tdd-workflow
TDD workflow for Meerkat SDK — Jest with @swc/jest, Nx monorepo, SQL AST testing patterns.
48
52%
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 ./.claude/skills/tdd-workflow/SKILL.mdQuality
Discovery
40%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 very specific technical niche (TDD for Meerkat SDK with particular tooling), which gives it strong distinctiveness. However, it reads more like a list of technology tags than a proper skill description — it lacks concrete action verbs describing what the skill does and completely omits any 'Use when...' guidance for skill selection.
Suggestions
Add explicit action verbs describing what the skill does, e.g., 'Guides test-driven development workflows, writes Jest test files, validates SQL AST transformations, and runs test suites in the Meerkat SDK.'
Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when writing tests for Meerkat SDK, setting up Jest configurations, testing SQL query builders, or following TDD practices in the Nx monorepo.'
Include common natural language variations users might say, such as 'unit tests', 'test-driven development', 'write tests', 'testing', or 'test coverage'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD workflow for Meerkat SDK) and mentions specific technologies (Jest, @swc/jest, Nx monorepo, SQL AST testing patterns), but doesn't list concrete actions like 'write tests', 'run test suites', 'generate test files', etc. It reads more like a tag list than a description of capabilities. | 2 / 3 |
Completeness | Partially addresses 'what' (TDD workflow with specific tools) but has no 'when' clause at all — no 'Use when...' or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also weak (no concrete actions listed), this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant technical keywords (Jest, TDD, Nx monorepo, SQL AST, @swc/jest, Meerkat SDK) that a developer might mention, but these are fairly niche. Missing common natural language triggers like 'write tests', 'unit testing', 'test-driven development', or 'testing patterns'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to a particular SDK (Meerkat), a particular toolchain (Jest with @swc/jest in Nx monorepo), and a particular pattern (SQL AST testing). This is unlikely to conflict with other skills due to its narrow, well-defined niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable guidance for TDD in the Meerkat SDK with concrete code examples and specific CLI commands. However, it mixes generic TDD knowledge (that Claude already possesses) with project-specific patterns, reducing token efficiency. The workflow section would benefit from explicit validation checkpoints and error recovery guidance rather than restating standard TDD steps.
Suggestions
Remove generic TDD advice (core principles, best practices like 'one behavior per test', 'independent tests') that Claude already knows, and focus exclusively on Meerkat-specific patterns and conventions.
Add explicit validation checkpoints to the workflow, such as what to check in coverage output, how to verify AST correctness, or when SQL output validation should trigger a re-examination of the approach.
Extract the detailed testing patterns and file organization into a separate reference file (e.g., TESTING_PATTERNS.md) and keep SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content like explaining core TDD principles ('Tests BEFORE Code', 'Write minimal code to make tests pass') that Claude already knows. The 'Common Testing Mistakes to Avoid' and 'Best Practices' sections contain generic TDD advice that doesn't add project-specific value. | 2 / 3 |
Actionability | The skill provides fully executable code examples with concrete TypeScript test patterns, specific Nx CLI commands for running tests, and realistic domain-specific examples (filter transformers, AST builders). The commands are copy-paste ready and the test patterns are complete enough to follow. | 3 / 3 |
Workflow Clarity | The 6-step TDD workflow is clearly sequenced with specific commands at each step, but it lacks explicit validation checkpoints or feedback loops — there's no guidance on what to do when tests fail unexpectedly, how to interpret coverage reports, or when to stop iterating. The workflow is essentially a restatement of standard TDD without project-specific validation gates. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's somewhat monolithic — the testing patterns, file organization, and running tests sections could be split into separate reference files. With no bundle files provided, there are no external references to evaluate, and the single file contains more detail than an overview should. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- devrev/meerkat
- Commit
b09913f
- 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.