tdd

Red-Green-Refactor for changes with behavior or regression risk. Use when: adding observable behavior, fixing a bug, or changing logic not already covered by a precise executable check. Not for: pure docs/research, deterministic generated-artifact refreshes, or mechanical changes already covered by an existing checker. Output: observed RED (new test or existing failing check) → minimal GREEN → refactor under protection.

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

100%Weight 40%Scale 1-5

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

A tight, project-specific TDD skill that assumes Claude's competence and supplies only the non-obvious judgment rules — when RED already exists, when to skip new tests, how to route bugs. Workflow, examples, and validation checkpoints are all explicit.

Dimension	Reasoning	Score
Conciseness	Lean and dense; assumes Claude already knows Red-Green-Refactor and adds only project-specific judgment rules (no duplicate RED, reuse existing checkers, route unknown bugs to debugging), with every section earning its place.	5 / 5
Actionability	Gives concrete executable guidance — '先写测试，亲眼确认它以预期原因失败', a real command ('pnpm check:sop-definitions'), explicit RED/GREEN/REFACTOR branch handling, and concrete positive/negative/grey examples covering common cases.	5 / 5
Workflow Clarity	Clear Red-Green-Refactor sequence with explicit validation checkpoints and feedback loops ('RED 立即通过 → 先纠正测试', 'GREEN 让别的检查变红 → 停下修复回归', 'REFACTOR 后变红 → 回退'), plus an error→consequence→fix Common Mistakes table.	5 / 5
Progressive Disclosure	Self-contained ~60-line body with clear section headers and no bundle files needed; the only external link is a clearly signaled one-level-deep cross-skill pointer (bug-diagnosis-capsule.md), not a nested reference chain.	5 / 5
	Total	20 / 20 Passed

Description

92%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.

A precise, well-bounded description that clearly states what TDD does, when to use it, when not to, and what the output looks like. Trigger terms are natural and the niche is distinct from neighboring skills.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'adding observable behavior', 'fixing a bug', 'changing logic not already covered by a precise executable check' — plus a concrete RED→GREEN→refactor output pipeline, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Red-Green-Refactor for changes with behavior or regression risk') and when (explicit 'Use when:' trigger list), plus a 'Not for:' boundary clause and an 'Output:' shape — all with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('TDD', 'test first', '红绿重构', '写代码') and concrete 'Use when' phrases, but coverage leans slightly jargon-ward and a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear TDD niche with explicit 'Not for' exclusions (pure docs/research, deterministic artifact refreshes, mechanical changes already covered) and a risk-based gate, minimizing overlap with adjacent skills.	5 / 5
	Total	19 / 20 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: 090626a

Reviewed: ~23 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.