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.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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 well-organized, token-efficient overview that correctly pushes implementation detail to a real one-level-deep reference file. Its weaknesses are in the body's own guidance: no executable command or code snippet inline, and no explicit measurement-verification checkpoint, leaving both actionability and workflow clarity at the mid anchor.

Suggestions

Inline one copy-paste-ready command in the Check section (e.g., `lighthouse https://example.com --chrome-flags="--headless"`) so the body is immediately actionable without opening the reference.

Add an explicit validation step after Fix, such as "Re-run the audit and confirm the targeted metric (LCP/CLS/INP) improves before considering the change done" — the verification content already exists in references/rule.md and should be signaled from the body.

Trim the Quick Reference bullets or merge them with the Check section to remove overlap with the intro and Fix sections.

Dimension	Reasoning	Score
Conciseness	The 44-line body is lean and well-sectioned, with only minor trimmable redundancy: the intro sentence ("Static analysis alone cannot simulate...") and the Quick Reference bullets partially restate the Check/Fix sections. Efficient but not perfectly lean, matching anchor 4 over 5.	4 / 5
Actionability	Concrete tool names (Lighthouse, Puppeteer, WebPageTest) and metrics (LCP, CLS, INP) appear, but the body contains no commands or code — "Integrate browser-based testing tools like Lighthouse or WebPageTest into the development workflow and CI/CD pipeline" is a high-level directive. This matches anchor 3 (some concrete guidance but incomplete); the executable steps exist only in references/rule.md.	3 / 5
Workflow Clarity	Check → Fix → Explain → Code Review forms a recognizable sequence, but the body has no explicit validation checkpoint — the "confirm the targeted metric improves" step lives only in rule.md's Verification section and is not signaled from the body. Anchor 3 (steps listed, checkpoints implicit or missing) fits better than 4.	3 / 5
Progressive Disclosure	A short overview with a clearly signaled one-level-deep reference — references/rule.md (verified to exist, containing the full implementation details, code, and verification steps, with no further nesting) — plus the source page URL. Well-organized sections under 50 lines, matching the top anchor and the simple-skill guidance.	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.

The description has an explicit, natural "Use when…" trigger clause and a concrete verification action, and stays in third person. Its main weakness is that the "what" is underdeveloped: the skill title is crammed into the trigger sentence instead of a clean capability statement, leaving specificity below the top anchors.

Suggestions

Lead with a third-person capability statement (e.g., "Performs browser-based performance audits using Lighthouse, Puppeteer, or WebPageTest to measure LCP, CLS, and INP under real device and network conditions") and keep the title out of the trigger sentence.

Add common trigger synonyms such as "page speed", "Core Web Vitals", or "LCP/CLS/INP" to widen natural keyword coverage.

State both core actions explicitly — running the audit and verifying the bottleneck — so the what-side is comprehensive rather than implied by the title.

Dimension	Reasoning	Score
Specificity	Names the domain (browser-based performance audits) with one concrete action ("Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes"), but "related to Perform browser-based performance audits" embeds the skill title rather than enumerating capabilities. Anchor 3 (domain plus 1-2 concrete actions, not comprehensive) fits; 4 would require several distinct specific actions.	3 / 5
Completeness	Has both an explicit when ("Use when auditing slow page loads, heavy assets, or rendering delays") and an explicit what ("Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes") in third-person imperative voice. Not 5 because the what-side is muddled by the embedded title phrase and never plainly states the core capability of performing the audits.	4 / 5
Trigger Term Quality	"slow page loads", "heavy assets", "rendering delays", "DevTools", "Lighthouse", and "field data" are natural phrases a user would say, giving good keyword coverage. Not 5 because common synonyms like "page speed", "Core Web Vitals", or "LCP" are absent; well above the generic one-or-two-keyword level.	4 / 5
Distinctiveness Conflict Risk	A clear niche (browser-based performance auditing) with named tools (DevTools, Lighthouse, field data) makes it mostly distinct. Minor overlap risk remains with generic performance-optimization or static-analysis skills sharing the same trigger terms.	4 / 5
	Total	15 / 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/browser-required/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.