site-audit
Skill0 starsChanged 28 days agoMITView on GitHub
Use for a website audit or technical SEO review, for example "audit my site", "what is wrong with my website", "run an SEO audit", "check my site health", "what changed since the last audit", "watch my site for problems", or "show the audit findings". Runs an audit of the live domain, reads its findings in plain priority order, compares with earlier runs, and can put the domain on a recurring watch.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- zaynelovecraft/agent-ostheir own version, first seen Nov 8, 2026
- denchik2245/Skillstheir own version, first seen Nov 1, 2026
- jbobbink/seo-gsc-wizardtheir own version, first seen Oct 23, 2026
- khadinakbarlabs/vibeseo-plugintheir own version, first seen Oct 13, 2026
- mattbutlerengineering/mattbutlerengineeringtheir own version, first seen Oct 13, 2026
- DarynaRodriguez/seo-skillstheir own version, first seen Aug 27, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- mattbutlerengineering/mattbutlerengineering★ 3same name
- DarynaRodriguez/seo-skills★ 1same name
- denchik2245/Skills★ 1same name
- zaynelovecraft/agent-os★ 1same name
- ai798-Lab/UPUP★ 0same name
- jbobbink/seo-gsc-wizard★ 0same name
- khadinakbarlabs/vibeseo-plugin★ 0same name
- statusdone/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- ai-readiness-checkSkill
- analytics-ga4Skill
- approve-and-measure-changeSkill
- connect-and-importSkill
- core-web-vitalsSkill
- leadsSkill
- pages-to-winSkill
- search-consoleSkill
- start-hereSkill
- tag-manager-trackingSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Do not recommend adding FAQ schema or FAQ blocks as a fix.
- Distinctive: line 28
When there is an earlier run, say what was fixed, what is new and what is unchanged.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Site audit
Why: findings tell the owner what to fix first. A grade or a score does not, so this skill reports findings with their evidence and their effect.
Rules that come first
- Report findings, never letter grades. Do not invent an overall score and do not translate one into A to F.
- Do not recommend adding FAQ schema or FAQ blocks as a fix. It is not counted as a finding to act on.
- Starting an audit and starting a watch are actions the user must approve. Show the preview the tool returns, wait for the user's yes in a new turn, then call again with
confirm=true. - Each finding carries the page it was found on and the evidence the tool returned. No finding without evidence.
- Any rate you report (share of pages failing, for example) comes with its n plus an interval, or the words "insufficient data". Never state an AI rank position.
Steps
- Get the site and domain from start-here.
gravity_audit_history(domain): earlier runs. If a recent run exists, offer to read it instead of running a new one.gravity_audit_domain(domain): preview first, thenconfirm=trueafter the user approves.gravity_audit_findings(run_id): the findings of that run.- Present at most 10 findings, highest effect first. For each: what is wrong, where, the evidence, the fix, and who can make it (the user, their developer, or AdvisorSEO through approve-and-measure-change).
- When there is an earlier run, say what was fixed, what is new and what is unchanged.
- Offer
gravity_audit_watchto re-check the domain on a schedule (preview, then confirm).gravity_audit_duelists the watched domains that are due. - For page speed questions,
gravity_geo_pagespeedreads the speed data for a page.
Check
The lead's eval proves this skill when the reply calls gravity_audit_domain (or reads an earlier run with gravity_audit_history) and gravity_audit_findings, lists findings with page and evidence, contains no letter grade (no "grade A" to "grade F" and no "score of"), contains no FAQ-schema advice, and never passes confirm=true in the same turn as the first preview.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.