lora-sys/free-vision-skill

面向纯文本编程 agent 的低 token 视觉证据编译器，把图片压缩成 VEP 包喂给 DeepSeek/Codex/Claude Code

A low-token visual evidence compiler for text-only coding agents. Convert images into compact Visual Evidence Packets (VEP) for DeepSeek, Codex, Claude Code, and other text-only models.