DSH Plugins技能

agent-vision-toolkit

Anionex/agent-vision-toolkit

agent-vision-toolkit is a tool for DeepSeek Harness. A better vision toolbox and skill for pure-text models to "see": multi-image understanding, image Q&A, frontend UI restoration, GUI automation and more, with optional seamless integration into multiple mainstream agents, recognizing pasted images directly | 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

查看仓库项目主页

Anionex/agent-vision-toolkit Screenshot preview

Stars: 1.2k
Forks: 46
Issues: 9
Update: 20 days

REVIEW SCORECARD

评测成绩单

8.6/10Excellent

detail.dimSecurity9.0

detail.dimQuality8.5

detail.dimContent8.0

detail.dimDeps7.0

detail.dimMaintenance9.0

✓ 无Risky检出 · 自动化扫描结果仅供参考，非官方背书

AI DEEP REVIEW

AI 深度评测

7.2/10Consider

A promising vision toolkit for text-only agents, but install steps are undocumented and security details are unclear.

Code quality7

README describes multiple CLIs, a skill, a local proxy, native plugins, and a submodule package, but shows no test suite, CI badges, or build configuration.

Security6

The README mentions a transparent local proxy and shell-invokable CLIs plus a managed isolated runtime, but no permission model, secret handling, or download-and-execute details are given, so risk cannot be assessed.

Utility9

It directly addresses a real and common pain point for text-only models such as DeepSeek: image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation.

Maintenance8

Last updated 2026-08-27 with dated changelog entries in 2026-08, an active Trendshift badge, and 1198 stars, indicating ongoing development.

Docs6

The README excerpt is long on marketing and highlights but the install command is listed as unknown and no concrete setup or usage steps appear in the provided text.

Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.

PROJECT README项目说明展开Collapse

正在读取 GitHub README...

PROJECT TOPICS

项目标签

agent agent-skills claude-code codex computer-use deepseek dsh-plugin glm harness-engineering multimodal opencode text-only-llm vision vision-language-model

VALIDATION LADDER

验证进度

待结构检查

01市场发现Passed

02归类识别Passed

03结构检查Pending

04实机验证Pending

FAQ

Frequently Asked Questions

What is agent-vision-toolkit used for?

A better vision toolbox and skill for pure-text models to "see": multi-image understanding, image Q&A, frontend UI restoration, GUI automation and more, with optional seamless integration into multiple mainstream agents,

How popular is agent-vision-toolkit?

agent-vision-toolkit has 1,198 stars and 46 forks on GitHub, last updated 2026-08-27.

What license does agent-vision-toolkit use?

agent-vision-toolkit is distributed under the MIT license.

Is agent-vision-toolkit compatible with DeepSeek Harness?

agent-vision-toolkit is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE