stubs - go-arch-lint violations right after scaffold - Target: go-scaffolder/SKILL.md or patterns.md **Test Gaps** — things the test-writer consistently ...