test-driven-development

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

Quality

47%

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

62%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.

The body delivers a clear, well-validated TDD workflow with strong executable examples, but is dragged down by redundant rhetorical reinforcement and broken references to missing bundle files.

Suggestions

Collapse 'Why Order Matters', 'Common Rationalizations', and 'Red Flags' into a single concise section — the same anti-rationalization points are made three times.

Either create the referenced @testing-anti-patterns.md and @testing-strategy.md files or remove the references, so navigation is not broken.

Replace the non-standard <Good>/<Bad> tags with markdown-friendly labels (e.g. bold '**Good:**' / '**Bad:**') so the contrasts render correctly.

Dimension	Reasoning	Score
Conciseness	The core cycle and examples are efficient, but the anti-rationalization message is rehashed three times ('Why Order Matters', 'Common Rationalizations' table, 'Red Flags' list), which is noticeably padded rhetoric Claude does not need.	2 / 5
Actionability	Concrete, executable Ruby/Rails code and bash commands with good/bad contrasts cover the common cases, but the non-standard <Good>/<Bad> pseudo-tags would be stripped by markdown renderers and the Rails-only framing is never acknowledged.	4 / 5
Workflow Clarity	Red-Green-Refactor is explicitly sequenced with mandatory 'Verify RED' and 'Verify GREEN' checkpoints, error-recovery feedback loops ('Test passes? Fix test.'), and a final verification checklist — fully matching the top anchor.	5 / 5
Progressive Disclosure	The file is well-sectioned but monolithic, and it signals one-level-deep references (@testing-anti-patterns.md, @testing-strategy.md) that point to files which do not exist in the bundle, leaving structure present but navigation partially broken.	3 / 5
	Total	14 / 20 Passed

Description

32%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.

The description functions as a trigger clause but omits the skill's core action (test-first development) and the distinctive 'TDD' terminology, leaving it broad and only half-complete.

Suggestions

State the 'what' explicitly, e.g. 'Drives test-driven development: write a failing test first, then minimal code to pass it.'

Add the distinctive trigger terms users actually say — 'TDD', 'test-driven development', 'write tests first' — so the skill surfaces for those queries.

Narrow the 'when' scope or tie it to the test-first behavior so it does not collide with every general coding skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ('implementing any feature or bugfix, before writing implementation code') but lists no concrete actions the skill performs — it never says it writes tests first or drives TDD, so it sits at 'names the domain, actions minimal/generic'.	2 / 5
Completeness	It provides only a 'when' clause and no 'what' — it never states the skill drives test-first development, matching the 'only when is present without what' anchor.	2 / 5
Trigger Term Quality	It includes natural phrases a user might say ('implementing any feature or bugfix', 'writing implementation code') but omits the most distinctive trigger terms ('TDD', 'test-driven', 'write tests first'), leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	'Any feature or bugfix' is maximally broad and would overlap with virtually any coding skill, matching the 'very broad; high overlap risk' anchor.	2 / 5
	Total	9 / 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: lucianghinda/superpowers-ruby
Path: skills/test-driven-development/SKILL.md
Commit: 99fac3d

Reviewed: 6 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.