CATEGORY
Verified manifests and exact versions in this category.
@lisonevf/dsh-qwen-imageDSH conversational image generation / editing plugin, specifically for Qwen-Image-2.1 (diffusers backend).
dsh-screen-readerGive the agent eyes on the screen: capture the whole desktop, one window, or one region and hand the IMAGE ITSELF to the session model (no second model, no description layer), plus an exact local pixel diff that locates what actually changed between two images instead of asking a model to guess. Win
dsh-pixel-artHandwritten pixel-art skill plugin: teaches the agent to use scripts to draw any image the user requests pixel by pixel, including recreating images from references through downsampling, and requires it to revise until satisfied before delivering. Handwritten pixel-art skill for DeepSeek Harness.
dsh-mimo-ttsMiMo voice for DeepSeek Harness: read answers aloud, talk to the composer, switch voices, clone your own. / 小米 MiMo 语音插件：自动朗读回复、点一下说话、音色切换与克隆。
