Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 1065 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-image-dscribershuxu-zhao/dsh-image-dscriberCatalog AnalyzedGiving text models eyes.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedxby-image-detectxby-skill/xby-image-detectCatalog Analyzed检测图像中的80类COCO目标（人、车、动物、日常物品等），输出边界框、置信度和类别标签。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-bridgeC-4-C-4/dsh-vision-bridgeCatalog Analyzed让 DeepSeek 模型获得图像理解能力Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-toolkit-windows-edgesailoflight/dsh-vision-toolkit-windows-edgeCatalog AnalyzedStatus:完成Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedxby-extract-imagexby-skill/xby-extract-imageCatalog AnalyzedMCP服务器提供从本地文件、URL提取图像并转换为base64格式的功能，适用于LLM分析。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visionAnyi-qaq/dsh-visionCatalog Analyzed⚠️ 已归档，不再维护，不可用（archived & unavailable）Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-windows-ocrdsh-windows-ocrCatalog AnalyzedLocal OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.7.0dsh-minimal-visionFlora233333/dsh-minimal-visionCatalog AnalyzedDSH 极简模式视觉辅助：保持灰测体验所需的首轮干净上下文，同时通过隐藏上下文和按需 Bash 工作流提供视觉分析 | Vision assistance for DSH minimal mode: preserve the clean first-turn context behind the gray-test DeepSeek experience while adding on-demand visual analysis through a hidden-context Bash workflow.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tesseract-ocrdsh-tesseract-ocrCatalog AnalyzedLocal OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.7.0improved_vision_for_deepseekzyh20041227/improved_vision_for_deepseekCatalog AnalyzedFull-coverage image tiling for DeepSeek Harness vision models, dense-text OCR, and document AIMemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-hub#file-dropxing666173/dsh-vision-hubCatalog AnalyzedDrag-and-drop file upload for PDF, Word, Excel and images: dropped files are saved to a local directory and referenced by path, no base64 bloat in the chat.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-hub#bridge-previewxing666173/dsh-vision-hubCatalog AnalyzedInline preview for \[图片: path] image bridge markers: after the marker renders, the image shows in chat automatically, keeping long instructions out of the conversation.Sessions & MessagesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-open-eyesdsh-open-eyesCatalog AnalyzedVision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2-rc.1dsh-inline-images3403473060/dsh-inline-imagesCatalog AnalyzedRender local image paths from assistant replies inline in the message body (9 formats, click-to-zoom lightbox, adjustable size).Sessions & MessagesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-browser-visiontristan-mcinnis/dsh-browser-visionCatalog AnalyzedBrowser tool for DeepSeek Harness that can SEE the page: browser-use over CDP driven by deepseek-v4-flash-vision-exp. Reads canvas text, text inside images and rendered charts, returns schema-validated JSON, and reports per-run cost.Browser & WebGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedDSH-dseyesdsh-dseyesCatalog AnalyzedNative image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.0vision-usezzy6-a/vision-useCatalog AnalyzedDesktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedscreenshot-reviewwenyixiaoqingnian/screenshot-reviewCatalog AnalyzedScreenshot-review skill for DeepSeek Harness: the agent opens a frontend page, screenshots it, views the screenshot itself, revises the code, then re-screenshots — iterating until the page visually matches the user's requirements. Ships as a dsh.bundle, so it installs with `dsh plugin add`.SkillsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedSource candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation