跳到正文
TakoAPI
返回技能列表

vlmrun-cli-skill

由 spillai 提供

Coding Agents & IDEs
724下载量由 clawskills.sh 提供
2星标
1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

Use the VLM Run CLI (`vlmrun`) to interact with Orion visual AI agent.

描述

该技能的功能

A CLI tool that sends images, videos, and documents to VLM Run's Orion visual AI agent using natural language prompts. Supports object detection, OCR, image and video generation, and document extraction. Sessions can be continued across multiple interactions to preserve context and generated artifacts.

Processes visual content and generates images or videos from the command line without writing any code, with session continuity that retains generated artifacts and conversation context across follow-up prompts.

何时使用

  • Extract line items and totals from invoice PDFs
  • Summarize key points from meeting recordings
  • Generate photorealistic images from text descriptions
  • Transcribe lecture videos with section timestamps
  • Compare two images and describe their differences

示例工作流

输入

User asks: Extract the vendor name, line items, and total from invoice.pdf

智能体
  1. 1

    Run vlmrun chat with the extraction prompt and invoice.pdf as input file

  2. 2

    Upload the PDF to the VLM Run API concurrently

  3. 3

    Orion processes the document and identifies structured fields

  4. 4

    Return extracted data as raw JSON with the --json flag

输出

Structured JSON containing vendor name, itemized line entries, and total amount from the invoice

前置要求

  • VLMRUN_API_KEY environment variable
  • VLM Run account to generate an API key

安装

clawhub install spillai/vlmrun-cli-skill

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