test-driven-development

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Quality

78%

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-development/SKILL.md

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 thorough, highly actionable TDD skill with clear sequenced workflows, executable examples, and strong validation checkpoints. Its main limitation is length: several widely-known testing concepts could be trimmed to respect the context budget.

Suggestions

Trim or collapse the sections on well-known concepts (Test Pyramid, DAMP over DRY, Arrange-Act-Assert, One Assertion Per Concept) into a brief pointer plus one example each, since Claude already knows these.

Move the Browser Testing with DevTools section fully behind its referenced skill (browser-testing-with-devtools) and keep only a one-line trigger for when to use it.

Consider splitting the JS/TS-specific examples into the already-referenced testing-patterns.md so SKILL.md stays a language-agnostic overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but at ~390 lines it re-explains well-known concepts (the test pyramid, DAMP over DRY, Arrange-Act-Assert, one-assertion-per-concept) that Claude already knows and could be trimmed.	3 / 5
Actionability	Copy-paste ready TypeScript/Jest examples for RED/GREEN/REFACTOR and the Prove-It pattern, concrete repo commands (./gradlew, pytest, go test), and the TS-only scope is explicitly justified, matching the fully-executable anchor.	5 / 5
Workflow Clarity	RED -> GREEN -> REFACTOR and the Prove-It flow are clearly sequenced with explicit validation checkpoints (run tests after every refactor, full suite before completion) and a final verification checklist with error-recovery feedback loops.	5 / 5
Progressive Disclosure	Well-organized sections with one-level, clearly signaled references (browser-testing-with-devtools, ../../references/testing-patterns.md); no bundle files exist to verify, and the browser-testing material is partially inlined rather than fully split out.	4 / 5
	Total	17 / 20 Passed

Description

75%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, complete description with explicit what-and-when guidance and natural trigger phrases. Its main weakness is broad triggers that risk overlap with general development skills and a single generic capability statement.

Suggestions

Tighten the capability statement from the generic "Drives development with tests" to 2-3 concrete actions (e.g., 'Writes failing tests before implementation, reproduces bugs with regression tests, and refactors under green tests').

Narrow the triggers so the skill is less likely to fire for routine edits (e.g., lead with 'Use when a change could break existing behavior or when a bug must be proven fixed before the fix ships').

Add a domain signal or synonym (e.g., 'test-first' / 'red-green-refactor') to improve distinctiveness against general coding skills.

Dimension	Reasoning	Score
Specificity	Names the domain and one generic action ("Drives development with tests") but does not enumerate multiple specific concrete actions, fitting the 'names domain and 1-2 concrete actions' anchor rather than the comprehensive 5.	3 / 5
Completeness	Explicitly answers both what ("Drives development with tests") and when with two concrete "Use when..." trigger clauses, matching the anchor for clearly answering both what and when.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ("fixing any bug", "bug report arrives", "modify existing functionality", "prove that code works"); a few synonyms or ecosystem-specific terms are missing, so it sits just below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The TDD niche is distinct, but triggers like "implementing any logic" and "changing any behavior" are broad and overlap with general coding skills, so it could still collide with related skills.	3 / 5
	Total	15 / 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: addyosmani/agent-skills
Path: skills/test-driven-development/SKILL.md
Commit: df1edb2

Reviewed: about 19 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.