review-retrospectivelisted

Use this skill right after a pull request merges, or any time you want to mine an already-merged PR's review history for durable evolution lessons — not for reviewing an open/unmerged diff (use /ievo:deep-review for that) and not for capturing a lesson you already know in your own words (use /ievo:evo directly for that). Given an explicit merged PR URL or number, collects every formal review, inline review comment, review thread, and issue comment on it with full provenance (review/comment URL, head commit SHA, current-or-stale status, responsible target), dedupes and clusters the findings by both root cause and responsible target (project-wide, a named agent, a named skill, or unknown), classifies each cluster (stale, one-off code defect, already covered by an existing rule, ordinary follow-up, or durable evolution lesson), and previews the clusters for your confirmation.
ievo-ai/skills · ★ 0 · Code & Development · score 72

Install: claude install-skill ievo-ai/skills

# Review Retrospective — mine a merged PR's reviews for evolution lessons Post-merge review feedback is a rich evolution signal, but two obvious ways of processing it both fail: invoking `/ievo:evo` once per review comment floods the overlay with duplicate, noisy entries, and passing every finding as one raw bundle loses attribution — `/ievo:evo` cannot know which agent, skill, or project-wide workflow actually caused each failure. This skill collects the full review history of one already-merged PR, preserves per-finding provenance, dedupes and clusters by root cause **and** by responsible target, classifies each cluster, and presents a preview for you to confirm. **Scope boundary — read this first.** This skill implements collection through preview only. It never invokes `/ievo:evo` and never edits any agent, skill, or overlay file other than the park file described in Step 4. Turning a confirmed "durable evolution lesson" cluster into an actual `/ievo:evo` capture is deliberately a separate, later piece of work — see "Scope boundary (MVP boundary)" below for why. ## When to use - Right after a PR you care about merges, while the reviewing session's context (which agent/skill produced the changes) is still fresh - Periodically, against an older merged PR, to catch review feedback that was never turned into a lesson - When a PR accumulated several rounds of review and you want the *pattern* across rounds, not just the last round's comments ## Step 1: Resolve the PR refe