seo-unlighthouse

Multi-page Lighthouse audit via the MIT-licensed Unlighthouse CLI. Free-tier alternative to running PageSpeed against every URL on a site, no API quota burn, runs locally.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./extensions/unlighthouse/skills/seo-unlighthouse/SKILL.md

Quality

Content

87%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 content is highly concise and actionable with concrete commands and exact output paths, and it is well-structured for a simple skill. The main gap is the absence of explicit validation/error-recovery checkpoints for a batch operation that audits many routes.

Suggestions

Add an explicit validation checkpoint for the batch audit, e.g., confirm `ci-result.json` exists and reports the expected route count before summarizing scores, and a fix/retry path if the wrapper times out or returns partial results.

Note how to detect and handle partial failures (e.g., routes that failed to audit) so aggregate medians aren't silently skewed.

Specify the failure mode when `url_safety` pre-flight rejects a URL, so the workflow has a clear error-recovery branch.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: no explanation of what Lighthouse or CWV are, just commands, flags, and output field names, with every section earning its tokens.	5 / 5
Actionability	Concrete executable commands are given directly in the routing table (`/seo unlighthouse <url> --device desktop`, `--max-routes 50 --output-dir ./reports`) with exact output field paths and a precise delegation command, covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	The sequence is implied (install -> route command -> read ci-result.json) and it notes subprocess timeout management, but for a batch operation auditing up to 200 routes there are no explicit validation checkpoints or error-recovery feedback loops, which caps this at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	A short, well-organized overview under 50 lines with clear section headers and no bundle files to reference; per the simple-skill guideline, this clear organization earns a 5 without external file references.	5 / 5
	Total	18 / 20 Passed

Description

61%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 is specific and distinctive, positioning the skill clearly against PageSpeed quota limits, but it omits an explicit "Use when..." trigger clause, which caps completeness. Trigger terms are good but could include more natural synonyms.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when you need site-wide Lighthouse scores beyond PageSpeed's 25k QPD quota, or for offline CWV measurement in CI').

Spell out natural synonyms users might say, such as 'Core Web Vitals' alongside 'CWV', to broaden trigger coverage.

List one or two more concrete capabilities (e.g., aggregate median scores across routes, JSON+HTML report output) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Lighthouse audit) and one concrete action ("Multi-page Lighthouse audit") plus how it runs ("via the MIT-licensed Unlighthouse CLI", "runs locally"), but stops at one core action rather than listing multiple specific capabilities.	3 / 5
Completeness	It clearly states what (multi-page Lighthouse audit via Unlighthouse) but provides no explicit "Use when..." clause; the when is only weakly implied through the comparison to PageSpeed quota, so completeness caps at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	It surfaces natural user-facing terms ("Lighthouse audit", "PageSpeed", "CWV", "quota", "locally") that a user needing this would say, though it omits common synonyms like "Core Web Vitals" spelled out and file/url-type phrasings.	4 / 5
Distinctiveness Conflict Risk	The Unlighthouse CLI framing plus the explicit free-tier/no-quota/local positioning carves a clear niche distinct from single-URL PSI skills, with only minor overlap risk against a generic PageSpeed skill.	4 / 5
	Total	14 / 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: AgriciDaniel/claude-seo
Path: extensions/unlighthouse/skills/seo-unlighthouse/SKILL.md
Commit: a1480c7

Reviewed: 15 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.