PR Review Skill

Comprehensive pull request review that analyzes code quality, architecture, test coverage, and identifies scope creep (unrelated changes mixed into the PR).

Activation Triggers

• "review pr 123", "check pr 123", "look at pr 123"
• "review the pr", "what do you think about this pr"
• "review draft pr", "check the open pr"
• "comment on issue 42", "look at issue 42", "review issue 42"

Workflow

1. Fetch PR metadata + discussion history + merge status
1.5. Ask review mode: Full (default) or Quick
--- Full path ---
2. Setup worktree, launch subagent for deep analysis (read files, validate, architecture, scope creep, cleanup)
3. Present condensed findings from subagent, ask to proceed
4. Resolve open questions (if any)
5. Draft review comment
--- Quick path ---
Q1. Read diff inline, summarize what/why/size
Q2. Flag obvious issues from diff
Q3. Draft review comment

Phase 0: Detect PR vs Issue

Determine if the target is a PR or an issue. If a URL is provided, check if it contains /pull/ or /issues/. If just a number, detect type:

gh pr view <number> --json number 2>/dev/null && echo "PR" || echo "ISSUE"

• PR → proceed with full PR review workflow (Phase 1 onwards)
• Issue → use the Issue Comment Flow below, skip all PR-specific phases

Issue Comment Flow

For issues, skip worktree/diff/architecture analysis. Focus on understanding the issue and drafting a helpful comment.

1. Fetch issue details and discussion:

gh issue view <number> --json title,body,author,state,labels,comments,createdAt

2. Read the full discussion - understand what was reported, what others said, whether there are linked PRs

3. Investigate the codebase if the issue references specific code, files, or behavior:

   • search for relevant files, read them
   • understand the reported problem in context

4. Draft a comment addressing the issue - could be: analysis of root cause, a proposed approach, questions for clarification, or acknowledgment with next steps

5. Post as a regular comment (not a review):

cat > /tmp/issue-comment.md << 'COMMENT_END'
<comment content>
COMMENT_END
gh issue comment <number> --body-file /tmp/issue-comment.md

Use AskUserQuestion before posting:

question: "Post this comment to issue #<number>?"
header: "Comment"
options:
  - Post (post as shown above)
  - Edit (tell me what to change)
  - Cancel (discard draft)

After posting → done. No worktree cleanup needed for issues.

Phase 1: Fetch PR Metadata and Discussion History

Get PR number from $ARGUMENTS. If not provided, list recent PRs and ask user to select:

# if no PR number provided, list recent PRs
gh pr list --limit 5 --state all

# get PR details
gh pr view <number> --json title,body,additions,deletions,changedFiles,files,author,state,headRefName

# get all comments (PR comments and review comments)
gh pr view <number> --json comments,reviews

Capture:

• title: what the PR claims to do
• body: detailed description, linked issues
• files: list of changed files with additions/deletions per file
• scope: total additions/deletions, number of files
• discussion history: all comments and reviews with authors and timestamps

1.1 Analyze Discussion History

Before reviewing, understand what has already been discussed:

# get PR comments (general discussion)
gh api repos/{owner}/{repo}/issues/<number>/comments --jq '.[] | "[\(.user.login)] \(.body)"'

# get review comments (inline code comments)
gh api repos/{owner}/{repo}/pulls/<number>/comments --jq '.[] | "[\(.user.login) on \(.path):\(.line)] \(.body)"'

# get reviews with their state (approved, changes_requested, commented)
gh api repos/{owner}/{repo}/pulls/<number>/reviews --jq '.[] | "[\(.user.login) - \(.state)] \(.body)"'

Summarize discussion:

• What issues were raised by reviewers?
• What was the PR author's response?
• Are there unresolved threads or pending questions?
• What has already been addressed vs still open?

Check automated reviews (Copilot, etc.): Read any automated review comments - they can have valuable findings. If Copilot or other bots flagged real issues, verify them and include in your review if valid. Don't dismiss automated feedback just because it's automated.

CRITICAL - Check for inline suggestions:

# get inline review comments (where actual suggestions live)
gh api repos/{owner}/{repo}/pulls/<number>/comments --jq '.[] | "[\(.user.login) on \(.path):\(.line // .original_line)]\n\(.body)\n---"'

Look specifically for:

• Suggested changes - code blocks with suggestion tags containing proposed fixes
• Inline comments - specific line-by-line feedback
• Security/bug warnings - automated tools often catch real issues

The review body is often just a summary. The inline comments are where the real feedback is.

Important: Do not re-raise issues that were already discussed and resolved. Focus on new findings or unaddressed concerns.

1.2 Check Merge Status

Check if PR is mergeable and CI status:

gh pr view <number> --json mergeable,mergeStateStatus,statusCheckRollup

Report:

• mergeable: MERGEABLE (no conflicts) or CONFLICTING (needs rebase)
• mergeStateStatus: CLEAN (ready), BLOCKED (checks failing), BEHIND (needs update)
• statusCheckRollup: CI check results (build, tests, lint)

If PR has conflicts or is behind, note this early - it may explain "deletions" in the diff that are actually just missing commits from the base branch.

Print summary:

PR #<number>: <title>
Author: <author> | State: <state>
+<additions>/-<deletions> across <changedFiles> files
Merge status: <mergeable> | <mergeStateStatus>
CI: <pass/fail summary>

Discussion: <N> comments, <M> reviews
- Resolved: <list of addressed issues>
- Open: <list of unresolved questions>

Phase 1.5: Select Review Mode

After presenting the Phase 1 summary, ask the user to choose review depth:

question: "Review mode for PR #<number>?"
header: "Mode"
options:
  - Full review (Recommended) — clone, run tests/linter, architecture analysis, scope creep detection
  - Quick review — diff-only, summarize what/why/size, flag obvious issues

• Full review → continue to Phase 2 (existing deep analysis)
• Quick review → jump to Quick Review path below

Quick Review Path

Lightweight review based on diff and metadata only. No worktree, no subagent, no test/linter execution.

Q1. Read and Summarize Diff

gh pr diff <number>

From the diff and Phase 1 metadata, present:

• What: 2-3 sentence summary of what the PR does
• Why: purpose/motivation (from PR body, linked issues, or inferred from changes)
• Size: +additions/-deletions across N files - small/medium/large assessment
• Files changed: grouped list (code, tests, config, docs)

Q2. Flag Obvious Issues

Scan the diff for issues detectable without full file context:

• Obvious bugs (nil dereference, unchecked errors, off-by-one)
• Missing error handling in new code
• Hardcoded values that should be configurable
• TODO/FIXME/HACK comments added
• Test files missing for new code files
• Large functions added (50+ lines)
• Unrelated changes mixed in (files that don't match PR purpose)

If nothing found, say so explicitly.

Q3. Proceed to Draft

After presenting the summary and any flagged issues, skip directly to Phase 5 (Draft Review Comment). All Phase 5 rules apply: check previous comments, use writing-style skill, don't restate what the PR does.

No worktree cleanup needed since quick review never creates one.

Phase 2: Deep Analysis via Subagent

CRITICAL: Delegate all file reading, validation, and architecture analysis to a subagent to protect the main conversation's context window. The subagent does the heavy lifting and returns a condensed report.

2.1 Setup Worktree (in main conversation)

Create the work