Conciseness

The body is dense and directive with no padding — the anti-pattern section ('DO NOT write all tests first...') delivers non-obvious judgment efficiently. The Philosophy section spends three paragraphs explaining good vs. bad tests, some of which (mocking, private methods) Claude already knows, so it is not quite anchor 5's 'every token earns its place' but comfortably above anchor 3.

Actionability

As an instruction-only skill the guidance is concrete and executable: 'Write ONE test that confirms ONE thing', explicit rules ('Only enough code to pass current test', 'Never refactor while RED'), a per-cycle checklist, and a literal question to ask the user. It stays at anchor 4 rather than 5 because there is no worked example of a behavior-focused test, and the files that would have carried examples (tests.md, mocking.md) do not exist in the bundle.

Workflow Clarity

The sequence (Planning with user approval → Tracer Bullet → Incremental Loop → Refactor) is clearly staged, the RED→GREEN cycle is itself a validate→fix feedback loop, and checklists plus 'Run tests after each refactor step' provide checkpoints. It falls short of anchor 5 because there is no error-recovery guidance for a cycle that cannot reach GREEN (e.g., what to do when stuck).

Progressive Disclosure

The body links five files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md), but no bundle files exist at all — every reference is dangling, so navigation is broken despite the links being inline and clearly signaled. Scoring against the actual bundle structure, this lands at anchor 3 ('structure present but references do not enable navigation'), not anchor 4, whose references resolve.

Specificity

The description names the domain and one concrete practice ("Test-driven development with red-green-refactor loop") but lists no further specific actions like writing failing tests first or refactoring after green. This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') and falls short of anchor 4, which expects several specific actions.

Completeness

It explicitly answers both questions: the 'what' ("Test-driven development with red-green-refactor loop") and an explicit 'Use when...' clause with multiple concrete trigger phrases. This matches anchor 5; the 'when' clause is fully explicit, so anchor 4's caveat ('when could be more explicit') does not apply.

Trigger Term Quality

Natural trigger phrases are well covered: "build features or fix bugs using TDD", "mentions 'red-green-refactor'", "wants integration tests", "asks for test-first development". A few common variants are missing (e.g., 'write the tests first', 'unit tests'), so it fits anchor 4 rather than anchor 5's comprehensive synonym coverage, and is clearly above anchor 3's partial coverage.

Distinctiveness Conflict Risk

Triggers like 'red-green-refactor' and 'test-first development' carve out a clear TDD niche, but 'wants integration tests' overlaps with general testing skills. This is anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than anchor 5's minimal-conflict profile.