test
Use when you need to run tests for React core. Supports source, www, stable, and experimental channels.
88
81%
Does it follow best practices?
Impact
100%
2.85xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
75%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 is functional and clearly scoped to React core testing with explicit 'Use when' guidance and distinct channel identifiers. However, it lacks specificity in describing concrete actions beyond 'run tests' and could benefit from more natural trigger terms that users might employ when needing this skill.
Suggestions
Add more specific actions such as 'Runs unit tests, integration tests, and builds for React core packages'
Include additional natural trigger terms like 'jest', 'test suite', 'React test failures', or 'run CI checks'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (React core testing) and mentions specific channels (source, www, stable, experimental), but doesn't describe concrete actions beyond 'run tests'. Missing details like what kinds of tests, how they're run, or what outputs are produced. | 2 / 3 |
Completeness | Explicitly answers both 'what' (run tests for React core across multiple channels) and 'when' ('Use when you need to run tests for React core'). The 'Use when' clause is present and provides clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'tests', 'React core', and channel names (www, stable, experimental), but misses common variations users might say such as 'unit tests', 'jest', 'test suite', 'CI', or 'react testing'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to React core testing with named channels (source, www, stable, experimental), making it clearly distinguishable from general testing skills or other framework-specific skills. Unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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-crafted, concise skill that provides exact commands for each React test channel with clear usage examples. The channel mapping table and hard rules are particularly valuable. The only notable weakness is the lack of error recovery guidance in the workflow—e.g., what to do when sandbox issues occur despite --no-watchman, or how to interpret ambiguous test output.
Suggestions
Add a brief error recovery step (e.g., 'If tests fail to start, check node_modules with yarn install; if watchman errors persist despite --no-watchman, check sandbox permissions') to strengthen the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what React is, what testing is, or how yarn works. The channel mapping table is dense and informative. Token-efficient throughout. | 3 / 3 |
Actionability | Provides exact yarn commands for each channel, specific flags (--silent, --no-watchman), concrete usage examples with patterns, and clear argument parsing instructions. Copy-paste ready commands. | 3 / 3 |
Workflow Clarity | The 3-step workflow (parse → map → report) is clear and the channel-to-command mapping is explicit. However, there's no validation or error recovery guidance—what to do if tests fail to run (vs fail assertions), no feedback loop for common errors beyond the brief 'Common Mistakes' section. | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope, the content is well-organized into logical sections (usage examples, channels, instructions, rules, common mistakes). The cross-reference to the `feature-flags` skill is appropriately one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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
- facebook/react
- Commit
705268d
- 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.