CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-required

Use when auditing slow page loads, heavy assets, or rendering delays related to Perform browser-based performance audits. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-required/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.

The body is well-organized and correctly defers detail to a real one-level reference, but it is light on executable guidance: it names tools and metrics without commands or code, presents categories instead of a sequenced workflow, and opens with conceptual explanation Claude already knows.

Suggestions

Add at least one concrete, runnable example in the body (e.g. an actual `lighthouse` CLI invocation or a Puppeteer snippet) instead of only naming the tools.

Convert the Check/Fix/Code Review sections into a short sequenced workflow with a validation checkpoint (e.g. run audit -> read LCP/CLS/INP -> confirm the bottleneck -> then recommend), rather than parallel topical categories.

Cut the opening paragraph explaining why static analysis cannot simulate browsers; Claude already knows this, and the Quick Reference already conveys the runtime-metric focus.

DimensionReasoningScore

Conciseness

The opening sentence "Static analysis alone cannot simulate the complex rendering, script execution, and layout processes of modern web browsers..." explains a concept Claude already knows, and the "Explain" section repeats that rationale, so it is mostly efficient but carries unnecessary explanation that could be trimmed.

2 / 3

Actionability

It names concrete tools and metrics (Lighthouse, Puppeteer, WebPageTest, LCP/CLS/INP) but provides no executable commands or code, and the Fix guidance "Integrate browser-based testing tools... into the development workflow and CI/CD pipeline" is vague direction that defers real examples to the reference file.

2 / 3

Workflow Clarity

The Check/Fix/Explain/Code Review sections are topical categories rather than a sequenced workflow, and there are no explicit validation checkpoints; the Code Review section hints at a measurement method but no validate-then-fix loop is laid out.

2 / 3

Progressive Disclosure

The body is a concise overview that signals a single one-level-deep reference — "see references/rule.md" for full implementation details and code examples — and that file exists, matching the "clear overview with well-signaled one-level-deep references" anchor.

3 / 3

Total

9

/

12

Passed

Description

90%

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 has strong trigger terms, a clear niche, and an explicit "Use when" clause answering both what and when. Its main weakness is that the stated actions are abstract verbs rather than concrete operations, and the phrase "related to Perform browser-based performance audits" reads as a garbled title inserted mid-sentence.

Suggestions

Rewrite the broken clause so the skill's purpose reads as a clean action statement instead of "rendering delays related to Perform browser-based performance audits", which jams the H1 title into the sentence.

Replace abstract verbs ("auditing", "verifying", "recommending") with concrete operations, e.g. "Run Lighthouse/Puppeteer audits, capture LCP/CLS/INP, and pinpoint the bottleneck in DevTools or field data before recommending fixes."

DimensionReasoningScore

Specificity

The description names the domain and some actions — "auditing slow page loads, heavy assets, or rendering delays", "Verify the actual bottleneck", "before recommending changes" — but these are abstract verbs rather than multiple concrete operations like the PDF anchor ("Extract text and tables, fill forms, merge"), so it stops at "names domain and some actions, not comprehensive."

2 / 3

Completeness

It explicitly answers both: the "what" ("Perform browser-based performance audits", "Verify the actual bottleneck") and the "when" via an explicit "Use when auditing slow page loads..." trigger clause, satisfying the rubric's requirement for an explicit trigger.

3 / 3

Trigger Term Quality

It includes natural terms a user would actually say — "slow page loads", "heavy assets", "rendering delays" — plus concrete tool names "DevTools, Lighthouse, or field data", giving good coverage rather than just technical jargon.

3 / 3

Distinctiveness Conflict Risk

It targets a clear niche — browser-based performance auditing with named tools (DevTools, Lighthouse) and specific triggers (slow page loads, rendering delays) — making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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.