mcpbeat Sign in

Pr Review Agent Skill

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

5k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
514
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/oliver-kriska/claude-elixir-phoenix --skill pr-review

What comes with it

12 400 bytes besides the instruction
references/bot-triage.md
references/gh-commands.md
references/response-patterns.md

The instruction itself

11 sections, as written by the author

PR Review Response

Close the review loop: fetch unresolved threads → fix → reply → resolve.

GitHub's isResolved is the state — re-runs are idempotent, handled

threads drop out automatically.

Usage

/phx:pr-review 42                  # Triage unresolved threads on PR #42
/phx:pr-review 42 --fix            # Triage + apply approved code fixes
/phx:pr-review https://...         # Full URL also works (repo parsed from URL)
/phx:pr-review 42 --bots-only      # Triage only CI bot threads (Copilot, Codex...)
/phx:pr-review 42 --no-resolve     # Reply but leave threads open

Step 1: Resolve PR + Fetch Threads

gh pr view "$PR" --json number,title,state,baseRefName,headRefName,url,author

(accepts number or URL; URL also yields owner/repo). Then fetch ALL review

threads with thread IDs + resolved status — REST alone cannot do this:

cat > /tmp/review_threads.graphql <<'GQL'
query($owner:String!, $repo:String!, $pr:Int!, $cursor:String) {
  repository(owner:$owner, name:$repo) {
    pullRequest(number:$pr) {
      reviewThreads(first:50, after:$cursor) {
        pageInfo { hasNextPage endCursor }
        nodes {
          id isResolved isOutdated path line originalLine
          comments(first:20) { nodes {
            databaseId body createdAt
            author { login __typename } } }
        }
      }
    }
  }
}
GQL
gh api graphql --paginate -F owner="$OWNER" -F repo="$REPO" -F pr="$PR" \
  -F query=@/tmp/review_threads.graphql \
  --jq '.data.repository.pullRequest.reviewThreads.nodes[]
        | select(.isResolved == false)
        | {threadId: .id, isOutdated, path, line: (.line // .originalLine),
           firstCommentId: .comments.nodes[0].databaseId,
           author: .comments.nodes[0].author.login,
           isBot: (.comments.nodes[0].author.__typename == "Bot"),
           body: .comments.nodes[0].body}'

Also fetch review summaries (gh api "repos/$OWNER/$REPO/pulls/$PR/reviews")

— they are NOT threads and cannot be resolved; surface CHANGES_REQUESTED

bodies separately. Bot detection: __typename == "Bot" / user.type == "Bot"

(the [bot] login suffix is NOT reliable across endpoints).

Step 2: Triage Table

Group by file, one row per thread. With --bots-only, keep only isBot rows.

| # | file:line | author | category | proposed action |

|---|-----------|--------|----------|-----------------|

Categories: code-change ("should be", "use X instead") · question

("why", "how does") · nitpick ("nit:", style) · praise (no action) ·

discussion (architecture) · bot-finding (CI bot inline comment —

verify before accepting, many are false positives) · outdated

(isOutdated: true — line moved; default: reply "addressed in {commit}" +

resolve). Present the table and let the user greenlight threads.

Step 3: Per-Thread Loop

For each greenlit thread:

  • Read code at path:line; check the suggestion against Iron Laws
  • Apply fix with a user-visible diff (only with --fix or explicit ok)
  • Draft reply (templates: ${CLAUDE_SKILL_DIR}/references/response-patterns.md)
  • STOP — show diff + reply, get confirmation
  • Post reply — REST, targeting the thread's root comment:
   gh api --method POST \
     "repos/$OWNER/$REPO/pulls/$PR/comments/$FIRST_COMMENT_ID/replies" \
     -f body="$REPLY_TEXT"
  • Resolve the thread (skip with --no-resolve):
   gh api graphql -f query='mutation($threadId:ID!){
     resolveReviewThread(input:{threadId:$threadId}){
       thread { id isResolved } }}' -F threadId="$THREAD_ID"

Mistake recovery: unresolveReviewThread takes the same input shape.

Step 4: Verify

mix compile --warnings-as-errors && mix test scoped to changed files.

Do NOT commit or push — leave that to the user.

Step 5: Final Summary

Print rollup: # | thread | action | status (replied/resolved/skipped).

List changed files. Optionally post a top-level conversation comment

(gh api --method POST "repos/$OWNER/$REPO/issues/$PR/comments" -f body=...)

with the rollup — only on user approval.

Iron Laws

  • NEVER auto-post responses — Always show drafts and get explicit approval
  • NEVER dismiss a review — Only the reviewer should dismiss
  • Iron Laws override reviewer suggestions — If a suggestion violates an Iron Law, explain why in the reply
  • Keep responses constructive — Acknowledge the feedback, explain reasoning
  • Separate fixes from responses — Apply code changes in a distinct step
  • NEVER resolve a thread without first posting a reply — every resolve is preceded by a reply on that thread explaining what was done
  • NEVER claim a fix without a shown diff — no "should be fixed" replies without a user-visible change
  • Bot findings get the same scrutiny as humans — decline Iron-Law-violating bot suggestions with explanation; never bulk-resolve "bot noise" without replies

Integration

PR receives review → /phx:pr-review {number}  ← YOU ARE HERE
   ↓ fetch unresolved threads (GraphQL, paginated)
   ↓ triage table → user greenlights
   ↓ per thread: fix (diff) → reply → resolve
   ↓ verify (mix compile + test) → summary
Push changes → user handles git push

Next Steps

  • /phx:plan — if findings reveal scope gaps
  • /phx:verify — full verification before pushing
  • Re-run /phx:pr-review after the next review round (idempotent)

References

  • ${CLAUDE_SKILL_DIR}/references/response-patterns.md — Response templates and tone
  • ${CLAUDE_SKILL_DIR}/references/gh-commands.md — Full gh command reference (3 comment surfaces, pagination, bot detection)
  • ${CLAUDE_SKILL_DIR}/references/bot-triage.md — Batch-triaging CI bot review passes

Other skills for the same job

different authors, same section of the catalogue
Receiving Code Review
by ZhanlinCui
×7

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

2k tokens
Requesting Code Review
by ZhanlinCui
×6

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

2k tokens
Git Commit
by github
vendor ×3

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

799 tokens
Github Code Review
by ComeOnOliver
×3

Comprehensive GitHub code review with AI-powered swarm coordination

13k tokens
Karpathy Guidelines
by hyyhf
×3

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

629 tokens
Code Reviewer
by google-gemini
vendor ×2

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

795 tokens
Agent MD Refactor
by softaworks
×2

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

4k tokens
Commit Work
by softaworks
×2

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

2k tokens

How to use it

Copy the folder

Take oliver-kriska/pr-review from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.