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

—

Does it follow best practices?

Impact

100%

4.54x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

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

The body is concise, fully actionable, and well-organized with executable npm commands and a complete pipeline. Its only real gap is workflow clarity: the batch quality-gate lacks explicit validation checkpoints or stop-on-failure guidance.

Suggestions

Add an explicit failure-handflow checkpoint to the pipeline, e.g. chain with '&&' (already done) but note 'stop on first failure; fix and re-run before proceeding' so Claude treats failures as a validation gate.

Clarify when to prefer the single-step commands vs. the combined pipeline (e.g., 'use individual commands to iterate; use the complete pipeline as the final PR gate') to make sequencing intent explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short 'When to Use' list and numbered commands each with a one-line purpose ('Verifies TypeScript types are correct'), with no padding or explanation of concepts Claude already knows, matching the score-3 lean-and-efficient anchor.	3 / 3
Actionability	Every step is a copy-paste-ready executable command (e.g., 'npm run lint', 'npm run typecheck', 'npm run test:coverage') and the closing pipeline is a concrete chained command, matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	Steps are clearly listed and a 'Complete Quality Pipeline' sequence is provided, but there is no validation/checkpoint guidance (e.g., stop on failure, verify before proceeding) for what is effectively a batch gating operation; per the rubric, missing validation in batch workflows caps workflow clarity at 2.	2 / 3
Progressive Disclosure	This is a short, single-purpose skill (well under 50 lines) with no external references needed; content is organized into clear 'When to Use', 'Instructions', and 'Complete Quality Pipeline' sections, which per the simple-skills note earns a 3 without external file references.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 solid: it uses third person, includes an explicit 'Use when' trigger clause, and covers natural user phrasing well. Its main weakness is specificity (summary-level rather than enumerating concrete sub-checks) and modest distinctiveness given the generic 'quality/lint/test' vocabulary.

Suggestions

List the concrete checks performed (e.g., 'lint, typecheck, format, unit/e2e/a11y tests') instead of the summary 'linting, type checking, and tests' to lift specificity toward 3.

Bind the skill to its project context (e.g., 'for the Spark UI project') in the description to reduce overlap with generic testing/linting skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('quality checks') and lists several actions ('linting', 'type checking', 'tests') but stays at a summary level rather than enumerating the concrete sub-commands (lint, typecheck, format, e2e, a11y) found in the body, so it is not fully comprehensive like the score-3 anchor.	2 / 3
Completeness	It explicitly answers both 'what' (run linting, type checking, and tests) and 'when' via a clear 'Use when...' clause with explicit triggers ('before committing', 'preparing a PR'), matching the score-3 anchor.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'verify code quality', 'before committing', 'preparing a PR' are phrases a user would plausibly say, matching the score-3 anchor's good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	It targets a recognizable niche (project quality pipeline before commit/PR) but 'quality checks', 'lint', and 'tests' are generic terms that could overlap with other development or testing skills, so it is only somewhat distinct rather than clearly non-conflicting.	2 / 3
	Total	10 / 12 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
Commit: 13e119c

Reviewed: about 17 hours 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.