CtrlK
BlogDocsLog inGet started
Tessl Logo

third-party-scripts

Use when auditing slow page loads, heavy assets, or rendering delays related to Optimize third-party script loading. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

65

Quality

78%

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/third-party-scripts/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A compact, well-organized overview that delegates depth to a real reference file, but the in-body guidance is high-level and the workflow lacks explicit validation checkpoints. The strongest dimension is progressive disclosure; the weakest are actionability and workflow clarity, where executable examples and a verify→fix→recheck loop would lift the score.

Suggestions

Add a small executable snippet (e.g. an async/defer script tag or a Lighthouse CLI command) directly in the body so guidance is copy-paste ready without opening the reference.

Replace the marketing-style opening line with a one-line diagnostic directive, and fold the vague Check/Fix lines into a concrete numbered workflow with a validate→fix→recheck checkpoint.

Make the Code Review section's verification step explicit (e.g. 'Record a trace, confirm third-party long tasks drop below ~50ms, then stop') so the feedback loop is visible in SKILL.md.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence, but the opening 'Third-party scripts are the #1 cause of slow websites—unoptimized loading can add 2-5 seconds' is padded marketing-flavored context Claude already knows, and the Check/Fix lines are somewhat generic. Mostly efficient but could be tightened.

2 / 3

Actionability

The Quick Reference gives concrete directives ('Use async for independent scripts', 'Lazy-load non-critical scripts after page load'), but the body itself carries no executable code or commands — the copy-paste-ready examples are offloaded to references/rule.md. Guidance is actionable but general rather than fully executable in-body.

2 / 3

Workflow Clarity

Check/Fix/Explain/Code Review give a rough sequence and the Code Review section asks to 'describe the measurement method used to confirm the issue', but there is no explicit validate→fix→retry feedback loop or validation checkpoints for the diagnostic task.

2 / 3

Progressive Disclosure

The body is short and well-organized into clear sections and points to the one-level-deep, clearly signaled references/rule.md (verified to exist) for implementation details, fitting the simple-skill allowance for a well-structured overview.

3 / 3

Total

9

/

12

Passed

Description

100%

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, well-scoped description that covers concrete actions, natural trigger terms, an explicit 'Use when' clause, and a clear niche. It distinguishes itself by pairing the trigger with a verification directive rather than over-claiming.

DimensionReasoningScore

Specificity

The description names multiple concrete actions — 'auditing slow page loads, heavy assets, or rendering delays' and 'Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes' — with named tools, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It explicitly answers both what (audit/verify third-party script loading bottlenecks and recommend changes) and when via an explicit 'Use when...' clause, matching the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

It uses natural performance-complaint terms a user would actually say ('slow page loads', 'heavy assets', 'rendering delays', 'DevTools', 'Lighthouse'), giving good coverage rather than only jargon or a single keyword.

3 / 3

Distinctiveness Conflict Risk

It is scoped narrowly to third-party script loading performance with distinct, specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.