dsh-artifact-viewer
Run the following command in DeepSeek Harness:
dsh plugin install wang-junjian/dsh-artifact-viewer
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, use the command dsh plugin install wang-junjian/dsh-artifact-viewer, or visit https://github.com/wang-junjian/dsh-artifact-viewer for more details.
About this plugin
In DeepSeek Harness agent conversations, artifacts produced by tools and attachments can be scattered and difficult to manage, hindering workflow efficiency. The dsh-artifact-viewer plugin addresses this by adding a sidebar that automatically detects artifacts like created files and image attachments, listing them in a right-hand panel for centralized access. It supports bookmarking to save and persist important artifacts locally, and offers previews for various file formats such as HTML, Markdown, images, and source code, with options to open files using host applications. Ideal for developers and users of DeepSeek Harness who frequently engage in code generation, file operations, or need quick access to conversation artifacts, this plugin enhances management efficiency and user experience, making conversation products easily accessible and organized.
Use Cases
- Automatically detect and list generated files and images in agent conversations.
- Use bookmarking to save important artifacts for quick access later.
- Preview multiple file formats like HTML and Markdown without leaving the conversation interface.
Best For
- Developers using DeepSeek Harness for model inference and file generation.
- AI tool users who need to efficiently manage conversation artifacts.
- Team members frequently handling code and attachments in collaborative projects.
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.