gh:pr-review
Review and interactively address PR comments. Use when the user wants to review PR feedback, go through PR comments, or address reviewer requests on a pull request.
What this skill does
# PR Review - Interactive Comment Worklist
Review and address PR comments interactively. Comments are grouped by category and presented as a worklist that shrinks as you resolve each item.
## Arguments
`$ARGUMENTS` — Optional PR number or URL. If omitted, use the current branch's open PR.
## Step 1: Fetch PR Comments
Use `gh` to retrieve all review comments and issue comments on the PR.
```
gh pr view <pr> --json number,title,url,reviews,comments
gh api repos/{owner}/{repo}/pulls/{number}/comments
gh api repos/{owner}/{repo}/issues/{number}/comments
```
Collect every comment that represents feedback, a question, or a requested change. Ignore CI status messages. Note which comments are part of a review thread vs standalone.
## Step 2: Categorize Comments
Group every comment into one of these categories (use your judgement — add or rename categories if the comments warrant it):
- **Code Changes Requested** — reviewer wants specific code modifications
- **Questions / Clarifications** — reviewer is asking a question or needs context
- **Nits / Style** — minor style, naming, or formatting suggestions
- **Architecture / Design** — higher-level design concerns
- **Documentation** — requests for docs, comments, or changelog updates
- **Positive Feedback** — praise, approvals, or acknowledgements (show these but mark as already resolved)
For each comment, capture:
- The reviewer's GitHub username
- The file and line (if it's an inline comment)
- A short summary of what they're asking for
- The `gh` API identifiers needed to reply or resolve it later
## Step 3: Present the Worklist
Each item gets a sequential number that is unique across all categories. Numbering starts at 1 and continues across groups so the user can reference any item by number.
Print the categorized worklist in this format:
```
## PR #123 — "Add caching layer" — 12 comments
### Code Changes Requested (4)
1. [ ] @alice `src/cache.ts:42` — Use LRU eviction instead of FIFO
2. [ ] @bob `src/cache.ts:87` — Handle cache miss error case
3. [ ] @alice `src/index.ts:15` — Remove unused import
4. [ ] @bob `src/cache.ts:102` — Add TTL option to config
### Questions / Clarifications (2)
5. [ ] @carol `src/cache.ts:30` — Why not use Redis here?
6. [ ] @carol — (general comment) Whats the expected memory footprint?
### Nits / Style (1)
7. [ ] @alice `src/cache.ts:55` — Rename `d` to `data`
### Positive Feedback (1)
8. [x] @bob — Great test coverage!
```
Numbers are stable — an item keeps its number even after other items are resolved.
## Step 4: Interactive Resolution Loop
Wait for the user to tell you what to do. They might say things like:
- "Fix #1" → make the code change for the LRU eviction item, then reply to the comment on GitHub confirming the fix
- "Reply to #5 saying we want to avoid the infra dependency" → post the reply via `gh api`
- "Dismiss #7, I prefer short names in that scope" → reply explaining the reasoning
- "Do all the code changes" → batch fix #1, #2, #3, #4
After completing each action:
1. Mark the addressed items as done `[x]`
2. Reprint the **remaining** worklist (omit fully-cleared categories)
3. If all items are resolved, print a summary and suggest the user re-request review
## Rules
- Always use `gh` CLI or `gh api` for GitHub interactions — never ask the user to go to the browser.
- When making code fixes, read the relevant file first to understand context before editing.
- When replying to comments, keep replies concise and professional.
- If a comment is ambiguous, ask the user what they'd like to do rather than guessing.
- Track the worklist state throughout the conversation — never lose track of which items remain.
- Always use repo-root-relative paths when referencing files (e.g. `src/cache/lru.ts:42`, not `lru.ts:42`).
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.