frontend-checklist-global

Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/frontend-checklist-global/SKILL.md

Quality

Content

77%

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

The content is highly actionable with concrete tool calls and well-structured decision checkpoints, and progressive disclosure is clean with a single real reference file. Its main weakness is conciseness: the decorative-image and Next-metadata guidance is restated across several sections, inflating the token budget without adding new information.

Suggestions

Consolidate the repeated decorative-image/alt='' guidance into a single section (Audit Stance, Known Safe Patterns, and Conflict Resolution all restate the same zero-issue pattern) to reduce redundancy.

Fold the duplicated Next.js metadata-api advice into one canonical location instead of repeating it in Audit Stance, Known Safe Patterns, and Conflict Resolution.

Trim the Coverage block's rule counts if they are not needed at load time, or move them into references/categories.md where they can be retrieved on demand.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but it repeats the same decorative-image/alt/Next-metadata guidance across Audit Stance, Coverage Checklist, Rule-Derived Highlights, Known Safe Patterns, and Conflict Resolution, adding considerable redundancy that could be tightened.	2 / 3
Actionability	It gives concrete, executable guidance: specific MCP tool calls (review_code, audit_url, get_rule, fix_rule), concrete code/markup patterns to recognize, and explicit zero-issue examples that are copy-paste ready for decision-making.	3 / 3
Workflow Clarity	The numbered Workflow sequence is clear, and Audit Stance plus Conflict Resolution act as explicit validation/decision checkpoints that tell Claude when to suppress or escalate findings, providing feedback loops for the review process.	3 / 3
Progressive Disclosure	SKILL.md is an overview with a single clearly signaled one-level-deep reference (references/categories.md, which exists as a real file) plus an external MCP docs link, with no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 has an explicit 'Use when' trigger and names a clear niche (the Front-End Checklist corpus), but it stays at a high level of abstraction and does not enumerate the concrete actions the skill performs or the fuller set of natural trigger terms a user might say.

Suggestions

List the concrete actions the entry point enables (e.g., review code, audit URLs, retrieve rules, get remediation fixes) so specificity reaches the multi-action anchor.

Add more natural trigger terms users would actually say, such as 'frontend review', 'accessibility/performance/SEO audit', or 'run the Front-End Checklist'.

Narrow the scope wording from 'any frontend codebase' to make the skill clearly distinct from generic frontend-review skills and reduce conflict risk.

Dimension	Reasoning	Score
Specificity	It names the domain ('frontend codebase') and the action ('auditing or improving') plus the corpus ('full Front-End Checklist rule corpus'), but describes only two broad actions rather than listing multiple concrete actions like reviewing, fixing, or explaining rules.	2 / 3
Completeness	It answers 'what' (auditing/improving a frontend codebase against the rule corpus) and 'when' with an explicit 'Use when' trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	'Auditing or improving any frontend codebase' are natural terms a user would say, but it omits common variations such as 'frontend review', 'accessibility audit', 'performance check', or 'Front-End Checklist' as a user-quoted phrase, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The 'Front-End Checklist rule corpus' niche is fairly distinct, but 'auditing or improving any frontend codebase' is broad enough that it could overlap with generic frontend review skills; the specific corpus anchor helps but the trigger is not narrowly scoped.	2 / 3
	Total	9 / 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/frontend-checklist-global/SKILL.md
Commit: 48405aa

Reviewed: about 11 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.