Intent mining
npx -y skills add excelle/seo-geo-toolkit --skill intent-miningAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Map searcher intent, volume signals, and topic clusters for SEO and GEO strategies. 搜索意图分析/意图挖掘
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.8 KB, as published. Nobody here has run it
Intent Mining
Maps searcher intent behind queries, surfaces volume signals, and organizes keywords into actionable topic clusters. This is the starting point for any SEO or GEO campaign.
Quick Start
Mine intent for [topic] targeting [audience]
Find keyword clusters for [product/service] in [market]
What are the informational vs commercial intents for [keyword]?
Engine Contract
- Reads: user goals, audience definition, available tool data, prior strategy from hot cache
- Writes: a user-facing research brief plus a reusable summary for
memory/research/ - Promotes: durable keyword priorities, competitor facts, entity candidates to hot cache and decisions log
- Next handoff: emit a signal packet with objective, findings, evidence, open loops, keyword, and content type
Instructions
Run these six phases (announce each as [Phase X/6: Name]):
- Scope — clarify product, audience, geography, language, and business goal
- Harvest — collect seed keywords from core terms, problem statements, solution language, and audience vocabulary
- Expand — generate variations using modifiers (how to, best, vs, tools, templates, examples, year), question prefixes, and comparison patterns
- Classify — tag each keyword by intent: Informational (learn/know), Commercial (compare/buy), Transactional (purchase/signup), Navigational (brand/site)
- Prioritize — score each opportunity with
Priority = (Estimated Volume × Intent Value) / Difficulty, where Intent Value = 1/2/3/1 respectively - Cluster — group related keywords into pillar topics and supporting cluster content; identify potential GEO questions (what is, how to, vs, best, why does)
Quality bar — every recommendation must have at least one specific metric or concrete qualifier. Generic advice must be rewritten with numbers or named examples.
Example
User: "Mine intent for a time-tracking app for freelancers"
Output (abbreviated):
- 120+ keywords mapped across 4 intent types
- 3 pillar topics: Freelancer productivity, Client billing workflows, Time management methods
- 18 high-priority opportunities with ~38K/month estimated volume
- GEO questions identified: "What is the best time tracker for freelancers?", "How to bill clients by the hour"
Deliverables
- Executive summary
- Quick wins (low difficulty, decent volume)
- Growth keywords (medium difficulty, high intent value)
- GEO question targets
- Topic cluster map
- Suggested content calendar
Next Best Engine
- Primary: landscape-scan — understand who already ranks
- Alternatives: white-space-finder, query-mapping