Skip to content
cccskills
FreePublished on GitHub

pr-review-comments

Review, triage, and resolve PR review comments. Use when user asks to check PR comments, address review feedback, fix issues raised in review, reply to reviewers, or resolve review threads.

The English summary is being prepared. Showing the original description.

Works withGitHub
See how to install

Files included (1)

  • SKILL.md4.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

PR Review Comments

Triage and address review comments on a pull request: read each comment, decide if valid, fix code, verify tests pass, reply, and resolve threads.

Prerequisites

  • gh CLI authenticated
  • Working directory inside the repo (or use --repo owner/repo)

Workflow

1. Fetch review comments

Get all review comments with context:

gh api repos/{owner}/{repo}/pulls/{pr}/comments \
  --jq '.[] | {id, path, line, body, user: .user.login}'

Also check top-level PR comments (non-inline):

gh api repos/{owner}/{repo}/issues/{pr}/comments \
  --jq '.[] | {id, body, user: .user.login}'

2. Triage each comment

For each comment, decide:

  • Valid & actionable → fix the code
  • Valid but won't fix → reply with rationale
  • Invalid / misunderstanding → reply with explanation
  • Question → answer it

Read the relevant file context before deciding. Don't blindly accept or reject.

3. Fix code

Apply fixes for valid comments. Group related fixes into a single commit. Use conventional commit style:

fix(<scope>): address PR review comments

- <summary of fix 1>
- <summary of fix 2>

Stage, commit, and push.

4. Validate tests pass

After fixing code, always run tests before pushing to make sure the fixes don't break anything:

  • Run the project's test command (check project docs / CLAUDE.md / Makefile / mise tasks for the right command).
  • If tests fail, fix the issue before pushing. A review fix that breaks CI is worse than the original comment.
  • If the fix changes test expectations (e.g., updated output values), update the tests too.
  • Pay special attention to mock/stub setups — removing or changing mocks can cause unrelated tests to fail when test infrastructure intercepts more than expected (e.g., mock_provider intercepting locally-evaluated data sources).

Only push once all tests are green.

5. Reply to comments

Reply to each review comment thread using the in_reply_to field:

gh api -X POST repos/{owner}/{repo}/pulls/{pr}/comments \
  -f body="<reply text>" \
  -F in_reply_to=<original_comment_id>

Important: The in_reply_to parameter must be a number (-F), not a string (-f). Use -F for numeric values.

Keep replies concise: state what was done or why not.

6. Resolve threads

Fetch unresolved thread node IDs via GraphQL:

gh api graphql -f query='
{
  repository(owner: "{owner}", name: "{repo}") {
    pullRequest(number: {pr}) {
      reviewThreads(first: 50) {
        nodes {
          id
          isResolved
          comments(first: 1) {
            nodes { databaseId body }
          }
        }
      }
    }
  }
}' --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false) | {id, commentId: .comments.nodes[0].databaseId, body: (.comments.nodes[0].body[:80])}'

Resolve each thread after replying:

gh api graphql -f query='
mutation {
  resolveReviewThread(input: {threadId: "<thread_node_id>"}) {
    thread { isResolved }
  }
}'

Loop over all thread IDs to resolve in batch:

for tid in PRRT_abc PRRT_def PRRT_ghi; do
  gh api graphql -f query="mutation { resolveReviewThread(input: {threadId: \"$tid\"}) { thread { isResolved } } }"
done

Rules

  • Read before deciding. Always read the file/context around the commented line before accepting or rejecting.
  • Don't blindly accept. Evaluate each comment on merit. Some automated/AI review comments are wrong.
  • Don't blindly reject. If a comment points out a real issue, fix it even if the wording is off.
  • Test before pushing. Run the full test suite (or at minimum the affected module's tests) after every fix. Never push code you haven't validated.
  • Codify repeatable findings. If a fixed comment is mechanically enforceable or clearly recurring, add a guard in the same commit via the review-guards skill (ast-grep rule with test; qualitative → a line in REVIEW_GUIDELINES.md).
  • One commit for all fixes. Don't create separate commits per comment unless changes are unrelated.
  • Reply to every comment. Even if resolved by a code change, confirm what was done.
  • Resolve only after replying. Don't resolve threads without a reply — reviewers need to see acknowledgment.
  • Push before replying. The fix commit should be visible in the PR when the reviewer reads the reply.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Explain a GitHub pull request as an English Markdown walkthrough and return a Plannotator share link. Use for PR explanations, walkthroughs, or review preparation.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

Codify project review rules as deterministic guards — ast-grep structural rules (with TDD-style rule tests) for mechanical checks, REVIEW_GUIDELINES.md for qualitative ones, wired into the project gate / wf verify. Use when the user wants to define review rules, turn a repeated review finding into a lint/guard, or set up ast-grep in a project.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

sem

Free

Entity-aware code change analysis using the pi-sem tools. Use when the user asks what changed, wants blast radius or affected tests, needs focused context for a function/class, wants review help on a commit/branch/PR, or asks to compare semantic diff with raw git diff. Prefer sem_context and sem_impact; use sem_diff selectively for summaries and reviews.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

wf

Free

Vytvoř workflow kontrakt z dosavadní diskuse — zapíše ~/Workspace/specs/<projekt>/<název>/contract.md (české tělo + strojový frontmatter) a zlintuje ho wf-gate. Použij, když uživatel řekne /wf nebo chce z probraného problému udělat kontrakt. Nikdy neimplementuje.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

České vysvětlení změny kódu z kontraktu, ref range nebo PR — pozadí, intuice, průchod kódem, důkazy, UAT a kvíz. Volá wf-impl po UAT nebo uživatel ručně.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

Dirigent jednoho workflow kontraktu ve svém super.engineering worktree — deleguje implementaci na subagenta, mezi fázemi pouští wf-gate, review předá skill wf-review, otevře draft PR (guardovaný), vyřeší komentáře, spustí UAT. Použij, když task session říká, že se má kontrakt provést přes wf-impl.

The English summary is being prepared. Showing the original description.

tomsej/pi-ext78Updated Sep 4, 2026

See all skills by tomsej

Report a problem with this skill