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

84%

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

81%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 lean, well-structured decision-routing skill: an explicit risk-entry table, a clearly sequenced cycle with failure-mode recovery rules, and concrete positive/negative/gray examples. Main weaknesses are mild redundancy of the duplicate-RED rule across sections and one external reference that does not resolve.

Suggestions

State the 'no duplicate RED for deterministic artifacts' rule once (e.g., in RED 来源) and let the 风险入口 table and 正反灰例 refer to it, trimming roughly a paragraph of repetition.

Add a minimal executable RED example (2-3 lines of a failing test invocation) so the GREEN step has a concrete template, and resolve or inline the dangling '../.cat-cafe-shared-refs/bug-diagnosis-capsule.md' reference.

Give paths or one-line pointers for the referenced 'debugging', 'quality-gate', and 'Harness Diet' artifacts so navigation does not depend on unstated environment knowledge.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence (no explanation of what TDD or testing is), but the rule 'don't stack a second equivalent RED for deterministic artifacts' is repeated across four sections (风险入口, RED 来源, 正反灰例, Common Mistakes), which could be trimmed. Not a 5 because of that redundancy; not a 3 because nothing is padding or concepts Claude already knows.	4 / 5
Actionability	Gives a concrete change-type routing table, a named command example ('pnpm check:sop-definitions'), and specific if-then recovery rules, which is actionable guidance for an instruction-only skill. Not a 5 because no executable example of a RED test or command sequence is shown, and environment-specific terms ('Harness Diet fix-forward', 'quality-gate 车道') are used without pointers.	4 / 5
Workflow Clarity	The RED → GREEN → REFACTOR cycle is explicitly sequenced with validation checkpoints and error-recovery 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：回退这次重构'), matching the top anchor including recovery loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is well-organized into clear sections that appropriately inline the decision content. The gap: the single external reference '../.cat-cafe-shared-refs/bug-diagnosis-capsule.md' does not resolve in this environment and 'debugging'/'quality-gate' are named without paths, leaving navigation partially dangling.	4 / 5
	Total	17 / 20 Passed

Description

87%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 tight, third-person description that states the workflow, explicit use conditions, and explicit exclusions. The only soft spot is that capability language is process-level ('RED → GREEN → refactor') rather than a broader inventory of concrete actions, and a few natural trigger synonyms are absent.

Dimension	Reasoning	Score
Specificity	Names the domain ('Red-Green-Refactor for changes with behavior or regression risk') and concrete actions ('observed RED (new test or existing failing check) → minimal GREEN → refactor under protection'), but the actions are process stages rather than a comprehensive list of specific operations, so it sits between the 3 and 5 anchors.	4 / 5
Completeness	Explicitly answers both what ('Red-Green-Refactor... Output: observed RED → minimal GREEN → refactor under protection') and when ('Use when: adding observable behavior, fixing a bug, or changing logic not already covered by a precise executable check'), and adds explicit 'Not for' exclusions — a clear match to the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say such as 'fixing a bug', 'adding observable behavior', 'regression risk', and 'Red-Green-Refactor' (plus frontmatter triggers 'TDD', 'test first'), but misses common variations like 'write tests', 'unit test', or 'test coverage'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (RED-first behavior protection) with distinct triggers and an explicit exclusion clause ('Not for: pure docs/research, deterministic generated-artifact refreshes, or mechanical changes already covered by an existing checker') that minimizes overlap with docs, formatting, or general testing skills.	5 / 5
	Total	18 / 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: 61389cc

Reviewed: 2 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.