summarize-pr-reviews
Summarize GitHub pull requests awaiting your review with status, age, and priority. Use when triaging your review queue, prioritizing code reviews, or checking what PRs need attention.
What this skill does
# Summarize My PR Review Queue Fetch all GitHub pull requests where the current user is requested as a reviewer, summarize the changes, and provide prioritization recommendations. ## Workflow 1. **Get user identity** - Identify the current GitHub user 2. **Search for review requests** - Query GitHub for PRs requesting the user's review 3. **Fetch PR details** - Get diff stats, reviews, CI status, and context for each PR 4. **Analyze and categorize** - Size, priority, and complexity assessment 5. **Generate summary** - Present a clear overview with prioritization recommendations ## Step 1: Get User Identity Identify the authenticated GitHub user's login. ## Step 2: Search for PRs Requesting Review Search for open PRs where the user is requested as a reviewer, sorted by most recently updated. Run both queries in parallel: - **Primary:** Open PRs awaiting your review - **Secondary:** Open PRs you've already reviewed but haven't approved (may have new changes) If the user asks about a specific org or repo, scope the search accordingly. ## Step 3: Fetch PR Details For each PR found, fetch in parallel: metadata (title, author, labels, created date), files changed (count, lines added/deleted, key paths), existing reviews and their states, and CI/check status. Extract from each PR: - Title and description - Author - Number of files changed, lines added/deleted - Labels (especially priority, urgent, blocker, critical) - How long it's been open - CI/check status (passing, failing, pending) - Existing reviews and their states (approved, changes requested, commented) ## Step 4: Analyze and Categorize ### Size Categories | Size | Criteria | Review Time Estimate | |------|----------|---------------------| | ๐ข **Small** | <100 lines changed, <5 files | ~10-15 min | | ๐ก **Medium** | 100-500 lines, 5-15 files | ~30-60 min | | ๐ด **Large** | >500 lines or >15 files | 1+ hours | ### Priority Signals Flag PRs as high-priority when: - Labeled `priority`, `urgent`, `blocker`, or `critical` - Open >3 days without any review - Author has pinged or requested re-review - Blocking other work (mentioned in description) - Failing CI that needs investigation - Security fix or hotfix ### Complexity Indicators Note when PRs involve: - Multiple reviewers requested - Files spread across different areas of the codebase - New dependencies added - Database migrations or API changes - Configuration or infrastructure changes ## Step 5: Generate Summary Structure the output in this order. Adapt detail level to queue size: full detail for <5 PRs, grouped summaries for 5-15, top priorities only for >15. ### At a Glance Open with a quick snapshot: - Total PRs awaiting review - Breakdown by size (small / medium / large) - Oldest PR waiting ### Priority Reviews (Address First) Table of PRs that are urgent, stale (>3 days without review), security/hotfix, or blocking others. Include a "Why Priority" column. For each priority PR, provide a detail block: - **Repository** and **Author** - **Changes:** `+X/-Y` lines across N files - **Summary of Changes:** Brief description from title, description, and files changed - **Key files to review:** Top 2-3 files with brief explanation - **Review notes:** CI failures, existing review comments, blockers ### Standard Reviews Remaining PRs in suggested review order. Table with PR number, repository, author, size, wait time, and notes. Detail blocks for each. ### Quick Reviews (Small PRs) Compact table of small PRs that can be knocked out quickly โ good for short time blocks. ### Needs Attention Flag concerning patterns: - **Stale PRs:** Open >7 days without review - **Failed CI:** PRs with failing checks - **Re-review requested:** PRs you reviewed but have new commits ### Suggested Review Order Numbered list combining priority, size, and wait time into a recommended sequence. End with an estimated total review time. ## Tips for Quality Summaries **Understand the changes:** - Read the PR description carefully - Look at file types changed to understand scope - Note if tests are included **Identify what matters:** - Focus on the "why" not just the "what" - Highlight breaking changes or API modifications - Note new dependencies or configuration changes **Make it actionable:** - Suggest a specific review order - Estimate review time for planning - Flag PRs that can be quick wins **Provide context:** - Link directly to each PR with full URL - Show how long PRs have been waiting - Note if CI is passing/failing **Adapt to queue size:** - For <5 PRs: Detailed summary of each - For 5-15 PRs: Group by priority, summarize key points - For >15 PRs: Focus on top priorities, list others briefly
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.