test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Quality

58%

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 ./plugins/superpowers/skills/test-driven-development/SKILL.md

The canonical home for this skill is jbvc/test-driven-development

Quality

Content

77%

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

The body is highly actionable with a clear, well-validated workflow, but it carries redundant motivational material and a broken cross-file reference. Trimming the repeated rationalizations and fixing or removing the missing reference would materially improve it.

Suggestions

Consolidate the three overlapping anti-rationalization sections ('Why Order Matters', 'Common Rationalizations', 'Red Flags') into a single concise block.

Fix the broken `@testing-anti-patterns.md` reference by adding the file or removing the pointer.

Consider splitting the lengthy worked examples and anti-patterns into a reference file to shorten the main body.

Dimension	Reasoning	Score
Conciseness	The procedural sections are lean, but the same anti-rationalization message is restated three times across 'Why Order Matters', the 'Common Rationalizations' table, and the 'Red Flags' list, which could be consolidated.	2 / 3
Actionability	It gives executable TypeScript test snippets, concrete `npm test path/to/test.test.ts` commands, Good/Bad code pairs, and a complete bug-fix worked example that is copy-paste ready.	3 / 3
Workflow Clarity	The Red-Green-Refactor cycle is explicitly sequenced with mandatory 'Verify RED' and 'Verify GREEN' checkpoints and clear error-recovery feedback loops (test passes? fix the test; errors? fix and re-run).	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic ~370-line file and references `@testing-anti-patterns.md` (line 359) which does not exist in any bundle directory, so the reference is broken.	2 / 3
	Total	10 / 12 Passed

Description

40%

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 provides a clear usage trigger but omits what the skill does and lacks the core test/TDD vocabulary. It reads as a pure 'when' clause rather than a what-plus-when statement.

Suggestions

Add the 'what': state the concrete action, e.g. 'Write a failing test first, watch it fail, then write minimal code to pass it.'

Include the trigger vocabulary users actually say — 'tests', 'TDD', 'test-driven', 'write tests first' — alongside 'feature or bugfix'.

Tighten distinctiveness by anchoring on the test-first behavior rather than the generic 'implementing any feature'.

Dimension	Reasoning	Score
Specificity	The description states only when to use the skill ('before writing implementation code') without naming any concrete actions such as writing tests, watching them fail, or writing minimal code.	1 / 3
Completeness	It has an explicit 'Use when...' trigger for the 'when', but never states the 'what' — what the skill actually does — so only one of the two required halves is present.	2 / 3
Trigger Term Quality	'feature or bugfix' and 'writing implementation code' are natural terms users say, but the central vocabulary ('test', 'tests', 'TDD') is entirely absent.	2 / 3
Distinctiveness Conflict Risk	'implementing any feature or bugfix' is broad enough to overlap with general coding skills, though the 'before writing implementation code' clause adds some narrowing.	2 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/superpowers/skills/test-driven-development/SKILL.md
Commit: 11c74d6

Reviewed: about 10 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.