frontend-checklist-global

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

Quality

59%

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

56%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 body is a well-structured, actionable audit guide with a clear tool workflow and verification loop, but it is materially hurt by heavy intra-document repetition and by inlining (and duplicating) detail that already exists in the reference file. Tightening the duplication would lift both conciseness and progressive disclosure.

Suggestions

Remove the Rule-Derived Highlights and Known Safe Patterns blocks from SKILL.md and point to references/categories.md instead, since that content is already duplicated there.

Consolidate the decorative-image guidance, which currently recurs across five sections, into a single statement in either Audit Stance or the reference.

Show exact MCP tool call signatures (parameters) for at least review_code and audit_url so the workflow steps are copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The same decorative-image / alt="" guidance is restated across Audit Stance, Coverage Checklist, Rule-Derived Highlights, Known Safe Patterns, and Conflict Resolution, and the entire Highlights + Safe Patterns block is duplicated verbatim in references/categories.md, producing several padded, redundant sections.	2 / 5
Actionability	It names exact MCP tools (review_code, audit_url, get_rule, fix_rule, etc.) and supplies concrete code snippets for safe patterns, but tool call signatures are not shown, leaving minor gaps below the fully copy-paste-ready 5 anchor.	4 / 5
Workflow Clarity	A clear 5-step tool-routing sequence is present alongside an Evaluation Standard feedback loop ('use search_rules to broaden review coverage before concluding clean'); the operation is non-destructive so the batch/destructive cap does not apply, but per-step validation checkpoints are not explicit, holding it just below 5.	4 / 5
Progressive Disclosure	Sections are well-headed and references/categories.md is signaled once at the end, but the bulk Highlights, Safe Patterns, and Coverage detail that already lives in the reference is inlined in SKILL.md, matching 'some structure; references present; content that should be separate is inline'.	3 / 5
	Total	13 / 20 Passed

Description

62%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 explicitly pairs a what-statement with a 'Use when' trigger and is anchored to a distinctive named corpus, but its actions are generic and its trigger keywords lack common synonyms. It reads as a competent but not maximally specific routing description.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'auditing, scoring, and fixing accessibility, performance, SEO, and security issues'.

Expand the 'Use when' clause with concrete trigger phrases users actually say, such as 'frontend review', 'accessibility audit', or 'SEO check'.

Avoid reusing the same phrase for both the what and the when; give the when its own concrete trigger scenarios.

Dimension	Reasoning	Score
Specificity	Names the domain ('frontend codebase against the full Front-End Checklist rule corpus') and two actions ('auditing or improving'), but the actions are generic verbs rather than a comprehensive list of concrete capabilities, matching the anchor for domain + 1-2 actions.	3 / 5
Completeness	An explicit 'Use when...' clause provides the trigger and the same clause states the what, so both are present; the when is not capped at 3 but reuses the what phrasing and lacks concrete trigger scenarios, placing it above 3 yet below the fully-explicit 5 anchor.	4 / 5
Trigger Term Quality	'auditing or improving any frontend codebase' and the named 'Front-End Checklist' are relevant natural terms, but common variations users would say (frontend review, accessibility/performance/SEO audit) are missing, fitting the 'some relevant keywords but missing synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	Being scoped to a named 'Front-End Checklist rule corpus through one entry point' gives it a clear niche with minimal conflict risk, though it still overlaps slightly with general frontend review/audit skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 20 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: 30756a7

Reviewed: 13 days 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.