test-implement
Test implementation patterns and conventions. Use when implementing unit tests, integration tests, or E2E tests, including RTL+Vitest+MSW component testing and Playwright E2E testing.
56
62%
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 ./skills/test-implement/SKILL.mdQuality
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 explicit 'Use when' guidance and good trigger term coverage across multiple testing frameworks and test types. Its main weakness is that the 'what' portion is somewhat abstract ('patterns and conventions') rather than listing concrete actions like writing tests, mocking dependencies, or setting up test harnesses. Overall it performs well for skill selection purposes.
Suggestions
Replace 'Test implementation patterns and conventions' with specific actions like 'Write and structure unit tests, integration tests, and E2E tests, including mocking, assertions, and test setup/teardown.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (testing) and mentions specific frameworks (RTL, Vitest, MSW, Playwright), but describes 'patterns and conventions' rather than listing concrete actions like 'write test cases, mock API responses, set up test fixtures'. | 2 / 3 |
Completeness | Clearly answers both what ('Test implementation patterns and conventions') and when ('Use when implementing unit tests, integration tests, or E2E tests, including RTL+Vitest+MSW component testing and Playwright E2E testing'). The explicit 'Use when' clause with specific triggers is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'unit tests', 'integration tests', 'E2E tests', 'component testing', 'Playwright', 'RTL', 'Vitest', 'MSW'. These cover common variations of how users refer to testing tasks. | 3 / 3 |
Distinctiveness Conflict Risk | The specific mention of testing frameworks (RTL, Vitest, MSW, Playwright) and test types (unit, integration, E2E) creates a clear niche that is unlikely to conflict with other skills. It's distinctly about test implementation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves primarily as a routing table to two reference files, with some generic testing principles that Claude already knows. It lacks any concrete, actionable content — no code examples, no specific patterns for RTL/Vitest/MSW or Playwright, and no workflow for test implementation. The reference table structure is a strength, but the body content doesn't justify its existence beyond the table.
Suggestions
Add concrete, executable code examples for at least one common test pattern (e.g., a React component test with RTL+Vitest+MSW setup, or a Playwright E2E test skeleton).
Remove or significantly condense the 'Common Principles' section — AAA, test independence, and naming conventions are well-known to Claude and waste tokens.
Add a brief workflow for test implementation: e.g., 1) identify test type, 2) consult reference, 3) write test following pattern, 4) run tests with specific command, 5) verify coverage/output.
Include the bundle reference files (references/frontend.md and references/e2e.md) so the progressive disclosure structure can actually function.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The AAA structure and test independence sections explain concepts Claude already knows well. The reference table and naming section are efficient, but the common principles section adds little novel value. | 2 / 3 |
Actionability | No concrete code examples, no executable commands, no specific patterns. The content describes testing principles abstractly (AAA, independence, naming) without showing actual test implementations, mock setups, or copy-paste-ready patterns. | 1 / 3 |
Workflow Clarity | The reference selection table provides a clear decision path for choosing which reference to consult. However, there's no workflow for actually implementing tests — no steps for setup, writing, running, or validating tests. | 2 / 3 |
Progressive Disclosure | The skill correctly references two separate files (references/frontend.md and references/e2e.md) with a clear selection table, which is good structure. However, no bundle files were provided to verify these references exist, and the SKILL.md itself contains very little substantive content — it's almost entirely a pointer with some generic principles that don't add value. | 2 / 3 |
Total | 7 / 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.
- Repository
- shinpr/claude-code-workflows
- Commit
68ecb4a
- 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.