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

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is test-driven-development in addyosmani/agent-skills

Quality

Content

77%Scale 1-3

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

This is a comprehensive, highly actionable TDD skill with excellent workflow clarity and concrete executable examples. Its main weakness is verbosity — it includes philosophical justifications (Common Rationalizations), well-known testing concepts (test pyramid, Beyoncé Rule), and extensive inline content that could be offloaded to referenced files. The skill would benefit from trimming content Claude already knows and better leveraging progressive disclosure to keep the main file focused.

Suggestions

Move the 'Common Rationalizations' table, 'Test Anti-Patterns' table, and 'Browser Testing with DevTools' section into separate referenced files to reduce the main SKILL.md to its essential workflow and patterns.

Remove or drastically shorten explanations of concepts Claude already knows well (test pyramid rationale, why TDD matters, the Beyoncé Rule) — a brief mention with a reference is sufficient.

Dimension	Reasoning	Score
Conciseness	The skill is well-written but verbose for its audience. Sections like 'Common Rationalizations', the test pyramid explanation, the Beyoncé Rule, and general TDD philosophy are concepts Claude already knows well. The ASCII diagrams are nice but add tokens. The core actionable content could be delivered in roughly half the space.	2 / 3
Actionability	Excellent actionable content throughout — executable TypeScript examples for every pattern (RED/GREEN/REFACTOR, Prove-It, Arrange-Act-Assert), concrete anti-pattern tables with fixes, specific verification checklists, and clear decision guides. Code examples are complete and copy-paste ready.	3 / 3
Workflow Clarity	The TDD cycle is clearly sequenced with explicit validation at each step (test fails → code passes → refactor with tests still passing). The Prove-It Pattern for bug fixes includes a clear flow with validation checkpoints. The verification checklist at the end provides a final validation gate. The DevTools debugging workflow also follows a clear sequence with verification.	3 / 3
Progressive Disclosure	References to `browser-testing-with-devtools` and `references/testing-patterns.md` are mentioned but no bundle files are provided, making it impossible to verify these exist. The SKILL.md itself is quite long (~300 lines) and could benefit from moving the test pyramid details, anti-patterns table, and browser testing section into separate referenced files rather than inlining everything.	2 / 3
	Total	10 / 12 Passed

Description

49%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 has strong completeness with explicit 'Use when' clauses but suffers from being overly broad and vague. Its triggers would fire on almost any development task, creating high conflict risk with other skills. The 'what' portion lacks concrete actions — it says 'drives development with tests' but doesn't specify what test-related operations it actually performs.

Suggestions

Add specific concrete actions like 'Writes unit tests, generates test fixtures, runs test suites, measures code coverage' to replace the vague 'drives development with tests'.

Narrow the trigger conditions — instead of 'implementing any logic' or 'fixing any bug', specify when test-driven approaches are specifically needed, e.g., 'Use when the user asks for TDD, test coverage, or wants tests written before implementation'.

Add distinctive trigger terms like 'TDD', 'test-driven', 'unit test', 'integration test', 'test coverage', 'pytest', 'jest' to differentiate from general coding skills.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'drives development with tests' without listing concrete actions. It doesn't specify what kind of tests, what frameworks, or what specific operations (e.g., 'write unit tests', 'run test suites', 'generate test fixtures'). The actions are abstract rather than concrete.	1 / 3
Completeness	The description answers both 'what' (drives development with tests) and 'when' with explicit trigger conditions: implementing logic, fixing bugs, changing behavior, proving code works, bug reports arriving, or modifying existing functionality. The 'Use when...' clauses are clearly present and detailed.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'tests', 'bug', 'logic', 'fix', and 'behavior' that users might naturally use. However, it misses common variations like 'unit test', 'TDD', 'test-driven', 'test suite', 'assertion', 'coverage', or specific testing framework names.	2 / 3
Distinctiveness Conflict Risk	The triggers are extremely broad — 'implementing any logic', 'fixing any bug', 'changing any behavior' would match virtually every coding task. This would conflict with nearly any development-related skill, as it claims applicability to all logic implementation and bug fixes.	1 / 3
	Total	7 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: finlay611/agent-skills
Path: skills/test-driven-development/SKILL.md
Commit: b765343

Reviewed: 4 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.