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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 and concrete examples. It would benefit from trimming motivational filler and either providing or removing the referenced bundle files so progressive disclosure is backed by real content.

Suggestions

Trim motivational content (the Beyonce Rule, the Common Rationalizations table, the 'superpower/liability' framing) that restates knowledge Claude already has.

Create the referenced `references/testing-patterns.md` and `browser-testing-with-devtools` files, or remove the dangling references, so progressive disclosure points to real material.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code examples, but motivational/philosophical padding ('a codebase with good tests is an AI agent's superpower; a codebase without tests is a liability', the Beyonce Rule, the Common Rationalizations table) restates attitudes Claude already holds and could be trimmed.	2 / 3
Actionability	Numerous complete, copy-paste-ready TypeScript examples (RED/GREEN/REFACTOR, the Prove-It pattern, good/bad test contrasts, Arrange-Act-Assert) plus a concrete command (`npm test`) and specific decision tables.	3 / 3
Workflow Clarity	Sequenced RED→GREEN→REFACTOR and Prove-It workflows carry explicit validation checkpoints ('Run tests after every refactor step', 'Test FAILS confirming the bug exists'), feedback loops, and a final verification checklist.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but it references `references/testing-patterns.md` and `browser-testing-with-devtools` which do not exist as bundle files, leaving dangling references alongside substantial inline content that could be split out.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 trigger-rich description that clearly answers both what and when using natural keywords. Its main weakness is second-person phrasing and a single abstract action rather than a list of concrete capabilities, the latter compounded by the rubric's voice penalty.

Suggestions

Rewrite in third person / impersonal imperative: replace 'Use when you need to prove...' and 'when you're about to modify...' with 'Use when proving code works...' to avoid the second-person specificity penalty.

List concrete capabilities instead of one abstract action, e.g. 'Write failing tests first, reproduce bugs with tests, and refactor under a green suite.'

Dimension	Reasoning	Score
Specificity	Opens with a third-person action ('Drives development with tests') that names the TDD domain, but it lists only one abstract action rather than multiple concrete capabilities, and the second-person phrasing ('you need to prove...', 'you're about to modify...') triggers the rubric's -1 specificity penalty.	1 / 3
Completeness	Explicitly states what ('Drives development with tests') and when via two explicit 'Use when' clauses, satisfying the rubric's requirement for explicit trigger guidance (no cap at 2).	3 / 3
Trigger Term Quality	Natural phrases a user would actually say — 'implementing any logic', 'fixing any bug', 'modify existing functionality', 'bug report arrives' — with good coverage spread across two 'Use when' clauses.	3 / 3
Distinctiveness Conflict Risk	TDD is a clear niche, but the triggers ('implementing any logic', 'fixing any bug', 'changing any behavior') are broad enough to overlap with general coding skills.	2 / 3
	Total	9 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: addyosmani/agent-skills
Commit: 70b7506

Reviewed: 3 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.