aeo-answer-optimizer
Skill13 starsChanged 21 days agoMITView on GitHub
Use this skill when you want your brand recommended and cited by AI assistants and answer engines (ChatGPT, Claude, Gemini, Perplexity, AI Overviews): \"answer engine optimisation\", \"get cited by ChatGPT\", \"AEO audit\", \"why doesn't AI recommend us\", \"generative engine optimization\". Finds the questions buyers ask assistants in your category, checks how answers describe you today, and rewrites pages so they give extractable, factual, well-structured answers with clear entities, comparisons, schema and third-party corroboration.
In this repository77 other files it gives its agents.
- AGENTS.mdAGENTS.md
- abm-account-planSkill
- account-research-briefSkill
- account-tieringSkill
- breakup-emailSkill
- buyer-persona-builderSkill
- buying-committee-mapperSkill
- buying-signal-scoringSkill
- call-coaching-scorecardSkill
- campaign-performance-analyzerSkill
- case-study-writerSkill
- churn-win-backSkill
- closed-lost-reactivationSkill
- cold-call-scriptSkill
- cold-email-sequenceSkill
- cold-email-writerSkill
- comparison-page-writerSkill
- competitive-battlecardSkill
- competitor-teardownSkill
- crm-hygiene-auditSkill
- customer-interview-guideSkill
- deal-qualificationSkill
- deliverability-auditSkill
- discovery-call-prepSkill
- domain-warmup-planSkill
- email-authentication-setupSkill
- email-copy-reviewSkill
- event-follow-upSkill
- expansion-opportunity-finderSkill
- first-line-personalizationSkill
- follow-up-email-writerSkill
- funding-signal-outreachSkill
- gtm-global-rulesSkill
- hiring-signal-outreachSkill
- icp-builderSkill
- job-change-playsSkill
- lead-list-builderSkill
- lead-magnet-builderSkill
- lead-scoring-modelSkill
- linkedin-comment-strategySkill
- linkedin-connection-noteSkill
- linkedin-message-sequenceSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- list-cleaningSkill
- lookalike-account-finderSkill
- meeting-booking-replySkill
- messaging-matrixSkill
- multichannel-cadenceSkill
- mutual-action-planSkill
- negotiation-playbookSkill
- no-show-recoverySkill
- objection-handlerSkill
- outbound-ab-testSkill
- outbound-mathSkill
- outreach-compliance-checkSkill
- pipeline-reviewSkill
- post-engagement-outreachSkill
- proposal-follow-upSkill
- prospect-research-briefSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
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
Use this when buyers ask AI assistants which tool to use and your brand is missing or described wrongly.
- Distinctive: line 30
Ask several assistants the top questions.
- Distinctive: line 33
Read references/aeo-checklist.md for the page-level checklist.
- Distinctive: line 36
Use comparison tables with clear criteria.
- Distinctive: line 38
Keep facts fresh and dated where they change.
- Distinctive: line 66
MUST keep every claim accurate and consistent across pages.
- Distinctive: line 67
MUST measure with repeatable question sets over time, not one-off screenshots.
- Distinctive: line 68
NEVER publish fake reviews, fake third-party pages or hidden text aimed at AI crawlers.
- Distinctive: line 69
NEVER make claims about competitors you cannot support.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Use this when buyers ask AI assistants which tool to use and your brand is missing or described wrongly. AI answers favour sources that state facts clearly, answer the question directly and are confirmed by other sources.
Inputs
- The category, product and the facts that define it (who it is for, pricing model, key capabilities, integrations).
- The pages that should be cited: home, product, pricing, comparisons, docs.
- The questions buyers ask (from sales calls, search and support).
The play
1. Map the questions
Group buyer questions by type: "what is", "best tools for", "x vs y", "how to", "how much does", "is x good for <use case>". Prioritise commercial questions where a recommendation is made.
2. Audit current answers
Ask several assistants the top questions. Record whether you are mentioned, what is said, which sources are cited and what is wrong or outdated. Repeat monthly; answers change.
3. Rewrite pages for extraction
Read references/aeo-checklist.md for the page-level checklist. The core:
- Lead each section with a direct, one or two sentence answer, then the detail.
- State facts plainly and consistently across pages: what it is, who it is for, price, limits.
- Use comparison tables with clear criteria; assistants reuse tables well.
- Name entities precisely: product names, categories, integrations, use cases.
- Keep facts fresh and dated where they change.
4. Make it machine-readable
Organization, Product or SoftwareApplication, FAQPage and Article schema; a clean sitemap; fast, crawlable HTML (key text not hidden behind scripts); an llms.txt summary with links to the most important pages; and no blocking of the AI crawlers you want to be cited by.
5. Build corroboration
Assistants trust facts confirmed elsewhere: review sites, directories, partner pages, community answers, credible articles. Make sure third-party descriptions match your own.
Output format
Question map: <question - type - priority - currently mentioned? - cited sources>
Wrong or missing facts: <...>
Page fixes: <page - change - why>
Schema and technical: <...>
Corroboration targets: <sources to update or earn>
Re-check: <date and questions to re-run>What good looks like
- One consistent fact sheet about the product, reused everywhere.
- Comparison and "best for" pages that are honest about fit; assistants pick up balanced sources.
- Progress measured by mentions and citations on the priority questions, checked monthly.
- The common mistake is writing for keywords alone, with answers buried in paragraph four of a long intro.
Rules
- MUST keep every claim accurate and consistent across pages.
- MUST measure with repeatable question sets over time, not one-off screenshots.
- NEVER publish fake reviews, fake third-party pages or hidden text aimed at AI crawlers.
- NEVER make claims about competitors you cannot support.
Example prompts
- "Audit how AI assistants describe us for 'best AI SDR tools' and fix our pages."
- "Rewrite our pricing page so answer engines quote it correctly."
- "Build a monthly AEO tracking sheet for our 20 most important buyer questions."
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.

