tdd-cycle
Guides Test-Driven Development workflow with Red-Green-Refactor cycle. Use when the user wants to implement a feature using TDD, write tests first, follow test-driven practices, or mentions red-green-refactor.
89
87%
Does it follow best practices?
Impact
93%
1.72xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 skill description with excellent trigger terms and completeness. The explicit 'Use when...' clause covers multiple natural phrasings users might employ. The main weakness is that the capabilities could be more specific about what concrete actions the skill guides (e.g., writing failing tests, implementing minimal code, refactoring).
Suggestions
Expand the capabilities portion to list specific actions like 'write failing tests first, implement minimal passing code, refactor for quality' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD) and mentions 'Red-Green-Refactor cycle' as a specific methodology, but doesn't list concrete actions like 'write failing tests', 'implement minimal code', or 'refactor for clarity'. | 2 / 3 |
Completeness | Clearly answers both what ('Guides Test-Driven Development workflow with Red-Green-Refactor cycle') and when ('Use when the user wants to implement a feature using TDD, write tests first, follow test-driven practices, or mentions red-green-refactor'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'TDD', 'write tests first', 'test-driven', 'red-green-refactor', and 'implement a feature using TDD' - good coverage of how developers naturally describe this workflow. | 3 / 3 |
Distinctiveness Conflict Risk | TDD is a distinct methodology with specific terminology (red-green-refactor) that wouldn't overlap with general testing or coding skills; the triggers are specific to this practice. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong TDD skill with excellent workflow clarity and actionability. The step-by-step checklist with validation checkpoints is particularly well-designed for guiding Claude through the red-green-refactor cycle. Minor verbosity in explanatory sections could be trimmed, but overall the skill provides concrete, executable guidance.
Suggestions
Trim explanatory text in Step 1 (Requirement Analysis) - Claude already knows to ask clarifying questions and consider edge cases
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanation (e.g., 'Ask clarifying questions if requirements are ambiguous' is obvious to Claude). The tables and templates are useful but the overall document could be tightened by ~20%. | 2 / 3 |
Actionability | Provides fully executable Ruby/RSpec code examples throughout, specific bash commands for running tests, and copy-paste ready templates. The common patterns section gives concrete, working examples for validations, associations, scopes, and services. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit checklist, clear sequencing (RED→GREEN→REFACTOR), and validation checkpoints at steps 4, 6, and 8. Includes feedback loops ('If specs fail, undo and try different approach') and clear error recovery guidance. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to detailed steps to common patterns. References external templates (unit_spec.erb, request_spec.erb) appropriately without deep nesting. Content is appropriately organized for discovery. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- ThibautBaissac/rails_ai_agents
- Commit
15fdeaf
- 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.