tdd

Red-Green-Refactor 测试驱动开发纪律。 Use when: 写新功能代码、修 bug、任何实现工作。 Not for: 纯文档、纯调研、已有充分测试的 trivial 改动。 Output: 失败测试 → 最小实现 → 重构，全程有测试保护。

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, highly actionable discipline skill with clear sequenced workflows, explicit validation checkpoints, and concrete decision rules. The one weakness is progressive disclosure: the sole external reference points to a missing file, breaking navigation.

Suggestions

Add the missing ../refs/bug-diagnosis-capsule.md file (or move the diagnosis-capsule template inline) so the body's only external link resolves.

If the capsule template is short, inline it under the Bug Fix 模式 section to make the skill fully self-contained and avoid the broken cross-file reference.

Verify any other referenced paths (e.g. the 'quality-gate' skill pointer) resolve before relying on them for handoff navigation.

Dimension	Reasoning	Score
Conciseness	The body is dense and terse — tables, short bullets, and compact flow diagrams — and avoids explaining basic concepts Claude already knows; the objection-rebuttal and rationalization sections earn their place as discipline-enforcement rather than generic padding, fitting the 'lean, every token earns its place' anchor.	3 / 3
Actionability	Guidance is concrete and specific: explicit decision rules ('RED 阶段测试立即通过？→ 你在测已有行为，修测试'), a numbered bug-fix checklist, and exact red-flag phrases with a concrete action ('删掉代码，从测试重新开始'); per the scoring note, absence of executable code in this instruction/discipline skill is not penalized because the guidance is actionable.	3 / 3
Workflow Clarity	The Red-Green-Refactor cycle and the main flow diagram are clearly sequenced with explicit validation checkpoints ('必须亲眼看到它失败' / '必须亲眼看到它通过') and error-recovery feedback loops (REFACTOR 后变红 → 撤销重来), matching the 'clear sequence with explicit validation and feedback loops' anchor.	3 / 3
Progressive Disclosure	Sections are well-organized and the one external reference is correctly signaled one-level-deep, but the link target [refs/bug-diagnosis-capsule.md](../refs/bug-diagnosis-capsule.md) does not exist — no refs/ directory is present — so navigation is broken; it falls short of the level-3 'easy navigation' anchor without being a monolithic wall of text (level 1).	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is well-crafted: it states concrete actions, gives an explicit Use when trigger set, includes a Not for exclusion list, and uses third-person voice. It clearly answers both what and when with natural, non-conflicting trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "失败测试 → 最小实现 → 重构" and "全程有测试保护" — naming the domain (测试驱动开发) and the specific steps, matching the 'lists multiple specific concrete actions' anchor rather than the 'some actions' level 2.	3 / 3
Completeness	Explicitly answers both what ("Red-Green-Refactor 测试驱动开发纪律" / Output line) and when (explicit 'Use when:' clause with triggers), and is not capped at 2 because an explicit trigger clause is present; voice is third-person, so no specificity penalty applies.	3 / 3
Trigger Term Quality	The 'Use when:' clause supplies natural terms users actually say — "写新功能代码", "修 bug", plus 'Red-Green-Refactor' and 'TDD' — giving good coverage of natural variations rather than only jargon or a single phrase.	3 / 3
Distinctiveness Conflict Risk	A clear TDD niche with distinct triggers and an explicit 'Not for:' exclusion list (纯文档、纯调研、已有充分测试的 trivial 改动) lowers conflict risk; it is more distinguishable than the 'somewhat specific but could overlap' level 2 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/tdd/SKILL.md
Commit: 80782c5

Reviewed: 11 days 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.