The body is a model instruction-only skill: lean, fully executable, with explicit STOP/validation checkpoints and error-recovery loops at every stage of the red-green cycle. It delegates project conventions to existing files rather than restating them, keeping every token load-bearing.

Dimension	Reasoning	Score
Conciseness	Every line is an executable instruction ("run `npm test`", "Write the Gherkin scenario in `tests/features/<name>.feature`") with zero concept explanations or padding; the step-7 sub-bullets ("Stateful behaviour inside `boot()` as closures", "Route dataset data through `StateManager`") convey repo-specific knowledge Claude cannot infer. This matches 'lean and efficient; every token earns its place'.	5 / 5
Actionability	The body provides concrete commands (`npm test`, `npm run check`), exact file paths (`tests/features/<name>.feature`, `tests/e2e/<name>.spec.js`, `src/app.js`), and a concrete import location (`tests/support/helpers.js`). As an instruction-only skill with fully executable, copy-paste-ready guidance, it matches the top anchor; per the scoring notes, absence of code is not penalized here.	5 / 5
Workflow Clarity	The 10-step sequence includes explicit validation checkpoints and feedback loops: step 2 ("If it fails, stop and report"), step 4 ("STOP — ... wait for explicit approval"), step 6 ("If it passes already, the test is wrong — stop and report"), and step 9's fix-violations loop. This matches 'clear sequence with explicit validation steps; feedback loops for error recovery'. No cap applies since the operations are additive, not destructive or batch.	5 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, with no bundle files; it is one well-ordered numbered list and delegates repo conventions to existing project files (CLAUDE.md, tests/CLAUDE.md, src/CLAUDE.md) instead of duplicating them. Per the guideline for skills under 50 lines with no need for external references, well-organized content scores 5.	5 / 5
	Total	20 / 20 Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill does and is well anchored to a specific project and workflow, giving it good specificity and distinctiveness. Its main weakness is the absence of any 'Use when...' trigger clause and missing natural synonyms (e.g., spelling out "test-driven development"), which caps completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to start a new feature, begin a TDD cycle, or implement the next feature on wheel-of-meeting."

Spell out "test-driven development" alongside "TDD" and include natural synonyms such as "red/green cycle" or "write a failing test first" to improve trigger-term coverage.

Briefly mention the validation loop (failing test verified before implementation, full suite green afterwards) to round out the action coverage.

Dimension	Reasoning	Score
Specificity	"Start a new TDD feature cycle for wheel-of-meeting. Guides strictly through Gherkin → failing test → implement → green suite" names the domain and several concrete actions (Gherkin scenario, failing test, implementation, green suite), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the compressed arrow chain omits other cycle stages (e.g., the lint/check and verification steps), and exceeds 3 because it lists more than 1-2 actions.	4 / 5
Completeness	The "what" is clearly stated ("Start a new TDD feature cycle... Guides strictly through Gherkin → failing test → implement → green suite"), but there is no "Use when..." clause or any explicit trigger guidance — the "when" is at best weakly implied. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like "TDD", "Gherkin", "failing test", and "green suite" are relevant, but common natural variations are missing: "test-driven development" is never spelled out, and phrases like "red/green/refactor" or "write a test first" are absent. This matches 'some relevant keywords but missing common variations or synonyms' rather than the good coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The description is anchored to a specific project ("wheel-of-meeting") and a specific workflow vocabulary (Gherkin, failing test, green suite), making it mostly distinct with only minor overlap risk against generic testing skills. It is not 5 because it lacks explicit distinct trigger phrases that would fully minimize conflict risk.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: koenighotze/wheel-of-meeting
Path: .claude/skills/tdd-cycle/SKILL.md
Commit: 4aca8e3

Reviewed: 16 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.