frontend-testing
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly identifies the specific technology stack (Vitest + React Testing Library), the target domain (Dify frontend), and the types of artifacts it handles (components, hooks, utilities). It includes explicit trigger guidance with a comprehensive list of natural keywords users would use. The description is concise, uses third-person voice, and is well-structured.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating tests for components, hooks, and utilities, and names the specific frameworks (Vitest, React Testing Library) and the specific project (Dify frontend). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate Vitest + RTL tests for Dify frontend components, hooks, and utilities) and 'when' (triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would say: 'testing', 'spec files', 'coverage', 'Vitest', 'RTL', 'unit tests', 'integration tests', 'write/review test requests'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Dify frontend, Vitest, React Testing Library, and the enumerated component types. Unlikely to conflict with other skills given the narrow, well-defined niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable testing skill with clear workflows and concrete examples. Its main weakness is moderate verbosity—it explains general testing concepts (AAA pattern, black-box testing, single behavior per test) that Claude already knows, and the main file could be slimmer by offloading some sections to the referenced files. The progressive disclosure structure is reasonable but unverifiable without bundle files.
Suggestions
Move general testing principles (AAA pattern, black-box testing, single behavior per test) to a reference file or remove them entirely—Claude already knows these concepts.
Trim the 'Required Test Scenarios' conditional table and 'Coverage Goals' section into a more compact checklist, or move them to `references/checklist.md` which is already referenced.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but includes some unnecessary content that Claude already knows (AAA pattern explanation, what black-box testing means, single behavior per test principle). The tech stack version table and some explanatory text could be trimmed. However, the project-specific conventions and patterns earn their place. | 2 / 3 |
Actionability | The skill provides fully executable code templates, specific bash commands, concrete file naming conventions, and copy-paste ready test structure. The mock patterns, query examples, and assertion patterns are all specific and directly usable. | 3 / 3 |
Workflow Clarity | The incremental testing workflow is clearly sequenced with an explicit write→run→verify feedback loop, a visual flowchart, complexity-based ordering, and clear validation checkpoints (PASS/FAIL branching). The 'NEVER generate all test files at once' constraint and refactoring thresholds add important guardrails. | 3 / 3 |
Progressive Disclosure | The skill references six files in `references/` directory and several codebase paths, which is good structure. However, no bundle files were provided, so we cannot verify these references exist. The main SKILL.md itself is quite long (~250 lines) and some sections (Core Principles, Required Test Scenarios) could potentially be moved to reference files to keep the overview leaner. | 2 / 3 |
Total | 10 / 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
- langgenius/dify
- Commit
3708e3e
- 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.