author-vitest-tests

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

Quality

83%

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

88%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.

An excellent, highly executable workflow document: concrete commands, mandatory checkpoints, and validation/feedback loops at every phase, with detail appropriately delegated to existing repo docs. The only real gaps are mild verbosity in the confirmation framing and inlined long prompts that could live in reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and instructional throughout with no explanation of concepts Claude already knows; commands and rationale are stated once. Not 5: minor tightening is possible, e.g. the repeated dev-confirmation framing in Phase 2 ('stop and wait for confirmation' appears several times) and the 'Do not skip this step, even when' bullet list add slight redundancy.	4 / 5
Actionability	Fully executable guidance throughout: exact commands ('npx vitest run <path-to-test-file>', 'npm run test:positron:check-ts 2>&1 \| grep ...', the builder-enforcement grep), concrete file paths, a copy-paste plan template, and ready-to-use Agent() invocations cover the common cases.	5 / 5
Workflow Clarity	Three clearly sequenced phases with explicit skip conditions, mandatory confirmation checkpoints, and validation at every step: run test, type-check, coverage, eslint, builder enforcement, and a review-then-fix feedback loop, ending with a single full-suite run. This matches the anchor-5 pattern of explicit validation steps plus error-recovery loops ('start low, let errors guide you up').	5 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep links to real repo materials ([CLAUDE.md decision table], [.claude/rules/vitest-tests.md], [.claude/rules/vitest-rtl.md], the review skill), keeping conventions out of the main body. Not 5: there is no bundle of its own, and sizable content (the ~50-line analysis-subagent prompt and the full plan template) is inlined in SKILL.md rather than split into a reference file.	4 / 5
	Total	18 / 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 trigger-focused description with concrete, well-scoped natural keywords and excellent distinctiveness. Its main weakness is that the capability statement is embedded entirely in the 'Use when' clause, leaving the full scope of what the skill does (e.g., independent review of written tests) implicit.

Suggestions

Add a brief declarative capability sentence before the trigger clause, e.g. 'Writes, runs, and independently reviews Vitest tests for Positron code.' to make the 'what' explicit rather than folded into the trigger.

Include natural trigger variants such as the '.vitest.ts' / '.vitest.tsx' file extensions or 'unit tests' to widen keyword coverage toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Vitest tests for Positron src/vs/ or extensions/ code') and several concrete actions ('writing or adding Vitest tests', 'checking a branch/PR for test-coverage gaps', 'testing React components with RTL'), matching anchor 4. It is not 5 because coverage is partial: capabilities the skill actually performs, such as the independent review phase, are not stated.	4 / 5
Completeness	Both 'what' (writing/adding Vitest tests, checking coverage gaps, RTL testing) and 'when' (explicit 'Use when...') are present and concrete. Not 5 because the what is folded into the trigger clause as gerunds rather than stated as a distinct capability declaration, as in the anchor-5 exemplar; not 3 because the when clause is maximally explicit, not weakly implied.	4 / 5
Trigger Term Quality	Good natural-keyword coverage ('Vitest tests', 'React components', 'RTL', 'branch/PR', 'test-coverage gaps') that users would plausibly say verbatim. Not 5: anchor 5 expects synonyms and file extensions, and variants like '.vitest.ts' or 'unit tests' are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers: 'Positron', 'src/vs/', 'extensions/', 'Vitest', and 'RTL' are highly specific to this one skill with minimal conflict risk against generic test-writing skills.	5 / 5
	Total	17 / 20 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: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: .claude/skills/author-vitest-tests/SKILL.md
Commit: b0258bc

Reviewed: 5 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.