tdd
Enforces strict test-driven development -- write a failing test first, implement minimal code to pass, then refactor. Use when implementing a feature, fixing a bug, adding behavior, refactoring, or any time production code will be written or changed. Also use when the user says "write tests", "add tests", "TDD", or "test first". DO NOT TRIGGER for throwaway prototypes, generated code, or config-only changes unless the user explicitly requests TDD.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines the TDD methodology it enforces, provides comprehensive trigger terms covering natural user language, and explicitly delineates both when to use and when NOT to use the skill. The inclusion of negative triggers (DO NOT TRIGGER) is a strong differentiator that reduces conflict risk. The description is concise yet thorough, using proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'write a failing test first, implement minimal code to pass, then refactor.' Also specifies concrete scenarios like implementing features, fixing bugs, adding behavior, and refactoring. | 3 / 3 |
Completeness | Clearly answers both 'what' (enforces strict TDD with red-green-refactor cycle) and 'when' (explicit 'Use when...' clause covering multiple scenarios plus explicit 'DO NOT TRIGGER' exclusions). This is exceptionally thorough. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'write tests', 'add tests', 'TDD', 'test first', 'implementing a feature', 'fixing a bug', 'refactoring'. Also includes negative triggers for when NOT to use it (prototypes, generated code, config-only changes). | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around test-driven development methodology. The explicit exclusions (prototypes, generated code, config-only changes) further reduce conflict risk with other coding or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable TDD skill with excellent workflow clarity including explicit verification gates and feedback loops at each phase. Its main weakness is verbosity — the philosophical justifications ('Why Order Matters', excuse tables, 'Recognizing When You've Left TDD') add significant token cost explaining concepts Claude already understands, and some of this content could be extracted to supplementary files.
Suggestions
Move the 'Why Order Matters' section and excuse tables to a supplementary file (e.g., tdd-rationale.md) — Claude doesn't need persuasion about TDD's value, it needs instructions on how to do it.
Condense 'Recognizing When You've Left TDD' to a brief bullet list without the excuse table, which largely repeats points already made elsewhere in the document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good examples and structure, but includes significant verbosity in the 'Why Order Matters' section that explains concepts Claude already understands (sunk cost fallacy, why automated tests beat manual testing). The 'Recognizing When You've Left TDD' section and excuse table also add bulk that could be trimmed. | 2 / 3 |
Actionability | Provides fully executable TypeScript code examples for each TDD phase, concrete bash commands for verification, clear good/bad comparisons, and a complete bug fix walkthrough. Every step is copy-paste ready with specific expected outputs. | 3 / 3 |
Workflow Clarity | The Red-Green-Refactor cycle is explicitly sequenced with verification checkpoints after each phase (Verify RED, Verify GREEN). Includes clear feedback loops (test passes unexpectedly → fix test; test errors → fix and re-run; other tests fail → fix now) and a comprehensive verification checklist before completion. | 3 / 3 |
Progressive Disclosure | The skill references `testing-anti-patterns.md` appropriately at the end, but the main content is quite long (~200+ lines) with sections like 'Why Order Matters' and the excuse tables that could be extracted to a separate file. The structure is good with clear headers, but the inline content is heavier than ideal for a SKILL.md overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- shousper/claude-kit
- Commit
a01bac9
- Reviewed
Table of Contents
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.