verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
75
62%
Does it follow best practices?
Impact
98%
2.57xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/verify/SKILL.mdQuality
Discovery
40%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 focuses almost entirely on when to use the skill but fails to explain what it actually does in concrete terms. It lacks specific actions, comprehensive trigger terms, and enough detail to clearly distinguish it from other validation or code-quality skills. The 'React contribution requirements' mention provides some niche targeting but is too vague to be truly distinctive.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Runs linting, type checking, unit tests, and formatting checks for React contributions.'
Expand trigger terms to include natural phrases users would say, such as 'lint', 'pre-commit', 'CI checks', 'code review', 'pull request', 'PR validation'.
Clarify the 'what' portion by listing the specific React contribution requirements being checked (e.g., ESLint rules, TypeScript compilation, test coverage).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'validate changes' and 'check all React contribution requirements' but does not list any concrete actions (e.g., run linting, run tests, check formatting). The actions are vague and abstract. | 1 / 3 |
Completeness | The description provides a 'Use when...' clause addressing when to use the skill, but the 'what does this do' part is essentially missing—it never explains what concrete actions the skill performs, only vaguely references validation and checking requirements. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'validate changes', 'committing', and 'React contribution requirements', but misses common variations users might say such as 'lint', 'pre-commit checks', 'CI checks', 'code quality', or 'pull request validation'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Validate changes before committing' is somewhat generic and could overlap with general linting, testing, or CI skills. The mention of 'React contribution requirements' adds some specificity but is still fairly broad. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-structured verification workflow that clearly sequences serial and parallel steps with appropriate failure handling. The main weakness is that the $ARGUMENTS parameter is declared but never shown being passed to the `/test` commands, and the delegated flows are referenced without clarifying their exact invocation syntax.
Suggestions
Show how $ARGUMENTS is passed to the /test steps, e.g., `Use /test $ARGUMENTS` to make the argument usage explicit and actionable.
Briefly indicate the exact invocation syntax for /flow and /test (e.g., are these slash commands, scripts, or subagent skill references?) to improve actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what yarn, linting, or type checking are. The skill is lean and assumes Claude's competence. | 3 / 3 |
Actionability | Provides concrete commands (`yarn prettier`, `yarn linc`) and references to other flows (`/flow`, `/test`), but the `$ARGUMENTS` usage is not shown in the actual commands, and the `/flow` and `/test` references are opaque without knowing what they resolve to. Missing explicit command syntax for the parallel steps. | 2 / 3 |
Workflow Clarity | Clear sequential-then-parallel workflow with explicit stop-on-failure checkpoints at each step. Includes error handling guidance (stop immediately, report with suggested fixes). For a simple verification skill, this is well-sequenced. | 3 / 3 |
Progressive Disclosure | This is a short, single-purpose skill under 50 lines that delegates to other flows (`/flow`, `/test`) for detailed behavior. The structure is clean with clear sections for arguments and instructions. | 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.