lint-new
Create a new ESLint rule with tests for eslintPluginScraps. Use when asked to "create a lint rule", "add an eslint rule", "scaffold a rule", "write a new scraps rule", or "new design system lint rule". Covers rule creation, test authoring, registration, and autofix implementation.
94
92%
Does it follow best practices?
Impact
96%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities, includes a well-crafted 'Use when' clause with multiple natural trigger phrases, and is clearly scoped to a distinct niche (ESLint rule creation for a specific plugin). The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: rule creation, test authoring, registration, and autofix implementation. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create ESLint rules with tests, covering rule creation, test authoring, registration, autofix) and 'when' (explicit 'Use when' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'create a lint rule', 'add an eslint rule', 'scaffold a rule', 'write a new scraps rule', 'new design system lint rule'. These are realistic user phrasings with good variation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific plugin (eslintPluginScraps), a specific task (ESLint rule creation), and includes domain-specific terms like 'scraps rule' and 'design system lint rule' that clearly distinguish it from general coding or linting skills. | 3 / 3 |
Total | 12 / 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.
This is a strong, well-structured skill that provides clear, actionable guidance for creating ESLint rules. The step-by-step workflow with concrete templates, utility tables, and explicit verification commands makes it highly usable. Minor verbosity in the autofix section and Fixer API documentation slightly reduces token efficiency, but overall the content earns its place.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and well-structured with tables and templates, but includes some content Claude already knows (e.g., the Fixer API comments listing all methods, basic explanations of when not to autofix). The utility table and archetype table are valuable domain-specific knowledge. Some sections like 'Extending an Existing Rule' add breadth that could be a separate reference. | 2 / 3 |
Actionability | Provides fully executable TypeScript templates for both rule and test files, concrete bash commands for running tests, specific file paths for registration, and real utility names with their locations. The templates are copy-paste ready with clear placeholder variables ($ARGUMENTS, $RULE_NAME). | 3 / 3 |
Workflow Clarity | Clear 4-step sequence (Choose Archetype → Check Utilities → Create Files → Register Rule) with explicit verification steps (run tests after creation and after registration). The workflow includes a feedback loop via test execution and clear validation checkpoints before proceeding. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to archetype docs, style-collector guide, and schema patterns. The main SKILL.md stays focused on the workflow while pointing to specific reference files for detailed archetype information. Tables make navigation easy. | 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
- getsentry/sentry
- Commit
552fb5c
- 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.