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-koboldcpp-handsdsh-koboldcpp-handsCatalog AnalyzedHands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.1.1dsh-bridge-previewxing666173/dsh-bridge-previewCatalog AnalyzedDSH Plugin:为 dsh-tool-vision 图片桥接提供对话内联预览 (inline image preview for bridged pasted images)Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-mmroutejmxsxwyzjdwl/dsh-mmrouteCatalog AnalyzedTransparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-toolkitchou109/dsh-toolkitCatalog AnalyzedDeepSeek Harness 增强工具包，四个即插即用的小工具合而为一——粘贴图片自动识图、工作区一键在资源管理器/VS Code/终端打开并可Copy路径、消息历史侧栏、已归档会话面板。一条命令安装全部组件。 a DeepSeek Harness enhancement pack — four tools in one: paste-image auto-vision, one-click workspace open (Explorer/VS Code/terminal) plus path copy, a message rail, and an archived-sessions panel. One command installs all.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-screen-eyedavidekingsss/dsh-screen-eyeCatalog AnalyzedAgent screen capture on macOS and Windows: one tool captures the screen and returns the image itself, so the model sees it without a second call. On Windows a whole burst runs in one engine call; on macOS a resident helper drops a region capture to 13ms and a change check to 23ms. A second tool, macOS only, reports whether Screen Recording is granted and opens the settings pane that fixes it.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-desktop-automationdsh-desktop-automationCatalog AnalyzedmacOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut, Photoshop, WPS, native clients) like a human — 14 tools for mouse, keyboard, scrolling, app activation, windows and screenshots, plus a vision closed-loop (desktop_see for image understanding + desktop_locate for UI element coordinates) that reuses dsh existing vision credentials. GUI-session service starts on demand, no login autostart.Remote & MobilenpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1picturereaderpicturereaderCatalog AnalyzedImage "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact3.3.3dsh-design-qadsh-design-qaCatalog AnalyzedDesign-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.4PPT-Design-Skillsunchaokun/PPT-Design-SkillCatalog AnalyzedPrecision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect Build Mode control, AI image generation, and fully editable PPTX. 面向专业演示设计场景，帮助用户从需求分析、视觉方向选择到原生可编辑 PPTX 交付，打造高质量、可持续修改的演示文稿。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-chat-imaginedsh-chat-imagineCatalog AnalyzedAutomatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.1dsh-ocr-localdsh-ocr-localCatalog AnalyzedLocal OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.3dsh-tool-visual-primitivesdsh-tool-visual-primitivesCatalog AnalyzedAnalyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.5.1dsh-plugin-grok2api-media-tooldsh-plugin-grok2api-media-toolCatalog AnalyzedGives dsh the ability to generate images and videos through the grok2api API.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.8.1dsh-labnanadsh-labnanaCatalog AnalyzedLabnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.3dsh-ocr-localdsh-ocr-localCatalog AnalyzedLocal OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR Plugin：图片转文字，PP-OCRv5 + ONNX Runtime，完全离线，支持 TUI 与 Web。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.3dsh-mingmudsh-mingmuCatalog Analyzed明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.5@try-works/dsh-paper-design@try-works/dsh-paper-designCatalog AnalyzedPaper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.4dsh-sightdsh-sightCatalog AnalyzedPlug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.1Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation