dsh-director-toolkit
Run the following command in DeepSeek Harness:
dsh plugin install lhmd/dsh-director-toolkit
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command: dsh plugin install lhmd/dsh-director-toolkit, or refer to the GitHub repository at https://github.com/lhmd/dsh-director-toolkit for more installation details.
About this plugin
The DSH Director Toolkit addresses the challenge of transitioning from vague 3D ideas to concrete scene implementation in digital art creation. Artists often start with rough concepts but need structured guidance to develop actionable production plans, especially when working across multiple software platforms. This plugin bridges that gap by providing detailed direction packs that cover essential elements like camera composition, lighting, materials, geometry, and motion, while adapting to tools such as Blender, Three.js, Houdini, and C4D. Its core capability lies in generating software-aware render settings, step-by-step build instructions, and supplementary features like negative prompts and bilingual showcase copies, making creative ideas more tangible and efficient to execute. Ideal for 3D artists, technical designers, and creators needing quick scene planning, it accelerates the workflow from inspiration to final product for both individual and collaborative projects.
Screenshots
Use Cases
- Rapidly convert rough 3D ideas into buildable scene direction packs
- Generate detailed render and motion guidance for Blender or Three.js projects
- Plan cross-software production steps to enhance team collaboration efficiency
Best For
- 3D artists and technical designers
- Independent game and film creators
- Creative teams needing quick scene planning
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.




