agentleFS
maragudkmaragudk/skills/address-code-review/SKILL.md

address-code-review

Skill49 starsChanged 9 months agoMITView on GitHub

Address code review feedback by walking through comments one at a time with the user. Use when the user has received code review comments — on a GitHub PR, in a document in the repo, or directly in conversation — and wants to work through them methodically. Also trigger when the user mentions "address review", "review comments", "PR feedback", or wants to respond to code review feedback.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Document: Read the file and extract review items.

    line 23
  2. Distinctive:

    Conversation: Use the comments as provided.

    line 24
  3. Distinctive:

    Wait for the user to decide what to do (apply, skip, modify, etc.).

    line 32
  4. Distinctive:

    After all comments have been discussed, apply all agreed-upon code changes in one batch.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Address Code Review

Work through code review comments with the user, one comment at a time. Never present multiple comments at once.

Input sources

Comments may come from:

  1. GitHub PR - Fetch inline and general comments using gh api
  2. Document in the repo - Parse whatever markdown structure is found
  3. Conversation - Comments given directly by the user

Process

1. Collect feedback

  • GitHub PR: Use GraphQL to fetch all comments in one go. Fetch inline review comments via pullRequest.reviewThreads and general PR comments via pullRequest.comments. Skip already-resolved threads (isResolved). Still present outdated but unresolved comments (isOutdated), noting to the user that the code has changed since the comment was left.
  • Document: Read the file and extract review items.
  • Conversation: Use the comments as provided.

2. Triage one at a time

For each comment, strictly one at a time:

  1. Present the comment to the user.
  2. Share your own assessment: agree, disagree, or propose an alternative. Explain your reasoning briefly.
  3. Wait for the user to decide what to do (apply, skip, modify, etc.).
  4. Record the agreed-upon action. Do not apply code changes yet.

For GitHub PR inline comments: immediately reply to the comment on GitHub and resolve the thread after discussion.

3. Apply changes

After all comments have been discussed, apply all agreed-upon code changes in one batch.

For GitHub PR general comments (which may contain multiple issues in one comment): post a single summary reply after all issues in that comment are addressed.

For document sources: update the document with status/progress as appropriate.

GitHub CLI reference

ActionCommand
Fetch all commentsGraphQL query on pullRequest.reviewThreads (inline) and pullRequest.comments (general)
Reply to inline commentgh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies -X POST -f body="..."
Reply to general commentgh api repos/{owner}/{repo}/issues/{pr}/comments -X POST -f body="..."
Resolve a threadGraphQL mutation resolveReviewThread(input: {threadId: "..."})

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.