lint-build-test
How to check code by linting, building, and testing.
73
60%
Does it follow best practices?
Impact
93%
1.60xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/lint-build-test/SKILL.mdQuality
Discovery
32%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 a brief, high-level summary that names three concrete activities but lacks depth in each. It is missing an explicit 'Use when...' clause, which significantly hurts completeness and makes it harder for Claude to know when to select this skill over others. The description would benefit from more specific trigger terms and explicit usage guidance.
Suggestions
Add a 'Use when...' clause with trigger terms like 'Use when the user asks to lint, build, compile, run tests, check for errors, or validate code before committing.'
Include common natural language variations users might say, such as 'run tests', 'compile', 'type check', 'CI checks', 'pre-commit checks', or specific tool names like 'eslint', 'pytest', 'tsc'.
Expand the 'what' portion to specify what kind of code or projects this applies to, e.g., 'Runs linters, builds the project, and executes test suites to validate code correctness and style compliance.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code checking) and lists three actions (linting, building, testing), but doesn't elaborate on specific tools, languages, or concrete sub-actions within each category. | 2 / 3 |
Completeness | Describes 'what' at a high level (check code by linting, building, testing) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'linting', 'building', and 'testing' which users might naturally say, but misses common variations like 'lint', 'compile', 'run tests', 'CI', 'check errors', 'type check', or specific tool names. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of linting, building, and testing provides some specificity, but 'check code' is fairly generic and could overlap with code review skills, CI/CD skills, or individual linting/testing skills. | 2 / 3 |
Total | 7 / 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-structured, concise skill that provides clear, actionable commands for checking code in a yarn monorepo. Its main weakness is the lack of error recovery guidance — when lint, build, or test steps fail, there's no explicit feedback loop (e.g., fix lint errors and re-run before proceeding to build). The decision tree for what to run based on changed file types is a nice touch.
Suggestions
Add a feedback loop for error handling: e.g., if lint:fix produces errors that can't be auto-fixed, fix them manually and re-run before proceeding to build; if build fails, don't proceed to test.
Consider adding a brief note about what to do when source file changes span multiple packages (e.g., should each affected package be checked individually, or should the full monorepo check be used?).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what linting or building is, assumes Claude knows git commands and yarn workspaces, and every section serves a clear purpose. No unnecessary padding. | 3 / 3 |
Actionability | Provides specific, copy-paste ready commands (e.g., `yarn workspace <package-name> lint:fix`, `yarn lint:fix`). The file categorization is concrete with explicit extensions listed. The decision tree for what to run is clear and unambiguous. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (analyze → determine → run), and the numbered sub-steps within the full check are well-ordered. However, there's no validation or error recovery guidance beyond 'report any errors encountered' — no feedback loop for fixing lint errors and re-running, or handling build failures before proceeding to tests. | 2 / 3 |
Progressive Disclosure | This is a simple, single-purpose skill under 50 lines with no need for external references. The content is well-organized with clear headers and logical sections that are easy to scan. | 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
- MetaMask/ocap-kernel
- Commit
a3eff0e
- 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.