author-vitest-tests

Use when writing or adding Vitest tests for Positron src/vs/ code, checking a branch/PR for test-coverage gaps, or testing React components with RTL.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A well-structured, highly actionable multi-phase workflow with concrete commands, explicit validation checkpoints, and well-signaled one-level-deep references. Its only weakness is mild cross-phase repetition that slightly undercuts conciseness.

Suggestions

De-duplicate the recurring guidance: reference the 'start low, let errors guide you up' pattern and the CLAUDE.md decision table once and link back, rather than restating them in each phase.

The 'do not run the full suite yet' point is made both in Phase 2 and Phase 3; consolidate it into a single explicit statement to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly project-specific and assumes Claude's competence (no generic concept explanations), but it repeats the decision-table reference and the 'start low, let errors guide you up' guidance across phases, so it could be tightened.	2 / 3
Actionability	Fully executable commands throughout -- 'gh pr diff <number>', 'npx vitest run <path>', 'npm run test:positron:check-ts 2>&1 \| grep ...', coverage and eslint invocations -- with specific preset method names and file paths, copy-paste ready.	3 / 3
Workflow Clarity	A clear three-phase sequence (analysis, writing, review) with explicit validation checkpoints -- mandatory confirmation gates, 'must be clean before considering it done', builder-enforcement grep, and a single full-suite run after fixes -- plus error-recovery feedback loops.	3 / 3
Progressive Disclosure	The body is an overview pointing one level deep to clearly signaled external materials (CLAUDE.md decision table, .claude/rules/vitest-tests.md and vitest-rtl.md, the positronTestContainer.ts JSDoc, and the review skill); no bundle files are provided to verify further.	3 / 3
	Total	11 / 12 Passed

Description

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.

A concise, third-person/trigger-voice description that names concrete actions, includes natural trigger terms, and explicitly covers both what the skill does and when to use it. It is highly distinct from generic testing skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions -- 'writing or adding Vitest tests for Positron src/vs/ code', 'checking a branch/PR for test-coverage gaps', and 'testing React components with RTL' -- rather than vague language.	3 / 3
Completeness	An explicit 'Use when ...' clause provides the when, while the three enumerated clauses state the what, so both are clearly answered with explicit triggers.	3 / 3
Trigger Term Quality	Uses natural terms a developer would actually say -- 'Vitest tests', 'test-coverage gaps', 'branch/PR', 'React components', 'RTL' -- with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Positron src/vs/ code, Vitest, and RTL, giving it a clear niche unlikely to trigger for unrelated testing skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: .claude/skills/author-vitest-tests/SKILL.md
Commit: b87c504

Reviewed: 2 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.