test
Advanced test implementation command with unit/E2E support, auto-execution, and smart fixing capabilities
53
41%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/test/SKILL.mdQuality
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 the testing domain and mentions some features (unit/E2E, auto-execution, fixing), but relies on vague buzzwords like 'advanced' and 'smart fixing capabilities' rather than concrete actions. It critically lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'write tests', 'fix failing tests', 'run test suite', 'unit test', 'end-to-end test', 'test coverage'.
Replace vague terms like 'advanced', 'smart fixing capabilities' with concrete actions such as 'generates unit and E2E tests, runs them automatically, and iteratively fixes failures based on error output'.
Include common file/framework references users might mention, such as 'Jest', 'pytest', 'Cypress', 'Playwright', or '.test.ts/.spec.js files' to improve trigger term coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (testing) and some actions (unit/E2E support, auto-execution, smart fixing), but these are somewhat vague and not fully concrete—'smart fixing capabilities' and 'advanced test implementation command' are more buzzword-like than specific actionable descriptions. | 2 / 3 |
Completeness | Provides a partial 'what' (test implementation with some features) but completely lacks a 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'unit', 'E2E', 'test', and 'auto-execution', but misses common natural user terms like 'write tests', 'run tests', 'fix failing tests', 'integration tests', 'test coverage', or specific frameworks. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to testing with unit/E2E distinction, but 'test implementation' and 'smart fixing' are broad enough to overlap with general coding skills, debugging skills, or CI/CD skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a well-structured command reference with clear syntax and options, but falls short on actionability — the implementation steps are too abstract and lack concrete code examples or templates that Claude could execute. The workflow sections describe what to do at a high level without providing the specific logic, patterns, or validation checkpoints needed for reliable test generation and fixing.
Suggestions
Add concrete, executable test templates for at least one framework (e.g., a Jest unit test skeleton and a Playwright E2E skeleton) so Claude has copy-paste-ready patterns to follow.
Expand the Smart Fixing section with specific error classification examples and concrete fixing strategies (e.g., 'If assertion error: compare expected vs actual, adjust assertion; If mock error: verify mock setup matches import path').
Add explicit validation checkpoints in the workflow, such as 'After test creation, verify the test file imports resolve correctly before running' and 'If 3+ consecutive fix attempts fail on the same error, stop and report'.
Consider splitting framework-specific guidance (Jest vs Vitest, Cypress vs Playwright) into separate referenced files to keep the main skill lean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary detail like the full target specification table (Claude can infer what valid targets are) and the verbose options table with many flags that could be more compact. The output report example adds bulk without critical instructional value. | 2 / 3 |
Actionability | While the skill provides usage examples and a clear command syntax, the actual implementation instructions are vague — steps like 'Test case creation: happy path, error cases, edge cases' and 'Apply appropriate fixing strategy' lack concrete guidance on what Claude should actually do. No executable code or specific test templates are provided. | 2 / 3 |
Workflow Clarity | The test implementation flow outlines steps for each mode, and the smart fixing section mentions iteration with a max of 10 attempts. However, validation checkpoints are implicit rather than explicit — there's no clear 'if X fails, do Y' feedback loop detail, and the steps are high-level descriptions rather than actionable sequences. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections with headers and tables, but everything is in a single monolithic file. For a skill this size with multiple modes (unit, E2E, performance, coverage), advanced topics like smart fixing strategies or framework-specific patterns could be split into referenced files. | 2 / 3 |
Total | 8 / 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
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.