testgen
Generate tests with expert routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test coverage.
75
66%
Does it follow best practices?
Impact
87%
1.07xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/testgen/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.
The description is strong on completeness and trigger terms, explicitly listing when it should be activated with natural user phrases. Its main weakness is that the capability descriptions ('expert routing', 'framework detection', 'auto-TaskCreate') lean toward internal jargon rather than concrete user-facing actions, which reduces specificity. Overall it's a functional description that would perform well in skill selection.
Suggestions
Replace jargon like 'expert routing' and 'auto-TaskCreate' with concrete actions such as 'generates unit tests, integration tests, and test suites for detected frameworks (Jest, pytest, etc.)' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (test generation) and mentions some capabilities like 'expert routing', 'framework detection', and 'auto-TaskCreate', but these are somewhat jargon-heavy and don't clearly describe concrete user-facing actions like 'generates unit tests for functions' or 'creates integration test files'. | 2 / 3 |
Completeness | Answers both 'what' (generate tests with expert routing, framework detection, auto-TaskCreate) and 'when' (explicit 'Triggers on:' clause with specific trigger phrases), satisfying the requirement for explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms users would say: 'generate tests', 'write tests', 'testgen', 'create test file', 'add test coverage'. These are realistic phrases a user would type when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to test generation with distinct trigger terms. The specific phrases like 'testgen', 'add test coverage', and 'create test file' make it unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has good structural organization and progressive disclosure, with clear references to external files for detailed examples. However, it is significantly over-verbose, repeating information across the architecture diagram and execution steps, and listing language-specific testing patterns Claude already knows. The most critical weakness is that the core purpose—actually generating tests—lacks any concrete code examples, and there's no validation checkpoint to verify generated tests work.
Suggestions
Remove the 'Expert Routing Details' section entirely—Claude already knows pytest fixtures, Go table-driven tests, React Testing Library patterns, etc. This saves ~60 lines of tokens that add no new information.
Add concrete, executable test code examples in Step 5 (e.g., a complete generated test file for a sample function) instead of abstract tables describing focus and depth levels.
Add an explicit validation step between Step 5 and Step 6: run the generated tests and verify they pass before suggesting next steps. Missing validation for file-creation workflows is a significant gap.
Consolidate the architecture diagram and execution steps—currently the same information is presented twice in different formats. Keep only the execution steps with their concrete commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It explains routing tables, CLI tool fallbacks, and framework detection details that Claude can infer or look up dynamically. The architecture diagram, while visually appealing, duplicates information that's then repeated in the execution steps. Much of the expert routing details section lists basic language testing patterns Claude already knows (e.g., pytest fixtures, table-driven Go tests, #[test] attributes). | 1 / 3 |
Actionability | The skill provides concrete bash commands for framework detection and file discovery, which is good. However, the actual test generation step (Step 5) is entirely abstract—it lists categories and depth levels in tables but provides zero executable test code examples. The 'Route to Expert Agent' step references a Task tool invocation but gives only a vague pseudo-structure rather than an actual executable call. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with a good architecture diagram. However, there are no validation checkpoints—no step verifies that generated tests actually compile or pass before suggesting next steps. For a test generation workflow that creates files, a validation step (run the tests, check for syntax errors) should be explicit, not just suggested as a 'next step' at the end. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external files (frameworks.md, visual-testing.md) for detailed code examples, keeping the main file as an overview. References are one level deep and clearly signaled. The structure uses clear sections with headers for easy navigation. | 3 / 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
- NeverSight/skills_feed
- Commit
9f4534c
- 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.