improve-rule

Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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

A well-structured, actionable meta-skill with concrete commands, an ordered workflow, validation checkpoints, and proper reference offloading. The only real slack is minor redundancy between the intro, the 'Explain' rationale, and the offloaded scoring spec.

Suggestions

Trim the intro paragraph (it duplicates the frontmatter description) and tighten the 'Explain' section to rule-specific rationale only.

Make the fix→verify loop explicit in the Fix workflow (e.g., 're-run pnpm score:rules and repeat until ≥ 50') rather than leaving re-scoring only in the Code Review checklist.

The inline dimension table partially duplicates references/scoring-rubric.md; confirm the table adds enough navigational value to justify the inline tokens or link out sooner.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and command snippets, but the intro paragraph restates the frontmatter description and the 'Explain' section is motivational rationale Claude could largely infer — fitting 'mostly efficient but could be tightened' rather than the every-token-earns-its-place anchor at 3.	2 / 3
Actionability	Copy-paste commands ('pnpm score:rules …', 'pnpm validate:rule-structure …'), a concrete grep pattern, and specific thresholds ('Score is ≥ 50', 'At least 3 tldr bullets') give fully actionable guidance appropriate for an instruction-only skill.	3 / 3
Workflow Clarity	A clear Check → Fix → Code Review sequence with explicit validation commands and a verification checklist; MDX editing is not in the destructive/batch category that would cap this at 2.	3 / 3
Progressive Disclosure	A concise dimension table serves as the overview while the full spec is offloaded to a real, well-signaled one-level-deep reference ('see references/scoring-rubric.md for full details'), which the bundle listing confirms exists.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-triggered description that names four concrete actions and uses an explicit 'Use when…' clause for a clearly distinct niche. Trigger-term naturalness is the only weak spot, leaning slightly technical.

Suggestions

Add more natural phrasings a user might say (e.g., 'review a rule', 'pass the quality check', 'fix lint errors') alongside the technical terms to broaden trigger coverage.

Consider leading with a short third-person capability clause before the 'Use when…' trigger to match the canonical [capabilities]. Use when [trigger] pattern.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples' — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicit 'Use when…' trigger plus a clear capability list answers both what and when; the trigger clause is present so completeness is not capped at 2 per the guidelines.	3 / 3
Trigger Term Quality	Relevant terms exist ('reviewing', 'improving', 'fix stub prompts') but lean technical ('MDX file', 'stub prompts', 'quality score') and lack common user phrasings, fitting 'some relevant keywords but missing common variations' rather than the broad natural-variation coverage at 3.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'Front-End Checklist rule MDX file' with project-specific triggers, giving a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/improve-rule/SKILL.md
Commit: 48405aa

Reviewed: about 13 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.