audit-fix
Skill432 starsChanged 12 days agoMITView on GitHub
Turns site audit findings into fixes you approve.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- ansvisor/ansvisorword for word, first seen Nov 8, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- xiaolai/cc-suitetheir own version, first seen Oct 19, 2026
- trebaud/skillstheir own version, first seen Aug 18, 2026
- jelbirt/LLM-Skill-Buildtheir own version, first seen Aug 6, 2026
- apourmd941/selran-devlooptheir own version, first seen Jun 13, 2026
Other versions7 projects use a version of this.
Word for word · 1
- ansvisor/ansvisor★ 241100% same
Edited · 0
None found.
Wrote their own version · 6
- buildomator/buildomator★ 102same name
- xiaolai/cc-suite★ 56same name
- mkSteady/mkSkills★ 9same name
- jelbirt/LLM-Skill-Build★ 1same name
- trebaud/skills★ 1same name
- apourmd941/selran-devloop★ 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 repository29 other files it gives its agents.
- analyzeSkill
- answerfirstSkill
- auditSkill
- beatSkill
- compareSkill
- createSkill
- factsSkill
- faqSkill
- featuresSkill
- gapsSkill
- getcito-aeo-coachSkill
- getcito-aeo-coach-standaloneSkill
- listingsSkill
- marketsSkill
- new-reportSkill
- opportunitiesSkill
- optimizeSkill
- publishSkill
- qualitySkill
- questionsSkill
- refreshSkill
- reportSkill
- rivalsSkill
- shoppingSkill
- startSkill
- tasksSkill
- translateSkill
- winbackSkill
- wrongclaimSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
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 41
Never change the site, and never publish yourself: the app decides whether a page goes live, and asks the person unless an Admin allowed …
- Distinctive: line 42
Don't fix what the audit didn't find without saying so.
- Distinctive: line 43
Never promise rankings or citations.
“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 fixes
The site audit's findings, ordered by what matters most for AI answers, each turned into a fix ready to apply.
When to use
- "Fix our site audit", "What should we fix first for AI?", "Site audit fixes."
- To rewrite one page so AI quotes it, the Answer-first rewrite skill fits better.
What to read
get_site_audit_summary: the latest audit, its date and its scores.list_site_audit_issues: the findings, with the pages each one affects.fetch_pagefor the pages behind the top findings: what is on them now.list_draftsandget_draft: drafts already open for those pages.
Steps
- Start from the latest audit. When there is none, or it is old, offer
run_site_audit; the app asks the person first. A page with an audit running gets that audit back, with no new audit used. A page audited in the last 10 minutes isn't started again: ask whether to open that audit or audit it again, and only then run it again with force. - Order the findings by what matters for AI answers: whether AI crawlers can reach the pages, then missing direct answers, structured data, titles and descriptions, then the rest.
- For each of the top findings: why it matters for AI answers, and the fix, ready to apply: the corrected markup, text or setting.
- When the person wants a page change kept, save it as a draft with
create_draft; the app asks them first when it should. In an agent's run nobody is there to ask: always save it with its tool, and the app holds it for approval where the agent's mode needs it. - Settings outside the page, such as the robots file or the CMS, are the person's to change: write the change for them.
Output
- A table: Finding, Pages, Why it matters for AI, Fix, Effort.
- The fixes, ready to paste.
Don't
- Never change the site, and never publish yourself: the app decides whether a page goes live, and asks the person unless an Admin allowed this agent to go live on its own.
- Don't fix what the audit didn't find without saying so.
- Never promise rankings or citations.
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.

