Pre-refactor safety checklist. Verifies test coverage exists before AI modifies existing code. Use before asking AI to refactor anything.
npx skills add https://github.com/rshankras/claude-code-apple-skills --skill tdd-refactor-guard
A safety gate that runs before any AI-assisted refactoring. Ensures tests exist to catch regressions. If coverage is insufficient, generates characterization tests first.
Use this skill when the user:
Without guard: With guard:
"Claude, refactor this" "Claude, refactor this"
→ AI rewrites code → Guard checks for tests
→ Something breaks → Tests missing → generate them
→ You don't know what → Tests pass → proceed with refactor
→ Debugging nightmare → Tests fail → exact regression found
What code is being refactored?
Ask user: "Which files/classes are you planning to refactor?"
Or detect from context:
Glob: [files mentioned in conversation]
Read: each file to understand scope
Determine:
Grep: "class.*Tests.*XCTestCase|@Suite.*Tests|struct.*Tests" in test targets
Grep: "@Test|func test" that reference the classes being refactored
| Level | Criteria | Action |
|-------|----------|--------|
| Good (> 80%) | Most public methods have tests for happy + error paths | Proceed with refactoring |
| Partial (40-80%) | Some methods tested, missing edge cases | Add characterization tests for uncovered methods |
| Minimal (< 40%) | Few or no tests | Generate full characterization test suite first |
| None (0%) | No test file exists | STOP — create characterization tests before any refactoring |
Even if tests exist, check quality:
// ❌ Low-quality test — doesn't actually verify behavior
@Test("test items")
func testItems() {
let vm = ViewModel()
vm.loadItems()
#expect(true) // Always passes, tests nothing
}
// ❌ Tests implementation, not behavior
@Test("calls repository")
func testCallsRepo() {
let vm = ViewModel()
vm.loadItems()
#expect(mockRepo.fetchCallCount == 1) // Brittle
}
// ✅ Tests observable behavior
@Test("loads items into published array")
func testLoadsItems() async {
let vm = ViewModel(repo: MockRepo(items: [.sample]))
await vm.loadItems()
#expect(vm.items.count == 1)
#expect(vm.items.first?.title == "Sample")
}
Quality checklist:
#expect(true) or always-passing assertionsIf coverage is insufficient, use characterization-test-generator/:
Before refactoring [ClassName], generate characterization tests:
1. Read the source file
2. Identify all public methods
3. Generate tests that capture CURRENT behavior
4. Run and verify all pass
## Refactor Guard: ✅ PROCEED
**Files**: ItemManager.swift, ItemRepository.swift
**Test coverage**: Good (12 tests covering 8/9 public methods)
**Test quality**: Adequate — tests verify behavior, not implementation
Safe to refactor. Run tests after each change:
`xcodebuild test -scheme YourApp`
## Refactor Guard: ⚠️ NEEDS TESTS
**Files**: ItemManager.swift, ItemRepository.swift
**Test coverage**: Partial (5 tests covering 4/9 public methods)
**Missing coverage**:
- `ItemManager.sort()` — no test
- `ItemManager.filter(by:)` — no test
- `ItemRepository.sync()` — no test
- Error paths for `save()` and `delete()` — not tested
**Action**: Generate characterization tests for uncovered methods before refactoring.
Use `characterization-test-generator` skill.
## Refactor Guard: 🔴 STOP
**Files**: ItemManager.swift, ItemRepository.swift
**Test coverage**: None (0 tests found)
**Action**: Do NOT refactor until characterization tests exist.
Refactoring without tests is like surgery without monitoring —
you won't know if you killed the patient.
Run `characterization-test-generator` on:
1. ItemManager (7 public methods)
2. ItemRepository (5 public methods)
Then re-run this guard.
After refactoring is complete:
# Run all tests
xcodebuild test -scheme YourApp
# Check specifically for regressions
xcodebuild test -scheme YourApp \
-only-testing "YourAppTests/ItemManagerCharacterizationTests"
These typically don't change behavior:
These can change behavior:
Full contract tests recommended:
## Refactor Guard Report
**Scope**: [Files/classes to be refactored]
**Verdict**: ✅ PROCEED / ⚠️ NEEDS TESTS / 🔴 STOP
### Coverage Summary
| Class | Public Methods | Tests | Coverage | Verdict |
|-------|---------------|-------|----------|---------|
| ItemManager | 9 | 12 | 89% | ✅ |
| ItemRepository | 5 | 2 | 40% | ⚠️ |
### Missing Coverage
- [ ] `ItemRepository.sync()` — needs characterization test
- [ ] Error path for `ItemRepository.delete()` — untested
### Recommendations
1. [Action item]
2. [Action item]
testing/characterization-test-generator/ — generates tests this guard may requiretesting/tdd-feature/ — for building new code during refactorToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when implementing any feature or bugfix, before writing implementation code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Take rshankras/tdd-refactor-guard from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.