perf-lighthouse

Run Lighthouse audits locally via CLI or Node API, parse and interpret reports, and set performance budgets. Use when measuring site performance, understanding Lighthouse scores, setting up budgets, or integrating audits into CI. Triggers on: lighthouse, run lighthouse, lighthouse score, performance audit, performance budget. Do NOT use for fixing specific performance issues (use perf-web-optimization or core-web-vitals) or Astro-specific optimization (use perf-astro).

Quality

89%

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

Quality

Content

78%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 dense, highly actionable reference of executable Lighthouse patterns, but it is a monolithic single-file dump with no progressive disclosure to separate reference files, and workflows lack explicit failure-feedback loops.

Suggestions

Move the larger blocks (GitHub Actions workflow, full LHCI config, comparison scripts) into files under references/ and link to them from SKILL.md to reduce inline bulk and improve progressive disclosure.

Add an explicit feedback loop after LHCI assertions — e.g., "if an assertion errors, inspect the failing audit, fix the regression, and re-run `lhci autorun`" — to strengthen workflow clarity for CI use.

Trim the Compare Builds section (the custom comparison script is somewhat extraneous given the LHCI assert block already covers metric thresholds) to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly lean code blocks with terse comments and no concept explanations, but the Compare Builds section and some repetition between the budget.json and LHCI assertion metrics could be trimmed for full token efficiency.	4 / 5
Actionability	Fully executable throughout — copy-paste CLI commands, Node API code, GitHub Actions YAML, LHCI config, JSON parsing, and a comparison script, plus a troubleshooting table with specific flags/env vars covering the common cases.	5 / 5
Workflow Clarity	The CI sections (GitHub Actions, LHCI) show a clear build→audit→assert sequence and LHCI assertions act as validation checkpoints, but there is no explicit feedback loop describing what to do when assertions fail.	4 / 5
Progressive Disclosure	No bundle files exist and all ~234 lines are inlined; substantial blocks (full GitHub Actions workflow, LHCI config, budget JSON, comparison scripts) that could live in separate reference files are monolithically embedded, though section headers are clear.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, explicit trigger phrases, and clear negative boundary guidance that distinguishes it from sibling perf skills. No vague language or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Run Lighthouse audits locally via CLI or Node API, parse and interpret reports, and set performance budgets" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (run/parse/interpret audits, set budgets) and when ("Use when measuring site performance... Triggers on:...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Triggers on: lighthouse, run lighthouse, lighthouse score, performance audit, performance budget" plus natural phrases like "measuring site performance" and "setting up budgets" gives comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative boundary guidance — "Do NOT use for fixing specific performance issues (use perf-web-optimization or core-web-vitals) or Astro-specific optimization (use perf-astro)" — minimizing conflict risk.	5 / 5
	Total	20 / 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(performance)/perf-lighthouse/SKILL.md
Commit: fe318be

Reviewed: 3 days 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.