run-quality-checks
Run all quality checks including linting, type checking, and tests. Use when the user wants to verify code quality, before committing, or when preparing a PR.
88
82%
Does it follow best practices?
Impact
100%
4.54xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 a strong description that clearly communicates what the skill does and when to use it. It lists concrete actions and includes natural trigger terms that developers would use. The only minor weakness is potential overlap with more specialized linting, testing, or type-checking skills if they exist in the same skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'linting, type checking, and tests' — these are distinct, well-defined quality check activities. | 3 / 3 |
Completeness | Clearly answers both what ('Run all quality checks including linting, type checking, and tests') and when ('when the user wants to verify code quality, before committing, or when preparing a PR') with explicit trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'quality checks', 'linting', 'type checking', 'tests', 'code quality', 'committing', 'PR'. These cover common developer vocabulary well. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies linting, type checking, and tests together, it could overlap with individual skills for linting, testing, or type checking separately. The combined nature helps but 'code quality' is somewhat broad. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides clear, executable commands for running quality checks. Its main weaknesses are minor verbosity in describing what each tool does (which Claude already knows) and the lack of error-handling guidance when steps in the pipeline fail. The complete pipeline command at the end is a strong practical addition.
Suggestions
Remove the one-line descriptions after each command (e.g., 'Checks code style and quality with Oxlint') since Claude already understands these tools — this would improve conciseness.
Add brief error-handling guidance, e.g., 'If lint fails, fix reported issues and re-run before proceeding' to improve workflow clarity for the pipeline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanations (e.g., 'Checks code style and quality with Oxlint', 'Verifies TypeScript types are correct') that Claude already knows. The one-line descriptions after each command add marginal value and could be trimmed. | 2 / 3 |
Actionability | Every step provides a concrete, copy-paste-ready bash command. The complete quality pipeline at the end gives a single executable command chain for the most common use case (pre-PR check). | 3 / 3 |
Workflow Clarity | Steps are clearly listed and the complete pipeline provides a sequence, but there are no validation checkpoints or feedback loops — no guidance on what to do when a step fails, how to interpret errors, or whether to continue after a failure. For a quality check pipeline, error handling guidance would be valuable. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill with no bundle files, the content is well-organized with clear sections (When to Use, Instructions, Complete Quality Pipeline). The length is appropriate and doesn't need external references. | 3 / 3 |
Total | 10 / 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
- leboncoin/spark-web
- Commit
76a3678
- 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.