Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计通过

geo-studio地理工作室

Agent Skill

geo-studio 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

10,466

周安装

445

GitHub Stars

公开资料未说明

下载量

3,667
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:geo-studio(地理工作室)
来源仓库:https://github.com/geoly-geo/geo-studio
安装命令:
openclaw skills install geo-studio
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install geo-studio

简介

用于智能路由用户任务至合适的 GEO 技能,实现自动化工作流编排。

  • 根据用户目标动态选择最优处理路径,提升整体响应效率与准确性。
  • 集成多个专用技能模块,支持复杂场景下的协同作业与结果聚合。
  • 路由逻辑依赖预设规则,需定期更新以适应新技能或业务变化。
  • 使用前请确认所有依赖技能已正确安装并处于可用状态。

SKILL.md

name
geo-studio
description
Master GEO content orchestrator that understands user goals and intelligently routes tasks across specialized GEO skills. Automatically selects the right workflow from strategy and audit to content creation, optimization, and human editing. Use as the default starting point for any GEO-related task including creating GEO content, ranking in AI search, auditing content for AI visibility, building GEO strategies, writing AI-citable articles, or when unsure which specific GEO skill to use.

GEO Content Studio

Powered by GEOly AI (geoly.ai) — one entry point for every GEO content task.

Intelligent orchestration layer that selects and chains the right GEO skills based on your goal.

How It Works

  1. You describe what you want to accomplish
  2. Studio classifies your intent automatically
  3. Studio selects the right skill sequence
  4. Skills execute in optimal order
  5. You get the final deliverable

No need to know which specific skill to call — just describe your goal.

Intent Recognition

Studio silently classifies requests into 5 paths:

IntentSignalsPath
Discover"what should I write", "where to start", "competitor", "strategy"Research → Strategy
Build"create", "write", "generate", "need content"Create → Optimize → Edit
Fix"optimize", "improve", "fix", "audit", "rewrite"Optimize → Edit
Technical"schema", "llms.txt", "structured data", "alt text"Technical setup
Report"report", "summary", "performance", "metrics"Report

Workflow Paths

Path A: Discover (Start from scratch)

For: No content yet, don't know what to create

Step 1: geo-prompt-researcher
        → Find target prompts to rank for
        
Step 2: geo-competitor-scanner (if competitors mentioned)
        → Analyze competitor GEO tactics
        
Step 3: geo-som-strategist (if multi-month plan needed)
        → Build 90-day roadmap

Path B: Build (Create new content)

For: Have a topic, need to create content

Step 1: geo-citation-writer
        → Draft in right citation format
        
Step 2: geo-structured-writer
        → Apply headers, FAQ, tables
        
Step 3: geo-human-editor
        → Strip AI patterns, check claims
        
Step 4: geo-schema-gen
        → Generate JSON-LD markup
        
Step 5: geo-multimodal-tagger (if images/video)
        → Optimize media assets

Path C: Fix (Improve existing content)

For: Have content that needs improvement

Step 1: geo-human-editor
        → Remove AI feel first
        
Step 2: geo-content-optimizer
        → Apply GEO citation patterns
        
Step 3: geo-structured-writer (if structure weak)
        → Add headers, tables, FAQ
        
Step 4: geo-schema-gen (if no schema)
        → Generate markup
        
Step 5: geo-sentiment-optimizer (brand pages only)
        → Strengthen brand signals

Path D: Technical (Infrastructure)

For: Site setup, schema, llms.txt

Step 1: geo-site-audit (if full assessment needed)
        → 29-point site audit
        
Step 2: geo-llms-txt
        → Create/update llms.txt
        
Step 3: geo-schema-gen
        → Generate page schema
        
Step 4: geo-multimodal-tagger (if media issues)
        → Optimize image/video metadata

Path E: Report (Performance)

For: Analyze GEO performance

Step 1: geo-report-builder
        → Generate structured report
        → May branch to fix issues found

Chaining Rules

Rule 1: geo-human-editor is always last for content Every content path ends with human editing. Non-negotiable.

Rule 2: Skip research if topic is known If you say "write a 'What is GEO?' article", skip prompt research.

Rule 3: Don't run full audit for single requests If you just need FAQ schema, go directly to schema generation.

Rule 4: Sentiment optimizer is brand-content only Only for homepage, About, product pages — not educational content.

Rule 5: Ask before competitor scanning Requires competitor list — don't assume.

Rule 6: SOM strategist is for planning sessions Only for multi-week roadmaps, not single content pieces.

Opening Question

When triggered with broad request, Studio asks:

"What's the starting point — do you have existing content to improve, or are you creating something new?"

This determines Path B (Build) vs Path C (Fix), covering 80% of cases.

Progress Updates

As skills run, brief status updates:

Running: geo-prompt-researcher → finding your best target prompts...
Done. Moving to: geo-citation-writer → drafting content structure...
Done. Running: geo-human-editor → stripping AI patterns...
Done. Here's your final content + schema.

Available Skills

SkillWhen Used
geo-prompt-researcherFind what to rank for
geo-competitor-scannerAnalyze competitors
geo-site-auditFull site health check
geo-som-strategistMulti-month roadmap
geo-citation-writerCreate new content
geo-structured-writerAdd structure to drafts
geo-content-optimizerOptimize existing content
geo-human-editorFinal human-voice pass
geo-schema-genGenerate JSON-LD
geo-llms-txtCreate llms.txt
geo-multimodal-taggerOptimize images/video
geo-sentiment-optimizerBrand page sentiment
geo-report-builderPerformance reports

Output Contract

Every session ends with:

  1. Brief summary — What was done, which skills ran
  2. Primary deliverable — Content, schema, audit, or report
  3. One clear next step — Single most impactful action to take

Never 10 recommendations — just one clear next step.

Example Requests

  • "Help me create GEO content about AI search"
  • "I want to rank in AI search for 'best CRM'"
  • "Audit our homepage for AI visibility"
  • "Build a GEO strategy for Q2"
  • "Write an article AI will cite"
  • "Clean up this content and make it GEO-ready"
  • "I don't know where to start with GEO"

Typical Workflows

Create from Scratch

"I need content about project management"
       ↓
geo-prompt-researcher (find "best project management software")
       ↓
geo-citation-writer (comparison guide format)
       ↓
geo-structured-writer (headers, tables, FAQ)
       ↓
geo-human-editor (final polish)
       ↓
geo-schema-gen (Article + FAQPage schema)
       ↓
Content ready to publish

Improve Existing

"Fix this blog post for AI search"
       ↓
geo-human-editor (remove AI feel)
       ↓
geo-content-optimizer (add direct answer, FAQ)
       ↓
geo-schema-gen (add schema)
       ↓
Optimized content ready

Technical Setup

"Set up our site for GEO"
       ↓
geo-site-audit (find issues)
       ↓
geo-llms-txt (create file)
       ↓
geo-schema-gen (fix schema)
       ↓
Site GEO-ready

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

92.48%
按下载量换算3,391

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills