pr-learning
PR Learning (Continuous Improvement from Review Feedback)
Your role
You are a Staff Engineer turning PR feedback into durable team guidance.
You are not summarizing PRs. You are extracting repeatable patterns that should prevent repeated mistakes.
What this skill does
- Collect PR review artifacts (comments, threads, replies, commit context) using
gh. - Normalize feedback into observations.
- Score acceptance/dispute confidence.
- Cluster repeated patterns.
- Propose candidate Rules (strict) and Learnings (soft).
- Ask the user to choose
all,none, or selected IDs. - Codify approved candidates in project/user AGENTS.md or CLAUDE.md with provenance markers.
- Persist dedupe state so the same lesson is not re-added.
More from cameroncooke/skills
pr-comment-resolution
Audit and resolve GitHub pull request review comments with an evidence-based workflow. Use when asked to "address PR comments", "resolve review feedback", "handle inline comments", "reply to review threads", or "close out PR review notes".
4reconcile-merge-conflicts
Reconcile merge or rebase conflicts with branch-aware, regression-focused analysis. Use when asked to "resolve merge conflicts", "fix rebase conflicts", "reconcile conflicts", "rebase main", or "help me finish this merge". Detects active conflict state, guides branch selection when no operation is active, and produces a confidence-ranked reconciliation report with open questions. Treats the target branch (often `main`) as canonical for current behavior.
3release-tweet
Draft a release announcement tweet from a GitHub release. Use when asked to compose a tweet, draft a release announcement, or write social media copy for a new version/release.
1changelog-updater
Update upcoming CHANGELOG release notes with user-facing outcomes. Use when asked to update changelog entries, prepare release notes, reconcile changelog content with git history, or audit release-note drafts.
1agent-change-walkthrough
Produces a single-story walkthrough of AI-authored code changes from runtime trigger to final behavior, weaving changed and unchanged code into one narrative with annotated diffs, trade-offs, alternatives, and risk analysis. Use when asked to "explain what changed", "walk me through this diff", "summarize agent edits", "show how this feature works", or "explain this implementation step by step".
1