gtm-present

Use when auditing slow page loads, heavy assets, or rendering delays related to Optimize Google Tag Manager implementation. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

Quality

70%

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/gtm-present/SKILL.md

Quality

Content

57%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 lean, well-structured overview with correct progressive disclosure to a single real reference file, but the guidance itself stays high-level: actions are named without executable specifics, and the workflow lacks a post-fix validation checkpoint. It reads as a checklist pointer rather than self-contained actionable instruction.

Suggestions

Add executable specifics to the Check and Fix sections, e.g., a Lighthouse CLI invocation (lighthouse https://example.com --view) and the concrete GTM steps for async loading or trigger throttling, even if one line each.

Add an explicit validation checkpoint after Fix, e.g., 'Re-run Lighthouse after changes to confirm the blocking time dropped' — Check -> Fix -> Re-measure closes the loop.

Move or trim the generic intro sentence about GTM causing main-thread blocking, since it explains a concept Claude already knows and adds no instruction.

Dimension	Reasoning	Score
Conciseness	The body is ~30 lean lines with well-organized sections and no tutorial-style padding; only the intro sentence 'An unoptimized GTM setup can lead to significant main-thread blocking and increased page weight, slowing down the overall user experience' over-explains what Claude already knows. Not 5 due to that minor padding; not 3 because there are no verbose multi-sentence explanations.	4 / 5
Actionability	Bullets name real actions ('Minimize the number of tags and triggers to reduce execution', 'Use Server-Side GTM', 'Clean up unused tags, use asynchronous loading') but no executable specifics — no Lighthouse command or CLI, no steps for enabling async loading or server-side setup, deferring all detail to the reference. Matches the some-concrete-guidance-but-incomplete anchor; not 4 because the body's guidance cannot be acted on without reading references/rule.md.	3 / 5
Workflow Clarity	Check -> Fix -> Explain -> Code Review sections provide a rough sequence and 'Verify that GTM is implemented correctly and evaluate its impact using Lighthouse' is a check step, but there is no validation checkpoint after the fix (e.g., re-run Lighthouse to confirm improvement). Sequence present with missing checkpoints matches anchor 3; not 4 because the post-fix validation is entirely implicit.	3 / 5
Progressive Disclosure	The body is a short overview with a clearly signaled one-level-deep reference — 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md' — and the file exists and holds the implementation detail (verified GTM snippets and trigger examples). This matches the clear-overview anchor and the simple-skill note allowing 5.	5 / 5
	Total	15 / 20 Passed

Description

83%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 is strong: it explicitly states both what the skill does and when to use it, with concrete natural trigger terms tied to a distinct GTM-performance niche. Minor room for improvement in adding common synonyms (GTM, page speed) and naming fix-side actions.

Dimension	Reasoning	Score
Specificity	Concrete actions are explicitly stated ('auditing slow page loads, heavy assets, or rendering delays', 'Verify the actual bottleneck in DevTools, Lighthouse, or field data'), matching the several-specific-actions anchor with minor gaps. Not 5 because fix-side capabilities like tag cleanup or server-side migration are not named; not 3 because more than 1-2 concrete actions are listed.	4 / 5
Completeness	Both what and when are explicitly answered: 'Use when auditing slow page loads...' gives concrete trigger phrases, and 'Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes' states the what. Not 4 because the when clause is fully explicit with concrete triggers rather than merely present.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ('slow page loads', 'heavy assets', 'rendering delays', 'DevTools', 'Lighthouse'). Not 5 because common synonyms and variations such as 'GTM', 'page speed', or 'Core Web Vitals' are missing.	4 / 5
Distinctiveness Conflict Risk	'Optimize Google Tag Manager implementation' carves out a clear niche, but generic trigger phrases like 'slow page loads' and 'heavy assets' could also fire a general performance-audit skill, giving minor overlap risk. Not 5 due to that overlap with closely related performance skills.	4 / 5
	Total	17 / 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/gtm-present/SKILL.md
Commit: 7bfd868

Reviewed: 1 day 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.