agent-vision-toolkit
SkillGitHubActivePython
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
Description provenance: Original source
Measured: Oct 22, 2026 · 71 observations
Domains & Uses
- Domains
- Agents, skills and MCP
- Uses
- Agent skills, Code assistants
Installation
git clone https://github.com/Anionex/agent-vision-toolkit ~/.claude/skills/agent-vision-toolkitCheck at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/Anionex/agent-vision-toolkitClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
1,241stars · Oct 22, 2026
+35 (+2.9 %)since Sep 22, 2026
Exact values · 31 readings
| Measured | stars | Change |
|---|---|---|
| 1,241 | +4 | |
| 1,237 | -1 | |
| 1,238 | +4 | |
| 1,234 | 0 | |
| 1,234 | 0 | |
| 1,234 | +1 | |
| 1,233 | +1 | |
| 1,232 | +1 | |
| 1,231 | +3 | |
| 1,228 | +2 | |
| 1,226 | +3 | |
| 1,223 | +3 | |
| 1,220 | +2 | |
| 1,218 | +1 | |
| 1,217 | +1 | |
| 1,216 | +2 | |
| 1,214 | 0 | |
| 1,214 | +1 | |
| 1,213 | -1 | |
| 1,214 | 0 | |
| 1,214 | -3 | |
| 1,217 | -2 | |
| 1,219 | +2 | |
| 1,217 | +2 | |
| 1,215 | +1 | |
| 1,214 | +1 | |
| 1,213 | +3 | |
| 1,210 | 0 | |
| 1,210 | +2 | |
| 1,208 | +2 | |
| 1,206 | · |