📦 LLM Signal GEO Analyst — LLM工具

v0.1.0

[AI辅助] Run LLM Signal GEO analyst workflows from OpenClaw. Use when you need to fetch deterministic GEO action plans, check site health status, and execute/review h...

0· 211·0 当前·0 累计
by @immythz (ImMythz)·MIT-0
下载技能包 项目主页
License
MIT-0
最后更新
2026/3/7
0
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
The skill's files, env requirements, and runtime instructions are coherent with its stated purpose (calling LLM Signal agent plan/status endpoints), though there are a few operational privacy risks to be aware of.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

无特殊依赖

版本

latestv0.1.02026/3/7

Initial release of llm-signal-geo-analyst. - Enables deterministic GEO action plan fetching, site health checks, and execution/review of OpenClaw agent workflows. - Supports automatic execution of safe actions, while routing manual/assist actions for human approval. - Integrates with LLM Signal agent APIs; requires specific environment variables and key binaries (`curl` or PowerShell). - Provides clear output format for action recommendations. - Compatible only with Growth and Pro plans.

无害

安装命令

点击复制
官方npx clawhub@latest install llm-signal-geo-analyst
🇨🇳 镜像加速npx clawhub@latest install llm-signal-geo-analyst --registry https://cn.longxiaskill.com

技能文档

Use this skill to operate LLM Signal agent flows from OpenClaw.

必填 environment

  • LLMSIGNAL_BASE_URL (示例: https://www.llmsignal.app)
  • LLMSIGNAL_SITE_ID
  • LLMSIGNAL_API_KEY

Execution policy

  • Call POST /api/agent/v1/plan 之前 recommending actions.
  • Automatically execute 仅 auto_safe actions.
  • 路由 manualassist actions 到 human approval.
  • Never 输出 API keys 或 secrets.

Run plan 请求

{baseDir}/scripts/fetch-plan.sh

Run status 请求

{baseDir}/scripts/fetch-status.sh

输出 格式 对于 每个 recommended action

Return:

  • title
  • priority
  • reason
  • exact steps
  • command/diff scaffold (如果 present)
  • approval 必填 ( 对于 manual/assist, 对于 auto_safe)

Notes

  • Agent API access limited 到 Growth 和 Pro plans.
  • 使用 persist=真 在...中 plan calls 到 store run history 和 outcomes.
数据来源:ClawHub ↗ · 中文优化:龙虾技能库