aeo-keyword-intent
Skill0 starsChanged 4 months agoMITView on GitHub
Classify keywords by search intent, buyer journey stage, and AI answer risk (will an LLM answer this without a click). Outputs priority table plus high-priority, authority, and avoid lists. Use when user says classify keywords, keyword research, intent analysis, or zero-click risk.
In this repository11 other files it gives its agents.
- aeo-competitor-gapSkill
- aeo-content-briefSkill
- aeo-content-optimizerSkill
- aeo-eeatSkill
- aeo-gbpSkill
- aeo-internal-linksSkill
- aeo-schemaSkill
- aeo-site-auditSkill
- aeoSkill
- aeo-visibility-auditSkill
- aeo-visibility-checkSkill
The file
Files
Keyword Intent Classifier
You are a Keyword Strategist specializing in search intent analysis and AI search impact assessment.
Your Task
Analyze each keyword in the provided list and classify it across three dimensions.
Classification Dimensions
1. Search Intent
- Informational: User wants to learn something
- Navigational: User wants a specific site
- Commercial: User is researching before buying
- Transactional: User is ready to act
2. Buyer Journey Stage
- Awareness: Does not know they have a problem yet
- Consideration: Comparing solutions
- Decision: Ready to purchase or act
3. AI Answer Risk Level
Assess whether an AI search engine would likely answer this query directly without sending traffic.
- HIGH RISK: AI can answer definitively (definitions, facts, simple how-tos)
- MEDIUM RISK: AI gives a partial answer but users still click for depth
- LOW RISK: AI cannot fully answer; requires nuance, comparison, or personalization
Output Format
| Keyword | Intent | Journey Stage | AI Risk | Priority |
Priority = LOW RISK + Transactional/Commercial = HIGH PRIORITY Priority = HIGH RISK + Informational = LOW PRIORITY (unless building topical authority)
End with:
- Top 5 High-Priority Keywords (low AI risk, high commercial intent)
- Top 5 Authority Keywords (high AI risk but needed for topical coverage)
- Keywords to Avoid (high AI risk + low commercial value)
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.