← Back to list

taxue-dsh-artisan

DeepSeek Harness Other Low risk

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

DSH 一体化视觉创作工具链:提示词反推与审计优化,多供应商生图,支持异步后台出图。

How to install

DeepSeek Harness dsh plugin add github:taxueseek/taxue-dsh-artisan

About

taxue-dsh-artisan DeepSeek Harness 的一体化视觉创作工具链:**提示词反推、确定性色卡提取、审计优化、多供应商生图**。基于原反推提示词插件完善而来,并原生整合了多供应商生图能力,成为可灵活组装的单插件。 解决什么问题 原来要「反推一张图 → 生成一张图」需要先后调用两个互不相识的插件:一个只出提示词、一个只生图,模型要自己把结构化的 meta_prompt 手动搬运成生图的 prompt,中间承接全靠试错。 整合后四个原生工具在同一插件内,可单个调用、也可按需串联:反推 → 色卡/优化 → 生图。 四个工具 | 工具 | 作用 | 是否调远程 | |---|---|---| | reverse_prompt | 反推图像/视频提示词并**直出可直接生图的完整提示词**,附带优化方向、画幅建议与同规格同风格新图引导 | 否(本地纯函数) | | optimize_prompt | 对候选提示词做本地结构审计:信息量、相机冲突、构图/动作缺失、硬冲突(风格机制互斥)、模仿/IP 风险、单变量优化建议 | 否(本地纯函数) | | extract_palette | 对 PNG 参考图做**确定性色卡提取**:主色/辅色/点缀色 hex 与占比、暗部/高光锚点色;同一张图永远同一结果 | 否(本地像素算法) | | generate_image | 用…

Recommendation signals

45 Tool quality · Based on stars, downloads, maintenance, security and docs
User interest · Adjusted by in-site views, install copies and download clicks
45 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
TypeScript
GitHub stars
0
mo. downloads
Last push
2026-08-24
Created
2026-08-19

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings
curated 收录但无 npm 包/安装命令
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
creative-tools, deepseek-harness, dsh-plugin, image-generation, prompt-engineering

Related plugins

DeepSeek Harness New
Score86

dsh-vision-router

ysr666/dsh-vision-router

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

☆ 962 ↓ 39.6K Other
DeepSeek HarnessClaude CodeCodex New
Score74

modlens

liustack/modlens

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

☆ 3.6K ↓ 20.0K Other
DeepSeek Harness New
Score69

dsh-vision-toolkit

Anionex/dsh-vision-toolkit

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

☆ 818 ↓ 1.8K Other
DeepSeek Harness Featured
Score68

dsh-deepseek-vision

siegfly/dsh-deepseek-vision

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

☆ 7 ↓ 3.2K Other