tdd
Strict TDD loop — red/green/refactor must be followed for every code change, no exceptions
78
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 identifies a specific development methodology (TDD) but reads more like a rule or constraint than a skill description. It lacks explicit trigger guidance ('Use when...'), concrete action verbs, and natural user keywords. The prescriptive tone ('must be followed', 'no exceptions') doesn't help Claude understand when to select this skill.
Suggestions
Add a 'Use when...' clause with trigger terms like 'TDD', 'test-driven', 'write tests first', 'test before implementing'
List specific concrete actions: 'Write failing tests before implementation, implement minimal code to pass tests, refactor while maintaining green tests'
Include natural keyword variations users might say: 'test-driven development', 'red-green-refactor', 'test first approach', 'unit test workflow'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD) and describes the core methodology (red/green/refactor), but doesn't list specific concrete actions like 'write failing tests first', 'implement minimal code', or 'refactor with passing tests'. | 2 / 3 |
Completeness | Describes what (TDD loop methodology) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Missing the 'when' component caps this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'TDD' and 'red/green/refactor' which are relevant keywords, but misses common variations users might say like 'test-driven', 'write tests first', 'test before code', or 'unit testing workflow'. | 2 / 3 |
Distinctiveness Conflict Risk | TDD is a specific methodology which provides some distinctiveness, but 'code change' is generic and could overlap with general coding skills. The lack of explicit triggers increases conflict risk with other development-related skills. | 2 / 3 |
Total | 7 / 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 file that demonstrates excellent token efficiency while remaining highly actionable. The strict TDD loop is clearly sequenced with explicit validation gates, and the failure modes table provides concrete corrections. The checkpoint format ensures consistent output without verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No explanation of what TDD is or why it matters—assumes Claude knows. The table format for failure modes is efficient, and the checkpoint format is minimal but complete. | 3 / 3 |
Actionability | Provides concrete, specific instructions at each step. The failure modes table gives exact corrections. The checkpoint format is copy-paste ready. Clear commands like 'Stop. Delete the implementation. Write the test first.' | 3 / 3 |
Workflow Clarity | The four-step loop is explicitly sequenced with clear validation checkpoints (confirm failure, confirm green, re-run after refactor). Includes feedback loop for mid-session recovery. The 'do not proceed until' gates are explicit. | 3 / 3 |
Progressive Disclosure | For a single-purpose skill under 50 lines, the content is well-organized with clear sections (Rule, Loop, Failure Modes, Resuming, Checkpoint). No need for external references; everything needed is appropriately inline. | 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.
- 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.