CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/gtm-present/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A well-structured, token-efficient overview that delegates executable detail appropriately to one clearly signaled reference file. The gaps are in the body's own actionability and workflow: no concrete command or snippet inline, and no explicit post-fix re-measurement loop.

Suggestions

Inline one small executable anchor in the body (e.g. the async GTM snippet or the exact Lighthouse/DevTools steps to spot third-party blocking), so the Fix section is not purely high-level.

Make the measure → fix → re-measure loop explicit: add a verify step after Fix (e.g. 'Re-run Lighthouse and confirm the third-party blocking / LCP improvement') rather than leaving verification only in the reference file.

Drop the generic opening sentence about what an unoptimized GTM setup causes; Claude already knows this, and the Quick Reference bullets carry the same information.

DimensionReasoningScore

Conciseness

The body is lean and section-driven with almost no padding, but the opening sentence ('An unoptimized GTM setup can lead to significant main-thread blocking and increased page weight, slowing down the overall user experience') explains background Claude already knows and could be trimmed.

4 / 5

Actionability

The body gives high-level direction with named tools ('Place the GTM script in the <head> but audit its impact', 'evaluate its impact on page performance using Lighthouse', 'Use Server-Side GTM'), but all executable code and commands are delegated to references/rule.md — no snippet, command, or specific DevTools/Lighthouse step appears in the body itself.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections establish a rough sequence with a measure-first checkpoint ('Verify that GTM is implemented correctly... using Lighthouse'), but the measure → fix → re-measure feedback loop is only implicit in the body; the verification steps live in the reference file.

3 / 5

Progressive Disclosure

The body is under 50 lines, cleanly sectioned, and points to a single one-level-deep reference that exists in the bundle ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), with the reference's contents clearly signaled.

5 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description with an explicit and specific 'Use when' trigger, a concrete verify-before-recommending what, and mostly natural trigger terms. Its main weaknesses are the missing 'GTM' acronym/page-speed synonyms and that the capability list is confined to auditing rather than the optimization guidance the skill body provides.

DimensionReasoningScore

Specificity

The description names the domain and a couple of concrete actions ('auditing slow page loads, heavy assets, or rendering delays', 'Verify the actual bottleneck in DevTools, Lighthouse, or field data'), but the actions cluster around a single audit/verify theme and it never states what optimization the skill actually performs (tag cleanup, async loading, server-side GTM), so coverage is not comprehensive.

3 / 5

Completeness

It explicitly answers both parts: an explicit 'Use when auditing slow page loads... related to Optimize Google Tag Manager implementation' trigger clause, and a concrete what ('Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes').

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'slow page loads', 'heavy assets', 'rendering delays', 'Google Tag Manager', 'DevTools', 'Lighthouse', 'field data' — but common synonyms users would say are missing, notably the 'GTM' acronym and 'page speed'.

4 / 5

Distinctiveness Conflict Risk

The GTM scoping creates a clear niche with distinct triggers, but the broad performance phrasing ('slow page loads', 'rendering delays') creates minor overlap risk with generic page-performance audit skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/gtm-present/SKILL.md

Reviewed

Table of Contents

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.