org-maintenance
Clean up stale worktrees and help stuck PRs across an org's repos
What this skill does
# Org Maintenance
Clean up dead worktrees and unstick PRs across repos in an org.
Run from `~/code/{org}/` or pass the org name as an argument.
## Accounts
Read `bot_account`, `owner_account` from the org's CLAUDE.md `## Automation config` table.
## Helper script
A pre-built script at `~/.claude/scripts/org-maintenance.sh` collects worktree and PR data in one pass.
Run it first to avoid spending tokens on individual `git` and `gh` calls.
```bash
~/.claude/scripts/org-maintenance.sh <org-name> > /tmp/org-maintenance.json
```
If the script is missing or not executable, flag this to the user and stop.
The script outputs a JSON object with:
- `worktrees`: array of non-main worktrees per repo (path, branch, whether directory exists)
- `open_prs`: array of open PRs by the bot/owner accounts with CI status, review decision, merge info
## Phase 1: Worktree Audit
From the script output, flag worktrees that:
1. Point to missing directories (`exists: false`)
2. Have branches merged or deleted on the remote
3. Have no commits in 30+ days and no uncommitted changes
Present a summary table and prune with confirmation.
## Phase 2: Stuck PR Audit
From the script output, identify PRs that are stuck:
- CI status (failing checks)
- Review status (changes requested, unreviewed)
- Time since last update
- Merge conflicts
### What to fix
**For bot/owner PRs** (full access):
- Fix failing CI (linting errors, test failures, docs issues)
- Resolve merge conflicts
- Address review comments where the fix is mechanical
- Push fixes directly to the PR branch
**For PRs on other people's repos**:
- Open a new PR addressing linting, docs, or test coverage gaps only
- Make it clear in the PR description that suggestions are optional
- Do not touch architectural or behavioural changes
### What NOT to fix
- Design decisions or API changes
- Anything requiring domain knowledge beyond the code itself
- PRs with ongoing discussion (don't interrupt)
## Phase 3: Team mode
If more than 3 PRs need attention, spawn a team.
Each teammate handles one PR fix.
The lead tracks progress and reports results.
## Phase 4: Summary
Report:
- Worktrees pruned (count by repo)
- PRs fixed (with links)
- PRs skipped (with reason)
## Auto-Exit When Standalone
**IMPORTANT**: If this command is being run as a standalone request, automatically exit after completing all phases successfully.
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.