aeo-pack-ai-tools
Skill13 starsChanged 6 months agoMITView on GitHub
Curated prompt pack for AI tool brands tracking their visibility in AI answer engines. 17 prompts covering AI-task discovery, alternatives to incumbents (ChatGPT, Claude, etc.), free-vs-paid framing, accuracy claims, privacy positioning, and vertical use cases. Variables (task, competitor, use_case, domain) fill per workspace. Use when a user is tracking visibility for an AI product, building an AEO baseline for AI-tool category, or asks for prompt ideas for an AI startup.
In this repository22 other files it gives its agents.
- aeo-ai-overview-simulatorSkill
- aeo-analytics-freeSkill
- aeo-baselineSkill
- aeo-cannibalization-detectorSkill
- aeo-citation-gap-finderSkill
- aeo-competitor-monitorSkill
- aeo-content-freeSkill
- aeo-entity-extractorSkill
- aeo-freshness-decay-trackerSkill
- aeo-grounding-query-mapperSkill
- aeo-initSkill
- aeo-multi-prompt-strategySkill
- aeo-optimizeSkill
- aeo-pack-b2b-saasSkill
- aeo-pack-local-servicesSkill
- aeo-prompt-frequency-analyzerSkill
- aeo-prompt-question-finderSkill
- aeo-prompt-research-freeSkill
- aeo-reportSkill
- aeo-schemaSkill
- aeo-source-authority-profilerSkill
- aeo-trackSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 57
If your tool is a Gemini-based product, expect Gemini to be measurably more generous about citing pages that mention Gemini directly.
≈ “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
AEO Pack: AI Tools
Source: github.com/psyduckler/aeo-skills Part of: AEO Skills Suite (v2 prompt packs) Schema: prompt-pack-v1
17 ready-to-track prompts for AI-tool visibility. The AI-tool space has its own retrieval patterns — buyers compare against incumbents (ChatGPT, Claude, Gemini), worry about hallucination, and care about pricing/privacy more than typical B2B SaaS.
Template variables
| Variable | Required | Example |
task | yes | content writing, code generation, image editing, customer support, legal research |
competitor | no | ChatGPT, Claude, Midjourney, GitHub Copilot |
use_case | no | long-form blog posts, unit test generation, legal contract review |
domain | no | legal, medical, finance, education |
How to use this pack
npx skills add psyduckler/aeo-skills --skill aeo-pack-ai-toolsThen fill in variables and merge into your aeo.config.json. Example for a content-writing AI tool competing with ChatGPT:
| Template | Filled |
Best AI tools for {{task}} | Best AI tools for content writing |
{{competitor}} alternatives for {{task}} | ChatGPT alternatives for content writing |
Most accurate AI {{task}} tool | Most accurate AI content writing tool |
AI {{task}} tools that don't hallucinate | AI content writing tools that don't hallucinate |
Why these prompts
AI-tool AEO has unique retrieval characteristics:
- Incumbent comparison is dominant. Almost every category-discovery prompt eventually narrows to "X vs ChatGPT" or "X vs Claude". Tracking these directly is essential.
- Hallucination concerns are a category-defining trust signal. Pages addressing accuracy/reliability get higher citation rates for "most accurate" prompts.
- Pricing transparency matters because AI tools vary widely (free, freemium, pay-per-use, subscription). The "free vs paid" comparison is a high-traffic prompt.
- Vertical positioning ("AI for legal", "AI for medical") gets surfaced when domain-specific accuracy/compliance constraints matter.
- Open-source / privacy alternatives are a distinct retrieval cluster — buyers who care about self-hosting or data sovereignty.
Notes
- If your tool is a Gemini-based product, expect Gemini to be measurably more generous about citing pages that mention Gemini directly. Don't game this — but be aware of the recurring retrieval set bias.
- The "doesn't hallucinate" prompts are noisy — citation rates fluctuate as Gemini's framing of hallucination changes. Sample at N=50 here for tighter signal.
- Pair with aeo-schema using
ProductorSoftwareApplicationJSON-LD to make your pricing/features machine-readable. - Suggested first-baseline scope: 10 prompts × 20 samples = ~$0.06 estimated cost.
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.