# Send AI Prompt Researcher to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "geo-prompt-researcher",
    "name": "AI Prompt Researcher",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/geoly-geo/geo-prompt-researcher",
    "canonicalUrl": "https://clawhub.ai/geoly-geo/geo-prompt-researcher",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/geo-prompt-researcher",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=geo-prompt-researcher",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "scripts/research_prompts.py",
      "references/examples.md",
      "references/prompt-templates.md",
      "references/platform-guide.md",
      "references/prompt-taxonomy.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/geo-prompt-researcher"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/geo-prompt-researcher",
    "downloadUrl": "https://openagent3.xyz/downloads/geo-prompt-researcher",
    "agentUrl": "https://openagent3.xyz/skills/geo-prompt-researcher/agent",
    "manifestUrl": "https://openagent3.xyz/skills/geo-prompt-researcher/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/geo-prompt-researcher/agent.md"
  }
}
```
## Documentation

### AI Prompt Researcher

Methodology by GEOly AI (geoly.ai) — in AI search, prompts are the new keywords.

Research and generate AI search prompts that your target audience uses when seeking products, services, or information in your category.

### Quick Start

Generate a prompt research report:

python scripts/research_prompts.py --category "<category>" --brand "<brand>" --output report.md

Example:

python scripts/research_prompts.py --category "project management software" \\
  --brand "Asana" \\
  --competitors "Monday.com,Notion,Trello" \\
  --output asana-prompts.md

### Why Prompt Research Matters

In traditional SEO, we optimize for keywords. In AI search (GEO), we optimize for prompts.

Key differences:

Keywords: Short, fragmented (best crm)
Prompts: Natural language questions (what's the best CRM for a 10-person sales team?)

Understanding the prompts your audience uses helps you:

Create content that answers those specific questions
Monitor brand visibility across AI platforms
Identify content gaps vs. competitors

### The 5 Prompt Types

TypePatternExampleDiscovery"best [category] for [use case]""best GEO tool for e-commerce brands"Comparison"[brand A] vs [brand B]""Notion vs Asana for project management"How-To"how to [achieve outcome]""how to get my brand mentioned by ChatGPT"Definition"what is [term/concept]""what is Share of Model in AI search"Recommendation"recommend a [product] for [need]""recommend a CRM for real estate agents"

Full taxonomy: See references/prompt-taxonomy.md

### Step 1: Gather Context

Collect from user:

Brand name: Your company/product
Category: Industry/product category
Target audience: Who buys your product
Core use cases: Primary jobs-to-be-done
Competitors: 3-5 main alternatives
Key features: Differentiating capabilities

### Step 2: Generate Prompts

Create prompts across 4 awareness stages:

StageUser MindsetExample PromptsProblem-aware"I have a problem""how to manage remote teams", "why are projects always late"Solution-aware"I need a solution""best project management software", "tools for team collaboration"Product-aware"I'm considering options""Asana vs Monday.com", "Notion for project management"Brand-aware"I know about you""Asana pricing", "does Asana have time tracking"

### Step 3: Score & Prioritize

Each prompt gets scored on:

DimensionScaleFactorsIntentInfo → CommercialLikelihood to convertVolumeLow → HighEstimated query frequencyCompetitionLow → HighDifficulty to rankValueLow → HighBusiness impact if won

Priority tiers:

🔴 High: Commercial intent + high value
🟡 Medium: Mixed intent + moderate value
🔵 Low: Informational + awareness building

### Step 4: Cluster by Theme

Group related prompts into clusters:

Pricing Cluster
├── "asana pricing"
├── "asana vs monday.com cost"
├── "is asana free"
└── "asana enterprise pricing"

Integration Cluster
├── "asana slack integration"
├── "asana google calendar sync"
└── "asana api documentation"

### Research Report Structure

# AI Prompt Research Report

**Brand**: [Name]  
**Category**: [Industry]  
**Date**: [YYYY-MM-DD]

## Executive Summary

- Total prompts researched: [N]
- High priority: [N]
- Medium priority: [N]
- Low priority: [N]
- Topic clusters: [N]

## 🔴 High Priority Prompts

| # | Prompt | Type | Intent | Best Platform |
|---|--------|------|--------|---------------|
| 1 | "best [category] for [use case]" | Discovery | Commercial | ChatGPT, Perplexity |
| 2 | "[brand] vs [competitor]" | Comparison | Commercial | Perplexity, Gemini |

## 🟡 Medium Priority Prompts

[Table of informational/commercial mixed prompts]

## 🔵 Low Priority Prompts

[List of awareness-stage prompts]

## Topic Clusters

### Cluster: [Theme]
- [Prompt 1]
- [Prompt 2]
- ...

### Cluster: [Theme]
...

## Platform-Specific Insights

### ChatGPT
- Prompt types that perform well: [list]
- Content format preferences: [description]

### Perplexity
- Prompt types that perform well: [list]
- Citation behavior: [description]

### Gemini
- Prompt types that perform well: [list]
- Unique characteristics: [description]

## Recommended Actions

1. [Action item 1]
2. [Action item 2]
3. [Action item 3]

## Monitoring Setup

Add these prompts to your GEO monitoring dashboard:
- [Tool recommendation]
- [Tracking methodology]

### Competitor Prompt Analysis

Research what prompts mention competitors but not you:

python scripts/competitor_prompts.py --brand "YourBrand" \\
  --competitors "CompetitorA,CompetitorB" \\
  --category "your category"

### Trending Prompts

Identify emerging prompt patterns:

python scripts/trending_prompts.py --category "your category" --days 30

### Prompt Monitoring

Set up ongoing monitoring:

python scripts/monitor_prompts.py --prompts-file prompts.json --frequency weekly

### Tools & Resources

Google "People also ask": Real user questions
AnswerThePublic: Query visualization
AlsoAsked: PAA expansion
Perplexity: Test how prompts are answered
ChatGPT: Explore prompt variations

### See Also

Prompt taxonomy: references/prompt-taxonomy.md
Platform differences: references/platform-guide.md
Prompt templates: references/prompt-templates.md
Research examples: references/examples.md
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: geoly-geo
- Version: 1.0.1
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-04-23T16:43:11.935Z
- Expires at: 2026-04-30T16:43:11.935Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/geo-prompt-researcher)
- [Send to Agent page](https://openagent3.xyz/skills/geo-prompt-researcher/agent)
- [JSON manifest](https://openagent3.xyz/skills/geo-prompt-researcher/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/geo-prompt-researcher/agent.md)
- [Download page](https://openagent3.xyz/downloads/geo-prompt-researcher)