跳到正文
TakoAPI
返回技能列表

external-ai-integration

由 konscious0beast 提供

Web & Frontend Development
382下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Leverage external AI models (ChatGPT, Claude, Hugging Face, etc.) as tools via browser automation (Chrome Relay)

描述

该技能的功能

Provides patterns for calling external AI models as tools within the assistant's own session. Supports browser-based LLMs (ChatGPT, Claude, Gemini) via Chrome Relay automation and Hugging Face models via direct Inference API calls. Control and context stay in the main session rather than being handed off to a sub-agent.

Calling external models as inline tools preserves the full session context and control flow, avoiding the isolation and coordination overhead of spawning sub-agents.

何时使用

  • Getting a second opinion on a code review from Claude or ChatGPT
  • Translating text using a Hugging Face language model
  • Generating blog title ideas by automating a ChatGPT browser session
  • Running sentiment analysis or summarization via Hugging Face Inference API
  • Identifying blind spots in a strategy analysis by querying an external LLM

示例工作流

输入

User asks: Translate this paragraph from English to German

智能体
  1. 1

    Formats prompt using the T5 input convention: 'Translate English to German: <text>'

  2. 2

    Retrieves HF_TOKEN from environment

  3. 3

    Sends POST request to Hugging Face Inference API with model Helsinki-NLP/opus-mt-en-de

  4. 4

    Parses generated_text field from the JSON response

输出

German translation of the provided paragraph returned to the user

前置要求

  • Hugging Face API token (HF_TOKEN environment variable)
  • Chrome Relay browser extension installed
  • Active logged-in sessions on target LLM websites such as chatgpt.com or claude.ai

安装

clawhub install konscious0beast/external-ai-integration

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接