CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

73%

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

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.

The body is a clean, brief overview that delegates implementation detail appropriately to references/rule.md. Its weaknesses are duplicated guidance between the Quick Reference, Check, and Fix sections, the absence of any inline executable example or concrete measurement step, and a workflow that lacks an explicit verify-after-fix checkpoint.

Suggestions

Inline one minimal executable snippet (e.g. the blocking vs async/defer head comparison from the reference) so the fix is copy-paste ready without opening the reference file.

Make the Check step concrete: specify what to look for in Chrome DevTools' Network waterfall (third-party requests on the critical path, script request start time vs main-thread blocking) or a Lighthouse audit to run.

Add an explicit post-fix verification checkpoint (re-run Lighthouse / re-check the waterfall and compare before/after) so the workflow closes the loop, and merge the redundant Check/Fix lines into the Quick Reference.

DimensionReasoningScore

Conciseness

The body is lean with well-chosen bullets, but the Check and Fix lines largely restate the Quick Reference bullets, and the "#1 cause of slow websites ... 2-5 seconds" motivation line is padding Claude does not need — minor trim potential, not full token efficiency.

4 / 5

Actionability

The Quick Reference gives concrete directives ("Use async for independent scripts (analytics, ads)", "Use defer for DOM-dependent scripts"), but the body contains no executable code, no specific DevTools/Lighthouse procedure in the Check section, and the Code Review section is abstract ("Flag exact files, requests, or rendering steps"), with all executable detail deferred to the reference file.

3 / 5

Workflow Clarity

A rough Check → Fix → Explain sequence exists via section ordering, but checkpoints are implicit: the Check step is vague ("Analyze third-party scripts on this page to ensure they use async/defer") and there is no post-fix re-measure step to confirm the change improved load time.

3 / 5

Progressive Disclosure

A short, well-sectioned body with a clearly signaled, one-level-deep pointer ("For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`"); the reference file exists and carries the code examples, with no nested references.

5 / 5

Total

15

/

20

Passed

Description

70%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 solid trigger-focused description with an explicit Use-when clause and natural performance vocabulary. Its main weakness is that it describes the auditing/verification behavior but omits what the skill actually recommends (async/defer, lazy-loading, facades), and the phrase "related to Optimize third-party script loading" reads as a title pasted into the sentence rather than natural prose.

Suggestions

State the core capabilities explicitly, e.g. "Audits third-party script loading, flags parser-blocking scripts, and applies async/defer, lazy-loading on intent, or facades to eliminate render blocking."

Replace the awkward "related to Optimize third-party script loading" phrasing with a natural capability clause in third person.

Add common synonyms users say, such as "page speed", "third-party JS", or "blocking scripts", to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and 1-2 concrete actions ("auditing slow page loads", "Verify the actual bottleneck in DevTools, Lighthouse, or field data") but never states the remediation capabilities (async/defer, lazy-loading, self-hosting), so coverage gaps exceed the 'minor' bar for a 4.

3 / 5

Completeness

Both parts are present: an explicit "Use when auditing slow page loads, heavy assets, or rendering delays" trigger and a what ("Verify the actual bottleneck ... before recommending changes"), but the what is folded into the trigger clause rather than stated as a crisp capability list, falling short of the 5 anchor.

4 / 5

Trigger Term Quality

Natural user phrases like "slow page loads", "heavy assets", "rendering delays", "DevTools", and "Lighthouse" are present, but common synonyms such as "page speed", "third-party JS", or "blocking scripts" are missing.

4 / 5

Distinctiveness Conflict Risk

"related to Optimize third-party script loading" plus DevTools/Lighthouse carve a clear niche, but "slow page loads" and "heavy assets" are triggers shared with sibling performance skills (image optimization, general page-speed), leaving minor overlap risk.

4 / 5

Total

15

/

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/third-party-scripts/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.