Skill reviews
Independent assessments of AI agent skills. No sponsored content, no affiliate links — and every review says up front whether we ran the skill or only read it.
seo Review: Lighthouse First, and No Ranking Promises
We ran Addy Osmani's seo skill on our homepage and a skill page. It used Lighthouse as evidence, treated title length as a guide rather than a rule, and wrote fixes against our source. Its schema reference still shows an FAQ example with no warning.
build-links Review: A Sound Link Plan, Scored With Data You May Not Have
We asked the build-links skill to design a link building campaign for our site with no paid SEO data. Its diagnosis and strategy worked from free searches. Its link-scoring formula needed data we couldn't get for three of its six factors.
seo-page Review: A Current Checklist That Needs Its Suite
We installed the single-page module of claude-seo on its own and ran it on our homepage. Its checklist is current and found real issues, but its first scripted check fails outside the suite and its score card has no formula.
claude-seo Review: We Ran Two Full Audits on Our Own Site
We ran claude-seo v2.4.0 twice against trustedskills.dev, once with a headless browser and once without. It found every real bug we know about. It also gave two different health scores on the same day, and one run put a made-up star rating into copy-paste schema.
Curated collections
How we review
Hands-on, or labelled
A hands-on review means the skill was installed and pointed at real work, and the page lists the task and what happened. Where we've only read the source, the review says so at the top and carries no measured results.
Five scored dimensions
Installation ease, documentation quality, feature depth, maintenance track record and platform support — each out of 5. The overall score is their mean, not a separate judgement.
No invented results
We never publish a benchmark we didn't run, a screenshot we didn't take, or a testimonial we didn't receive. If we can't verify something, we write down that we can't.