generate-tests

Generate comprehensive unit tests for a Spark UI component using Vitest and React Testing Library. Use when the user wants to add tests, improve test coverage, or test a specific component.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/generate-tests/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, appropriately concise skill body with concrete commands and a realistic test template. Its weakest point is workflow clarity: it never instructs the agent to run the generated tests and iterate on failures, leaving the core feedback loop implicit. The code template also relies on placeholders that could be more fully specified.

Suggestions

Add a validation loop to the workflow: after writing the test file, run `npm run test:run`, fix failing tests, and re-run until all tests pass before finishing.

Make the test template more complete — show how defaultProps is defined and use a real role/query (e.g., getByRole('button')) instead of '...' and '// Accessibility tests' placeholders.

Merge the duplicated accessibility guidance: fold 'Accessibility Testing' (section 5) into the 'What to Test' list to remove the repeated ARIA/keyboard/focus items.

Dimension	Reasoning	Score
Conciseness	The body is lean and project-specific ('Tests go in `ComponentName.test.tsx` in the component directory', concrete npm commands) with only minor trimmable redundancy — accessibility guidance is duplicated between the 'What to Test' bullet and the 'Accessibility Testing' section — so it fits 'efficient with minor instances' rather than the every-token-earns-its-place bar of 5.	4 / 5
Actionability	Gives concrete, runnable commands (npm run test:run / test:coverage) and a real import/test skeleton, but the template contains placeholders ({...defaultProps}, getByRole('...'), '// Accessibility tests') that keep it short of copy-paste-ready, matching 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	The numbered instructions form a clear sequence (location, setup, structure, coverage, running), but there is no validation checkpoint — no run-tests, fix-failures, re-run loop — leaving checkpoints implicit, which matches anchor 3 rather than 4. Test generation is neither destructive nor batch, so no lower cap applies.	3 / 5
Progressive Disclosure	Well-organized sections with nothing inlined that belongs in a separate file, and a single one-level, clearly signaled reference to existing patterns ('packages/components/src/*/ComponentName.test.tsx'). The thin Examples section and length just over the simple-skill bar keep it at 'good structure with minor gaps' rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: clear third-person statement of what the skill does with named tools, plus an explicit 'Use when' clause with concrete, natural trigger phrases. Its main weakness is thin action coverage — it names only the single act of generating tests rather than several specific capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and tooling ('Spark UI component using Vitest and React Testing Library') but covers a single concrete action ('Generate comprehensive unit tests'), matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-actions bar of 4.	3 / 5
Completeness	Explicitly answers both 'what' ('Generate comprehensive unit tests for a Spark UI component using Vitest and React Testing Library') and 'when' ('Use when the user wants to add tests, improve test coverage, or test a specific component') with concrete trigger phrases in third person, matching the anchor for 5.	5 / 5
Trigger Term Quality	Natural phrases users would say — 'add tests', 'improve test coverage', 'test a specific component' — give good keyword coverage, but common variations like 'write tests', 'testing', or 'specs' are missing, keeping it below the comprehensive-synonyms anchor of 5.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific component library and test stack, it is mostly distinct with only minor overlap risk against generic testing skills; it lacks the fully distinct trigger set of the 5 anchor.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: leboncoin/spark-web
Path: .cursor/skills/generate-tests/SKILL.md
Commit: da35814

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.