common-tdd
Implements a strict Red-Green-Refactor loop to ensure zero production code is written without a prior failing test. Use when: creating new features, fixing bugs, or expanding test coverage.
63
76%
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 ./.github/skills/common/common-tdd/SKILL.mdQuality
Discovery
67%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 clearly communicates the TDD methodology and includes an explicit 'Use when' clause, which is a strength. However, the trigger terms in the 'Use when' clause are overly broad ('creating new features, fixing bugs') and would likely conflict with many other coding skills. Adding more specific TDD-related trigger terms and narrowing the activation conditions would significantly improve selection accuracy.
Suggestions
Add natural trigger terms users would actually say, such as 'TDD', 'test-driven development', 'write tests first', 'unit tests', 'test-first'.
Narrow the 'Use when' clause to require TDD-specific intent rather than generic development activities — e.g., 'Use when the user requests test-driven development, asks to write tests before code, or mentions Red-Green-Refactor' instead of 'creating new features, fixing bugs'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD/Red-Green-Refactor) and describes the core constraint ('zero production code without a prior failing test'), but doesn't list multiple concrete actions beyond the general loop. Actions like 'creating new features, fixing bugs, expanding test coverage' are use-case triggers rather than specific capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (implements a strict Red-Green-Refactor loop ensuring no production code without a failing test) and 'when' (explicit 'Use when:' clause covering creating features, fixing bugs, or expanding test coverage). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Red-Green-Refactor', 'failing test', 'test coverage', 'features', 'bugs', but misses common natural user phrases like 'TDD', 'test-driven development', 'write tests first', 'unit tests', or 'test-first approach'. | 2 / 3 |
Distinctiveness Conflict Risk | The triggers 'creating new features' and 'fixing bugs' are extremely broad and would overlap with virtually any coding skill. While 'Red-Green-Refactor' and 'failing test' are distinctive, the use-when clause could cause this skill to fire for general development tasks where TDD isn't requested. | 2 / 3 |
Total | 9 / 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 well-structured TDD skill that is concise, clearly sequenced, and makes good use of progressive disclosure with reference files. Its main weakness is the lack of any inline executable code example — the AAA code structure is entirely deferred to a reference file, which reduces immediate actionability. Minor grammatical issues ('MUST deleted', 'not test') slightly reduce polish but don't impair comprehension.
Suggestions
Add one small inline code example demonstrating the AAA structure (e.g., a simple pytest test) so the skill is immediately actionable without needing to consult references/aaa_example.md.
Fix minor grammatical issues: 'Code written before test MUST deleted' → 'MUST be deleted'; 'test without assert not test' → 'a test without an assert is not a test'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what TDD is conceptually and jumps straight into actionable rules and steps. Every section earns its place with no padding or unnecessary context that Claude would already know. | 3 / 3 |
Actionability | The skill provides clear rules and a structured workflow, but lacks executable code examples inline — the AAA example is deferred to a reference file. Coverage thresholds and mock guidance are concrete, but without a single copy-paste-ready test example in the main body, it falls short of fully actionable. | 2 / 3 |
Workflow Clarity | The Red-Green-Refactor loop is clearly sequenced with explicit verification at each step (verify failure, verify pass, stay green). The verification checklist provides a feedback loop, and the iron law about deleting code written before tests establishes a clear error recovery pattern. | 3 / 3 |
Progressive Disclosure | The main body is a concise overview with well-signaled one-level-deep references to five supporting files (AAA example, methodology, test runners, TDD patterns, anti-patterns). Content is appropriately split between the overview and reference materials. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
3df717f
- 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.