consent-mode

Use when auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/consent-mode/SKILL.md

Quality

Content

57%

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, concise overview with clean progressive disclosure to a real one-level reference file, but it leans on descriptive guidance rather than executable steps in the body itself and keeps its validation checkpoints implicit.

Suggestions

Remove the opening GDPR/Consent Mode background sentence that Claude already knows to tighten conciseness.

Surface at least one short executable gtag.js consent-default snippet in the body so the skill is copy-paste ready without opening the reference.

Make the validate-before-recommend checkpoint explicit as a numbered step (measure in DevTools/Lighthouse -> confirm bottleneck -> then fix) rather than implied across sections.

Dimension	Reasoning	Score
Conciseness	The body is short overall, but the opening paragraph explains Consent Mode/GDPR context Claude largely already knows and the Quick Reference bullets lightly duplicate the Check section, so it could be tightened rather than being fully lean.	2 / 3
Actionability	It names concrete specifics ('ad_user_data', 'ad_personalization', DevTools/Lighthouse) but stops at 'Update your GTM or gtag.js implementation to support...' without executable steps in the body, deferring the actual code to the reference file.	2 / 3
Workflow Clarity	A Check/Fix/Explain/Code Review sequence exists and a validation mention ('Verify the actual bottleneck... before recommending changes', 'describe the measurement method') is present, but the validation checkpoints are implicit rather than explicit ordered validate-fix-retry steps.	2 / 3
Progressive Disclosure	The body is a concise overview that clearly signals a single one-level-deep reference ('see references/rule.md'), which exists and holds the detailed code and guidance, so content is appropriately split with easy navigation.	3 / 3
	Total	9 / 12 Passed

Description

50%

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 includes an explicit 'Use when...' trigger and names concrete tools, but it frames the skill as a generic performance-auditing task rather than the Consent Mode v2 implementation skill it actually is, weakening specificity, trigger relevance, and distinctiveness.

Suggestions

Rewrite the description to state the skill's real capability (e.g., 'Implement and verify Google Consent Mode v2 consent states in GTM/gtag.js') instead of generic performance auditing.

Add Consent-Mode-specific trigger terms users would naturally say (consent banner, CMP, ad_user_data, ad_personalization, gtag.js, GDPR/EEA).

Drop the generic performance phrases ('slow page loads', 'heavy assets', 'rendering delays') that cause overlap with unrelated performance skills.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('auditing slow page loads, heavy assets, or rendering delays') and tools ('DevTools, Lighthouse, or field data'), but these describe a performance-audit workflow rather than the skill's actual implementation capabilities (GTM/gtag.js consent types), so it is not comprehensive.	2 / 3
Completeness	An explicit 'Use when...' clause answers the 'when', and a partial 'what' is present ('auditing', 'verifying the bottleneck'), but the described 'what' does not accurately reflect the skill's real purpose (implementing Consent Mode v2), leaving the capability statement misaligned rather than clearly answered.	2 / 3
Trigger Term Quality	It includes natural trigger phrases ('slow page loads', 'heavy assets', 'rendering delays'), but these are generic performance terms; Consent-Mode-specific keywords a user would say (consent, CMP, ad_user_data, GTM) are largely missing, so coverage of the actual domain is incomplete.	2 / 3
Distinctiveness Conflict Risk	The Consent Mode v2 anchor gives it a niche, but the trigger language ('slow page loads', 'rendering delays') is generic performance phrasing that would overlap with other performance-audit skills, so it is not distinctly scoped.	2 / 3
	Total	8 / 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/consent-mode/SKILL.md
Commit: 48405aa

Reviewed: about 8 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.