tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
66
79%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/agentic-engineering/skills/tdd/SKILL.mdQuality
Discovery
82%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 a solid description with a clear 'Use when' clause and good trigger term coverage. Its main weakness is that the capability description is somewhat abstract—naming the methodology rather than listing the concrete steps Claude will perform—and some trigger terms like 'build features' and 'fix bugs' are generic enough to risk overlap with non-TDD skills.
Suggestions
Add specific concrete actions to the 'what' portion, e.g., 'Writes failing tests first, implements minimal code to pass, then refactors for quality' to improve specificity.
Narrow the broader trigger terms to reduce conflict risk—e.g., replace 'build features or fix bugs' with 'build features or fix bugs through a test-first workflow' to clarify the TDD-specific intent.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD) and mentions the red-green-refactor loop, but doesn't list specific concrete actions like 'write failing tests', 'implement minimal code', 'refactor for clarity'. The actions are implied by the methodology name rather than explicitly enumerated. | 2 / 3 |
Completeness | Clearly answers both 'what' (test-driven development with red-green-refactor loop) and 'when' (explicit 'Use when' clause listing four distinct trigger scenarios). The when clause is explicit and well-structured. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'TDD', 'red-green-refactor', 'integration tests', 'test-first development', 'build features', 'fix bugs'. These cover multiple natural phrasings a user might employ. | 3 / 3 |
Distinctiveness Conflict Risk | While TDD and red-green-refactor are fairly distinctive, terms like 'build features', 'fix bugs', and 'integration tests' are broad enough to overlap with general coding skills or testing-focused skills that aren't specifically TDD-oriented. | 2 / 3 |
Total | 10 / 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 TDD skill that efficiently communicates a clear methodology with good workflow sequencing and anti-pattern guidance. Its main weakness is the lack of concrete, executable code examples showing an actual red-green-refactor cycle, and the referenced supporting files (tests.md, mocking.md, etc.) are not provided in the bundle, making the progressive disclosure promises hollow.
Suggestions
Add a brief, concrete code example showing one complete RED→GREEN→REFACTOR cycle (e.g., a simple function with a test in Python or JavaScript) to improve actionability.
Provide the referenced bundle files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) or remove the references if they don't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The content avoids explaining what TDD is at a basic level and instead focuses on the specific methodology and anti-patterns Claude should follow. The ASCII diagram for horizontal vs vertical slices is efficient and informative. | 3 / 3 |
Actionability | The workflow steps and checklists are clear and specific, but there are no executable code examples showing actual test code (e.g., a concrete test in a language, a real red-green-refactor cycle). The guidance is concrete in process terms but lacks copy-paste-ready code artifacts. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Planning → Tracer bullet → Incremental loop → Refactor) with explicit validation checkpoints (per-cycle checklist, 're-run tests after each step', 'never refactor while RED'). The feedback loop of RED→GREEN→REFACTOR is well-defined with clear rules at each stage. | 3 / 3 |
Progressive Disclosure | References to supporting files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) are well-signaled and one level deep, which is good. However, no bundle files were provided, so these references are unverifiable and potentially broken. The main content is well-structured but the referenced files don't exist. | 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
- belchman/claude-skills
- Commit
be88d6c
- 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.