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.

4.54x

Quality

72%

Does it follow best practices?

Impact

100%

4.54x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/run-quality-checks/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is exceptionally concise and fully actionable, listing copy-paste-ready commands and a complete PR pipeline. Its main weakness is workflow clarity: it never sequences the checks with validation feedback loops, which matters for a batch/PR-prep operation.

Suggestions

Add an explicit ordered workflow with checkpoints, e.g. run lint → stop on failure, then typecheck → stop on failure, then tests → stop on failure, then a11y.

Include a validation/feedback loop: 'If any step fails, fix the reported errors and re-run that step before proceeding.'

Clarify that the Complete Quality Pipeline is the default PR-prep sequence and that each step must pass before continuing.

Dimension	Reasoning	Score
Conciseness	Lean command-per-item structure with one-line descriptions and no padding or explanations of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Each check is a copy-paste-ready npm command with a clear label, and the pipeline section gives a fully executable one-liner covering the common PR case.	5 / 5
Workflow Clarity	It lists commands but provides no sequenced workflow with validation checkpoints — no guidance to stop on lint failure, verify typecheck before tests, or confirm coverage/a11y pass before a PR — leaving rough sequence with validation absent.	2 / 5
Progressive Disclosure	A short, well-organized single-file skill under 50 lines with clear section headers and no external references; per the simple-skill exception this is appropriately structured with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

63%Weight 40%Scale 1-5

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 clearly states both what it does and when to use it, with concrete check categories and reasonable trigger phrases. It could improve by surfacing the specific trigger keywords ('lint', 'typecheck') and the full check inventory to boost specificity and distinctiveness.

Suggestions

Add concrete trigger keywords users would say, e.g. 'Use when the user mentions lint, typecheck, tests, or quality checks'.

Expand the capability list to mention formatting, coverage, e2e, and accessibility checks for fuller coverage.

Tighten the niche by framing it as 'code quality pipeline for the Spark UI project' to reduce overlap with generic build/test skills.

Dimension	Reasoning	Score
Specificity	Names several concrete checks ('linting, type checking, and tests') but stops at three categories without enumerating specifics like formatting, coverage, e2e, or a11y found in the body — minor coverage gaps keep it below 5.	4 / 5
Completeness	It explicitly answers both what ('Run all quality checks including linting, type checking, and tests') and when ('Use when the user wants to verify code quality, before committing, or when preparing a PR'), but the when could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes natural phrases ('verify code quality', 'before committing', 'preparing a PR') but lacks the concrete trigger words the body mentions ('lint', 'typecheck') and common synonyms a user would actually say, leaving gaps versus the 4-anchor.	3 / 5
Distinctiveness Conflict Risk	'Run all quality checks' is a broad project-maintenance niche that could overlap with general test/build skills; the PR/commit framing adds some specificity but conflict risk with sibling quality skills remains.	3 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: leboncoin/spark-web
Path: .cursor/skills/run-quality-checks/SKILL.md
Commit: ae95bee

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.