debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions "largest contentful paint", "page load speed", "CWV", or wants to improve how fast their hero image or main content renders.

1.75x

Quality

87%

Does it follow best practices?

Impact

86%

1.75x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable, well-sequenced debugging workflow with concrete Chrome DevTools MCP tool calls and a clear verification loop. Its main weakness is progressive disclosure: three reference files are never linked from the body and significant content (breakdown table, optimization strategies) is duplicated inline rather than referenced.

Suggestions

Link all four reference files from the body (e.g. point to references/lcp-breakdown.md and references/optimization-strategies.md) instead of inlining their content, so SKILL.md stays an overview and the bundle files are discoverable.

Remove the duplicated LCP subparts table from SKILL.md or the reference file to avoid maintaining two copies of the same breakdown.

Trim the 'What is LCP and why it matters' intro to just the thresholds and the 73% stat, dropping the definition sentence that restates knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and tool-focused, but the opening 'What is LCP and why it matters' section re-explains a concept Claude already knows, and the LCP subparts table is duplicated from references/lcp-breakdown.md; minor over-explanation keeps it just below a 5.	4 / 5
Actionability	Fully executable guidance: concrete tool calls with parameters (e.g. `performance_start_trace` with `reload: true` and `autoStop: true`), named insights (LCPBreakdown, DocumentLatency), and specific fixes (fetchpriority, preload, font-display) cover the common cases.	5 / 5
Workflow Clarity	Five explicitly ordered steps that build on each other, with a 'Common Pitfall' callout and an explicit verification step ('Re-run the trace... compare the new subpart breakdown. The bottleneck should shrink.'); no destructive/batch cap applies to this read-only debugging workflow.	5 / 5
Progressive Disclosure	Only one of four reference files (lcp-snippets.md) is linked from the body, while elements-and-size.md, lcp-breakdown.md, and optimization-strategies.md are orphaned; additionally the LCP breakdown table and optimization strategies are inlined in SKILL.md while fuller versions sit in unreferenced files, fitting the 'content that should be separate is inline' anchor.	3 / 5
	Total	17 / 20 Passed

Description

90%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, well-structured description that clearly states the skill's purpose and gives rich, natural trigger terms. The only weakness is specificity, which stays at two high-level actions ('debugging', 'optimizing') rather than enumerating several concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('debugging and optimizing Largest Contentful Paint (LCP)') and the tool family ('Chrome DevTools MCP tools') but only lists two high-level actions rather than several concrete operations, matching the '1-2 concrete actions' anchor; not a 4 because coverage is not broad enough.	3 / 5
Completeness	Explicitly answers both what ('Guides debugging and optimizing LCP using Chrome DevTools MCP tools') and when ('Use this skill whenever... Also use when the user mentions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and variations: 'LCP performance', 'slow page loads', 'Core Web Vitals optimization', 'largest contentful paint', 'page load speed', 'CWV', and 'hero image or main content renders'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (LCP-specific performance debugging) with distinct triggers; the LCP/Core Web Vitals framing makes overlap with generic performance skills minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ChromeDevTools/chrome-devtools-mcp
Path: skills/debug-optimize-lcp/SKILL.md
Commit: fce756a

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.