test-driven-development

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

Quality

65%

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

The canonical home for this skill is test-driven-development in obra/superpowers

Quality

Content

77%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 is highly actionable and the TDD workflow is sequenced with strong validation checkpoints and feedback loops. Its main weaknesses are repetitive anti-rationalization padding and a missing referenced bundle file.

Suggestions

Collapse the redundant rationalization material in "The Iron Law", "Why Order Matters", "Common Rationalizations", and "Red Flags" into a single section to reduce token cost.

Create the referenced references/testing-anti-patterns.md (or remove the @reference) so the signaled navigation target actually exists.

Consider moving the large rationalization/anti-pattern content into a separate reference file, keeping SKILL.md as a lean overview of the cycle.

Dimension	Reasoning	Score
Conciseness	Most sections are dense and skip basic explanations Claude already knows, but the same anti-rationalization message is repeated across "The Iron Law", "Why Order Matters", "Common Rationalizations", and "Red Flags", which could be tightened into one.	3 / 5
Actionability	It provides copy-paste-ready, executable TypeScript examples and concrete commands ("npm test path/to/test.test.ts") covering the common RED/GREEN/REFACTOR cases with both good and bad variants.	5 / 5
Workflow Clarity	The Red-Green-Refactor cycle is clearly sequenced with mandatory validation checkpoints ("Verify RED - Watch It Fail", "Verify GREEN"), explicit feedback loops for failure recovery, and a final verification checklist.	5 / 5
Progressive Disclosure	Section headers give reasonable structure, but the document is a long monolith and its one signaled reference, "@testing-anti-patterns.md", does not exist in the bundle, leaving a dangling navigation pointer.	3 / 5
	Total	16 / 20 Passed

Description

53%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 is concise with a clear, natural trigger clause, but it omits what the skill actually does and uses an overly broad trigger that overlaps with most coding tasks. It reads as a "when" with the "what" left implicit.

Suggestions

Add an explicit "what" clause stating the skill's action, e.g. "Write the failing test first, then minimal code to pass it."

Narrow the trigger so it is distinguishable from general coding skills, e.g. tie it to test-writing intent rather than "any feature or bugfix".

Include test-specific trigger terms ("write tests", "TDD", "test-first") so users who phrase the need in testing language still surface the skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ("implementing any feature or bugfix") and conveys a concrete timing directive ("before writing implementation code"), but never states the skill's actual action (write the failing test first); actions are minimal rather than comprehensive.	3 / 5
Completeness	It has an explicit, specific "when" ("Use when implementing any feature or bugfix, before writing implementation code") but only a weakly implied "what" — the skill's behavior must be inferred from the name rather than stated, so it sits between the "only when" and "both what and when" anchors.	3 / 5
Trigger Term Quality	It uses natural phrases a user would say ("implementing any feature or bugfix", "implementation code"), giving good keyword coverage, though test-specific synonyms like "test", "TDD", or "write tests" are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger "any feature or bugfix" is very broad and would fire for nearly all coding work, creating high overlap risk with general implementation, refactoring, and bugfix skills despite TDD itself being a distinct methodology.	2 / 5
	Total	12 / 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: roman01la/skills-agents
Path: skills/test-driven-development/SKILL.md
Commit: aa6f9d3

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.