test-driven-development

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

1.00x

Quality

56%

Does it follow best practices?

Impact

100%

1.00x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./eval/local/skills/benchmarks/dependency/superpowers/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 excels at workflow clarity with mandatory validation checkpoints, feedback loops, and a checklist. Its weak spots are conciseness (voluminous anti-rationalization padding) and progressive disclosure (a broken external reference plus large inline sections).

Suggestions

Trim or relocate the 'Why Order Matters', 'Common Rationalizations', and 'Red Flags' sections into a separate reference file to cut ~80 lines of persuasive padding from the core.

Fix the dangling reference: either create testing-anti-patterns.md in a references/ bundle or remove the link, so the signaled navigation actually resolves.

Keep the RED/GREEN/REFACTOR core and worked examples up front as the lean quick-start, moving the rationalization rebuttals behind a clearly signaled one-level-deep reference.

Dimension	Reasoning	Score
Conciseness	The RED/GREEN/REFACTOR core and examples are lean, but three large sections (Why Order Matters, Common Rationalizations, Red Flags) are persuasive padding that could be trimmed, fitting 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because the instructional core is tight and the padding is functional discipline reinforcement rather than concept over-explanation, not a 4 because the padding exceeds 'minor'.	3 / 5
Actionability	Executable TypeScript and bash examples (retry test, retryOperation, submitForm bugfix, 'npm test path/to/test.test.ts') are copy-paste ready and cover both a feature and a bugfix case, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The RED -> Verify RED -> GREEN -> Verify GREEN -> REFACTOR -> Repeat cycle has explicit mandatory validation checkpoints, feedback loops ('Test fails? Fix code, not test', 'Test passes? ... Fix test'), and a verification checklist, matching 'Clear sequence with explicit validation steps; feedback loops for error recovery; checklists'.	5 / 5
Progressive Disclosure	Section structure is good, but the only external reference (testing-anti-patterns.md) is a broken link (no such file exists) and large persuasive blocks are inlined rather than split out, fitting 'Some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline'; not a 2 because structure is not minimal, not a 4 because the broken reference and inline bulk prevent it.	3 / 5
	Total	16 / 20 Passed

Description

36%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 provides a clear 'when' trigger with natural keywords but omits the 'what' entirely and never mentions testing/TDD, leaving it broad and low on specificity. It reads as a trigger clause with no capability statement.

Suggestions

Lead with the 'what': state the concrete action, e.g. 'Write a failing test first, then minimal code to pass it (TDD)' before the 'Use when' clause.

Add core trigger synonyms so users saying 'test-drive', 'TDD', or 'write tests first' match the skill.

Narrow the trigger scope (e.g. 'when implementing production features or bugfixes in code with a test runner') to reduce overlap with refactoring or code-review skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('implementing any feature or bugfix') but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'; it is not a 1 because the domain is named, and not a 3 because no concrete actions are stated.	2 / 5
Completeness	Only the 'when' is present ('Use when implementing any feature or bugfix, before writing implementation code'); the 'what' (write tests first, run the TDD cycle) is never stated, matching 'only when is present without what'; not a 3 because there is no clear 'what'.	2 / 5
Trigger Term Quality	Natural terms like 'feature', 'bugfix', and 'implementation code' appear, but the core testing synonyms ('test', 'TDD', 'test-driven') are absent, fitting 'Some relevant keywords but missing common variations or synonyms'; not a 4 because the missing terms are central rather than incidental.	3 / 5
Distinctiveness Conflict Risk	'any feature or bugfix' is broad, but the 'before writing implementation code' qualifier gives a distinct timing trigger, fitting 'Somewhat specific but could still overlap with similar skills'; not a 2 because the timing adds specificity, not a 4 because the scope is too broad for minor overlap.	3 / 5
	Total	10 / 20 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/test-driven-development/SKILL.md
Commit: 99fd749

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.