refactor
Use for refactoring — same behaviour, better structure. Test-coverage gate enforced. Extract-then-rename ordering. Refuses to mix in feature changes or bug fixes.
What this skill does
# refactor Same behaviour, better structure. Tests are the contract — they must stay green throughout. ## Method 1. **Coverage gate.** Read the test coverage of the area you're refactoring. **If < 80% line coverage of the target code, write tests first** until it is. Refactor without coverage = unsafe. 2. **Memory pass.** Has this area been refactored before? Reuse the lessons. 3. **Plan.** State the target shape (in < 100 words). State the smell being addressed (e.g. "long method", "feature envy", "shotgun surgery"). 4. **Mechanical sequence.** Refactor in this order: - **Extract** before **rename** before **move** - Each step is its own commit (or commit-shaped diff in a PR) - Run tests **after every step** 5. **Verify.** Tests green. Lint. Typecheck. Read your own diff — does it actually look better? ## Output shape ``` Target: <area: file/symbol> Smell: <which one> Goal shape: <one paragraph> Steps: 1. Extract <X> from <Y> ✓ tests green 2. Rename <A> → <B> ✓ tests green 3. Move <fn> to <module> ✓ tests green ... Verify: lint ✓ types ✓ tests ✓ (M passing, N before N after) ``` ## Rules - **Tests stay green.** If a test breaks, the refactor changed behaviour — that's a different workflow. - **No feature changes.** Spotted a bug or missing feature? Note in memory + suggest as follow-up. - **One smell per refactor.** Don't mix "long method" with "rename" with "move" in undisclosed ways. - **Mechanical.** If you can't describe the step in one verb + one noun, it's too big. ## Anti-patterns - "Refactor" that touches semantics (e.g. changing default values, error messages) - Big-bang refactor in one commit — impossible to review or revert - Renaming variables across 50 files when only the public API needs renaming - Refactor that increases line count without increasing clarity ## When NOT to use - Bug fix — `/siftcoder:fix` - Performance — `/siftcoder:optimize` - Aggressive simplification / deletion — `/siftcoder:zen` - New feature — `/siftcoder:add-feature` ## Subagent dispatch - `Explore` to map current shape - `Plan` for non-trivial multi-step refactors - `general-purpose` for the mechanical edits ## Value over native CC CC will refactor when asked. CC won't naturally insist on coverage gates, mechanical step ordering, or refuse to mix concerns. This skill enforces the discipline that makes refactors safe.
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.