test-driven-dev

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/test-driven-dev/SKILL.md

The canonical home for this skill is tdd in mattpocock/skills

Quality

Content

67%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 well-structured, lean TDD methodology with a clear sequenced workflow and useful checklists. Its main weakness is progressive disclosure: five referenced files are missing from the bundle, leaving dangling links that Claude cannot follow.

Suggestions

Add the referenced bundle files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) under references/, or remove the links and inline the essential parts so there are no dead-end references.

Gather external references into a single clearly-signaled section (e.g. '## References') with one-level-deep links rather than scattering them mid-prose in Philosophy, Planning, and Refactor sections.

Add one short worked example of a behavior-style test (RED → GREEN) inline so the core loop is concrete and copy-paste ready without relying on the missing tests.md.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it does not explain what a test is or how libraries work — but the Philosophy and Anti-Pattern prose could be trimmed slightly, so it is not perfectly lean.	4 / 5
Actionability	Concrete, actionable guidance for an instruction-only skill: explicit rules ('Write ONE test that confirms ONE thing', 'Only enough code to pass current test') and checklists; a worked behavior-test example would make it fully copy-paste ready.	4 / 5
Workflow Clarity	A clearly sequenced workflow (Planning → Tracer Bullet → Incremental Loop → Refactor) with the RED→GREEN feedback loop, explicit checkpoints ('Run tests after each refactor step', 'Never refactor while RED'), and checklists; validation in the incremental loop is somewhat implicit (test pass/fail) rather than called out.	4 / 5
Progressive Disclosure	The body makes five inline references (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) to files that do not exist in any bundle directory, creating dead-end navigation; references are also scattered in prose rather than gathered in a signaled references section.	2 / 5
	Total	14 / 20 Passed

Description

78%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 strong, third-person description that clearly states both what the skill does and when to use it, with natural trigger terms and synonyms. The main gap is specificity — it names the method but not the concrete actions that comprise it.

Dimension	Reasoning	Score
Specificity	Names the domain ('Test-driven development with red-green-refactor loop') and one concrete action framing ('build features or fix bugs using TDD'), but does not enumerate the specific TDD actions (write failing test, implement minimal code, refactor), so coverage is not comprehensive.	3 / 5
Completeness	It explicitly answers both 'what' (TDD with red-green-refactor loop) and 'when' via a concrete 'Use when ... mentions "red-green-refactor", wants integration tests, or asks for test-first development' trigger clause.	5 / 5
Trigger Term Quality	Good natural keyword coverage including synonyms — 'TDD', 'red-green-refactor', 'integration tests', 'test-first development' — that users would naturally say; a few common variants (e.g. 'unit tests', 'test coverage') are missing, so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	TDD is a clear niche with distinctive triggers ('red-green-refactor', 'test-first'), but the broad 'build features or fix bugs' framing creates minor overlap risk with general coding skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/test-driven-dev/SKILL.md
Commit: 9d252b3

Reviewed: 2 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.