test-driven-generation
Generates code test-first — writes a failing test from a requirement, then generates the minimal code to pass it, then refactors, in strict red-green-refactor cycles. Use when building new features where the spec is clear, when the design is uncertain and you want tests to drive it, or when you need high confidence in coverage from the start.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill test-driven-generation94
Quality
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
85%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 strong skill description that clearly articulates the TDD methodology with specific actions and provides explicit trigger conditions. The main weakness is the trigger term coverage, which relies on methodology-specific jargon rather than including common user phrases like 'TDD' or 'test driven development' that users would naturally say.
Suggestions
Add common trigger terms users would naturally say: 'TDD', 'test driven development', 'unit tests', 'write tests first'
Consider adding file type or language context if applicable (e.g., 'for Python, JavaScript, or other languages with testing frameworks')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'writes a failing test from a requirement', 'generates the minimal code to pass it', 'refactors', and explicitly names the methodology 'strict red-green-refactor cycles'. | 3 / 3 |
Completeness | Clearly answers both what (generates code test-first with red-green-refactor cycles) AND when with explicit 'Use when' clause covering three distinct scenarios: clear specs, uncertain design, and high coverage needs. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'test-first', 'red-green-refactor', 'coverage', and 'tests to drive it', but misses common user phrases like 'TDD', 'test driven development', 'unit tests', or 'write tests first'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'test-first' and 'red-green-refactor' methodology creates a clear niche distinct from general coding skills or testing skills; unlikely to conflict with skills that write tests after code or general development skills. | 3 / 3 |
Total | 11 / 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.
Excellent skill content that demonstrates TDD through concrete, executable examples rather than abstract explanation. The triangulation concept is particularly well-illustrated with the Cart example showing why hardcoding is correct TDD. The anti-patterns table and 'Do not' section provide clear guardrails without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what TDD is conceptually—jumps straight to the cycle. The worked example is dense but necessary for demonstrating triangulation. Anti-patterns table is efficient. | 3 / 3 |
Actionability | Fully executable Python examples throughout. The Cart example shows complete red-green-refactor with real code. The rate limiter transcript provides a realistic worked example. Output format template is copy-paste ready. | 3 / 3 |
Workflow Clarity | The cycle diagram is explicit with clear sequencing. Each step has validation built in ('Run it. Confirm it fails for the RIGHT reason'). The worked transcript demonstrates the feedback loop explicitly. Anti-patterns table reinforces what not to skip. | 3 / 3 |
Progressive Disclosure | Well-structured single file appropriate for the content scope. Clear sections progress from concept → examples → anti-patterns → output format. No need for external references given the self-contained nature of TDD instruction. | 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.