CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

79%

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 ./extensions/unlighthouse/skills/seo-unlighthouse/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A tight, highly actionable routing document packed with non-obvious operational specifics and no padding. Its one real gap is the absence of validation and error-recovery steps for what is a batch operation across up to 200 routes.

Suggestions

Add a post-run verification step, e.g. check that route_count > 0 and that <output_dir>/ci-result.json exists before summarizing aggregate scores.

Add error-recovery guidance for partial audits — e.g. if the 600s subprocess guard trips, rerun with a lower --max-routes or raise --timeout.

Present the workflow as an explicit ordered sequence (install → run → verify output) instead of spreading it across Prerequisites, Routing, and Output handling sections.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it never explains what Lighthouse or CWV is, and every section carries non-obvious specifics (e.g. "the only CLI-documented way to set scanner.maxRoutes; unlighthouse-ci has no --max-routes flag"). The only trim candidate is the doubled "untrusted" phrasing in the Security section, which is too minor to drop below anchor 5.

5 / 5

Actionability

The routing table provides three copy-paste-ready command variants with concrete flags (--device desktop, --max-routes 50 --output-dir ./reports), plus the install command and documented defaults (--page-timeout 60s, --timeout 600s). This fully matches the anchor for executable guidance covering the common cases.

5 / 5

Workflow Clarity

The sequence (Prerequisites → Routing → Output handling) is coherent and the wrapper's url_safety pre-flight is mentioned, but this is a batch operation (up to 200 routes) with no post-run validation or error-recovery loop — no step to verify route_count or handle a missing/partial ci-result.json. Per the rubric's batch-operation cap, which overrides the simple-skill exception, workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

This is a compact single-file skill with well-organized sections and no bundle files; nothing in it belongs in a separate reference file and there are no nested references to get lost in. Per the rubric's guideline for short skills with no need for external references, well-organized sections alone warrant anchor 5.

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 communicates a clear, distinctive capability but reads more like feature marketing than trigger guidance. It lacks an explicit "Use when…" clause and natural trigger synonyms, capping both completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when auditing every page of a site with Lighthouse, when PageSpeed/API quota is insufficient, or for local/CI Core Web Vitals checks."

Include natural synonyms users would actually say — "Core Web Vitals", "site-wide audit", "SEO regression check" — alongside Lighthouse and PageSpeed.

Replace positioning filler ("no API quota burn") with concrete capabilities such as aggregating median per-category scores across routes.

DimensionReasoningScore

Specificity

"Multi-page Lighthouse audit via the MIT-licensed Unlighthouse CLI" names the domain and one concrete action, but the remainder ("Free-tier alternative… no API quota burn, runs locally") is positioning rather than additional capabilities, matching the 1-2-concrete-actions anchor. It is more concrete than the generic anchor 2, but does not list several specific actions needed for 4.

3 / 5

Completeness

The "what" is clear (multi-page Lighthouse audit via Unlighthouse), but there is no "Use when…" clause or equivalent explicit trigger guidance; "Free-tier alternative to running PageSpeed" only weakly implies the when. Per the judging guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes good natural keywords a user would say — "Lighthouse audit", "PageSpeed", "URL", "site" — but misses common variations such as "Core Web Vitals", "SEO", or "site performance". Coverage is stronger than anchor 3's "some relevant keywords" but lacks the synonym/extension breadth of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (local, multi-page Unlighthouse audits) distinct from single-URL PageSpeed skills, with only minor overlap risk since it names PageSpeed directly. It falls short of anchor 5, whose examples carry explicit distinct trigger phrases.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

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.