pantheon-ai/test-driven-development
Master Test-Driven Development with deterministic red-green-refactor workflows, test-first feature delivery, bug reproduction through failing tests, behavior-focused assertions, and refactoring safety; use when implementing new functions, changing APIs, fixing regressions, or restructuring code under test.
Does it follow best practices?
Evaluation — 86%
↑ 1.05xAgent success when using this tile
Validation for skill structure
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 hits all the marks. It provides specific TDD practices and workflows, includes natural trigger terms developers would use, explicitly states both capabilities and usage conditions, and carves out a distinct niche around test-driven development methodology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'red-green-refactor workflows, test-first feature delivery, bug reproduction through failing tests, behavior-focused assertions, and refactoring safety.' These are concrete TDD practices, not vague abstractions. | 3 / 3 |
Completeness | Clearly answers both what (guides TDD with specific workflows and practices) AND when (explicit 'Use when...' clause listing scenarios like 'writing unit tests, implementing new functions' plus quoted trigger phrases like 'TDD' and 'write tests first'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'unit tests', 'TDD', 'test-first', 'write tests first', 'test before code', 'test coverage', 'fixing regressions', 'refactoring'. These match how developers naturally discuss testing workflows. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on TDD methodology and test-first development. The emphasis on 'red-green-refactor', 'test-first', and 'write tests first' distinguishes it from general testing or code quality skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill document that demonstrates excellent TDD guidance. It's concise yet comprehensive, with executable examples in multiple languages, clear workflow steps with validation checkpoints, and well-organized progressive disclosure through reference links. The anti-patterns section with BAD/GOOD comparisons adds significant practical value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of what TDD is or why testing matters. Every section serves a purpose with no padding or concepts Claude already knows. | 3 / 3 |
Actionability | Provides fully executable TypeScript and Elixir examples with copy-paste ready code. The red-green-refactor cycle is demonstrated with concrete, runnable examples including expected outcomes (❌/✅ markers). | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation (step 2: verify failure is for expected reason). The examples show the complete cycle with clear state transitions between RED, GREEN, and REFACTOR phases. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick commands, and a well-organized Quick Reference table pointing to one-level-deep reference files. Content is appropriately split between the main skill and detailed references. | 3 / 3 |
Total | 12 / 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.
Install with Tessl CLI
npx tessl i pantheon-ai/test-driven-developmentReviewed
Table of Contents