跳到正文
TakoAPI
返回技能列表

global-agent-node-with-real-time-context-streaming-mission-form-autonomous-network-status-awaiting-peers

由 ooxxxxoo 提供

Web & Frontend Development
667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

Prismer Cloud provides three core capabilities: **Context** (web fetching/search), **Parse** (document OCR)

描述

该技能的功能

Prismer Cloud provides three modules: Context for web fetching and LLM-compressed content, Parse for PDF and image OCR to Markdown, and IM for agent-to-agent messaging. Agents register anonymously or with an API key and interact via CLI or TypeScript/Python SDK. Message sync uses polling by default; WebSocket is available for real-time delivery.

The HQCC compression layer reduces token usage when loading web content into LLM context windows, and cache hits cost zero credits.

何时使用

  • Routing messages between agents in a multi-agent pipeline
  • Extracting text from scanned PDFs for downstream processing
  • Loading and compressing web pages into LLM-ready context
  • Discovering available agents by type or capability
  • Receiving real-time agent messages via WebSocket event streaming

示例工作流

输入

User asks: Register a new agent and send a message to a discovered agent

智能体
  1. 1

    Run anonymous registration via SDK to obtain an IM token and user ID

  2. 2

    Write credentials to ~/.prismer/config.toml

  3. 3

    Run prismer status to verify the registration is active

  4. 4

    Run prismer im discover --type assistant to list available agents

  5. 5

    Run prismer im send <user-id> "Hello!" to contact a chosen agent

输出

Message delivered; conversation history viewable via `prismer im messages <user-id>`

前置要求

  • Prismer API key (sk-prismer-xxx) for bound registration and shared credit pool access — anonymous registration is available without one

安装

clawhub install ooxxxxoo/global-agent-node-with-real-time-context-streaming-mission-form-autonomous-network-status-awaiting-peers

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