test

Use when you need to run tests for React core. Supports source, www, stable, and experimental channels.

2.85x

Quality

75%

Does it follow best practices?

Impact

100%

2.85x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/test/SKILL.md

Quality

Content

80%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.

The body is highly actionable and well-structured for a simple single-purpose skill, with concrete yarn commands and clear sections. Its main weakness is workflow clarity: running tests is a batch operation without an explicit feedback loop for parsing failures, re-running, or handling skipped/@gate cases.

Suggestions

Add an explicit feedback loop in the Instructions, e.g. 'If tests fail or are skipped unexpectedly: read the failure, check for @gate pragma, fix or re-run with the specific failing pattern'.

De-duplicate the channel info between 'Usage Examples' and 'Release Channels' (e.g. keep examples as commands and channels as a single mapping table) to tighten conciseness.

Fold the 'Test skipped unexpectedly / @gate' Common Mistake into the workflow as a checkpoint rather than only a warning, so skipped tests are handled inline.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence, with no padding about what React or tests are; the 'Release Channels' list partially duplicates the 'Usage Examples' channel list, the minor over-explanation that keeps it from 5.	4 / 5
Actionability	Fully executable copy-paste-ready yarn commands per channel with exact flags (--silent, --no-watchman, --variant=false), and the usage examples cover the common cases.	5 / 5
Workflow Clarity	A clear numbered sequence exists (parse channel -> map to yarn command -> report results) but for a batch test run there is no explicit validate/fix/retry feedback loop; the --silent 'to see failures' rule implies failure handling that is never sequenced as a checkpoint.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections (Usage Examples, Release Channels, Instructions, Hard Rules, Common Mistakes) and a single clearly-signaled one-level reference to the feature-flags skill, meeting the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

71%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.

The description clearly conveys both purpose and trigger, scoped to React core with named channels, making it distinct and largely specific. It loses points mainly on trigger-term variety (missing jest/unit-tests phrasings) and could enumerate more concrete action variations.

Suggestions

Add natural trigger phrasings users actually say, e.g. 'Use when running jest tests, unit tests, or test patterns for React core'.

Mention the watch/TDD mode and the gate-pragma caveat in the description so the 'what' covers more of the skill's actual capabilities.

Keep the channel list but consider pairing each with its common user synonym (e.g. 'www (www-modern)') to broaden trigger coverage without much length.

Dimension	Reasoning	Score
Specificity	Names the domain ('run tests for React core') and enumerates concrete channel capabilities ('source, www, stable, and experimental channels'), giving several specific actions; gaps in coverage (e.g. watch mode, classic) keep it just below 5.	4 / 5
Completeness	Explicitly answers both what ('run tests for React core') and when ('Use when you need to run tests for React core'); the 'when' is present and channel-specific but not as richly triggered as the anchor-5 example.	4 / 5
Trigger Term Quality	Includes the natural phrase 'run tests' and channel keywords, but misses common variations users would say such as 'jest', 'unit tests', 'test pattern', or file extensions.	3 / 5
Distinctiveness Conflict Risk	'Run tests for React core' scoped to named release channels is a clear niche with distinct triggers and minimal conflict risk against generic test skills.	5 / 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: facebook/react
Path: .claude/skills/test/SKILL.md
Commit: eb8feb7

Reviewed: 3 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.