external-ai-integration
от konscious0beast
Web & Frontend DevelopmentКратко
Leverage external AI models (ChatGPT, Claude, Hugging Face, etc.) as tools via browser automation (Chrome Relay)
Описание
Что делает этот навык
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.
Когда его использовать
- 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
Пример сценария
User asks: Translate this paragraph from English to German
- 1
Formats prompt using the T5 input convention: 'Translate English to German: <text>'
- 2
Retrieves HF_TOKEN from environment
- 3
Sends POST request to Hugging Face Inference API with model Helsinki-NLP/opus-mt-en-de
- 4
Parses generated_text field from the JSON response
German translation of the provided paragraph returned to the user
Требования
- 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
Установка
clawhub install konscious0beast/external-ai-integrationВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.