aeo
Skill2 starsChanged 13 days agoMITView on GitHub
Audit and implement answer-engine discovery using aeo.js, crawler policy, canonical identity, structured data, and machine-readable content. Use for AEO/GEO audits, llms.txt, AI crawler access, or integrating aeo.js into a website.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- viasrijan/crazy-skillstheir own version, first seen Oct 20, 2026
- elmohq/elmotheir own version, first seen Oct 17, 2026
- Asmadey/aeo-geo-skilltheir own version, first seen Sep 5, 2026
- abouchard11/midnight-seo-skillstheir own version, first seen Aug 31, 2026
- andfrancot-alt/claude-skillstheir own version, first seen Aug 17, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- elmohq/elmo★ 577same name
- Hassaan146/claude-skills★ 18same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- seekdigital42/aeo-seo-claude★ 2same name
- abouchard11/midnight-seo-skills★ 1same name
- andfrancot-alt/claude-skills★ 0same name
- Asmadey/aeo-geo-skill★ 0same name
- darkweb19/skills★ 0same name
- KingForm242/claude-aeo★ 0same name
- piiiico/aeo-skill★ 0same name
1 more not listed
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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-worktree-orchestrationSkill
- critical-adversarial-reviewSkill
- evidence-driven-debuggingSkill
- gauntlet-loopSkill
- git-quality-hooksSkill
- multi-agent-collaborationSkill
- quality-gatesSkill
- source-backed-researchSkill
- spec-to-planSkill
- validated-coding-loopSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run the installed CLI's help before relying on options.
- Distinctive: line 16
If package acquisition is needed, follow the project's package manager and dependency policy.
- Distinctive: line 22
Use the framework adapter or CLI that fits the existing build.
- Very specific: line 32
Run the relevant build. Inspect generated files and the site's actual injection path for structured data.
- Distinctive: line 34
Check canonical and localized URLs, robots.txt, sitemap.xml, llms.txt, and other enabled surfaces.
- Distinctive: line 36
When an authorized preview or deployment is available, verify served HTTP responses there and rerun the audit.
“Common” is measured: kept by at least 6 in 10 of the 11 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
AEO with aeo.js
Make the site's intended public content discoverable and attributable, then verify the actual output. Read the aeo.js reference for verified commands and API examples.
Audit before changing
Identify framework, installed aeo.js version, canonical origin, locales, build output, existing robots/sitemap owners, structured data, and intended crawler policy.
Run the installed CLI's help before relying on options. Prefer the project's pinned dependency. For a URL audit, use the documented check/report command or available AEO MCP tools. Save the timestamp and relevant baseline findings.
If package acquisition is needed, follow the project's package manager and dependency policy. Do not execute an unreviewed remote install script.
Inspect both source and served behavior: status, redirect target, content type, canonical URL, indexability, crawler directives, and availability of the relevant metadata or content. Distinguish static inspection from runtime verification.
Implement the smallest useful integration
Use the framework adapter or CLI that fits the existing build. Compose with current configuration rather than replacing it.
Preserve explicit robots restrictions. Search crawling, retrieval, and model training may have different policies; do not broadly enable crawlers to improve a score. If existing tooling owns robots or the sitemap, keep that owner and disable the overlapping generator.
Populate titles, identity, organization, authorship, dates, and relationships from verified project data. Do not invent reviews, credentials, contacts, or schema claims.
Generate only intended public content. Exclude private routes, secrets, signed URLs, and unpublished material from machine-readable exports.
Verify end to end
Run the relevant build. Inspect generated files and the site's actual injection path for structured data. A schema.json file alone does not prove that a page exposes that schema.
Check canonical and localized URLs, robots.txt, sitemap.xml, llms.txt, and other enabled surfaces. Compare the resulting URLs against real routes and check for duplicate or conflicting generators.
When an authorized preview or deployment is available, verify served HTTP responses there and rerun the audit. Deployment itself requires the user's actual authorization.
Report the limit
Report observed defects fixed, commands and revision, before/after evidence, and pending checks. A readiness score is a tool diagnostic; it does not establish search placement, citations in answers, or traffic gains.
llms.txt and related discovery conventions do not replace access control or guarantee that a crawler follows a policy.
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.

