SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
Video Understanding & Analysis
分析已有视频的语义内容和时间线：场景感知、抽帧、关键帧索引、视频问答、转录摘要、分镜与剧本拆解、证据审查和内容检索。不包含视频剪辑、转码或生成。
Leaf membership
32 plugins
dsh-vision-bridge-skillLittleInk/dsh-vision-bridge-skillCatalog Analyzed一键式为dsh提供看图功能，借鉴了claude-vision-skill,先让agent读取了这个skill，后面尝试使用的时候发现平台会限制ds模型直接读取图片（只能剪贴板或者路径），所以做了一个桥接功能，VLM看完图后再把内容发送给DS并输出内容CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-dashscopeywleeo/dsh-vision-dashscopeCatalog AnalyzedDSH plugin from ywleeo/dsh-vision-dashscopeCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision#vision-tooldsh-vision-free-eyesCatalog AnalyzedModel-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.4Evidence updated2026-09-07Public signals2 stars · 845 downloadsdsh-visual-pluginjyh20030112/dsh-visual-pluginCatalog AnalyzedGives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals16 starsdsh-web-ui#packages/dsh-tool-describe-imagezhu1090093659/dsh-web-uiCatalog AnalyzedA `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals6900 starspicturereaderpicturereaderCatalog 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.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact3.3.1Evidence updated2026-09-06Public signals36 stars · 3404 downloadssidesightZhuXinAI/sidesightCatalog AnalyzedCLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starssoyo-dsh-pluginsoyo-dsh-pluginCatalog AnalyzedDSH-native video understanding with configurable multimodal providersCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-08Public signals437 downloadsvideo-reverse-engineeringwhaojie797-design/video-reverse-engineeringCatalog AnalyzedAgent Skill: reverse-engineer how a video was made. Extracts real keyframes/subtitles/audio, then produces a shot list, ready-to-paste AI image+video prompts, and a full replication guide (AI and live-action paths).CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsvision-toolkit-for-dsh-v0.1-maybe-jmjmj009gt/vision-toolkit-for-dsh-v0.1-maybe-Catalog AnalyzedZero-dependency vision OCR/Q&A toolkit (CLI + local web GUI) for OpenAI-compatible VLMs: Zhipu GLM, Qwen, OpenAI, OpenRouter, SiliconFlowCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsxby-detectxby-skill/xby-detectCatalog Analyzed包括日常物体检测、昆虫识别、植物识别、动物识别、电动自行车检测、手机检测、手势检测、火焰检测、香烟检测、人头人体检测、野生动物检测、鸟类识别、宠物情绪识别、菜品识别、Security帽人体检测、行人检测、反光衣检测、车辆检测、图像Category、目标检测、旋转目标检测、人体姿态估计和万物识别。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsxby-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。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsxby-pedestrianxby-skill/xby-pedestrianCatalog Analyzed输入一张图像，检测图像中的行人，输出所有目标的检测框、置信度和标签。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsxby-picxby-skill/xby-picCatalog Analyzed包括通用文本识别、手写识别、车牌识别、身份证识别、日常物体检测、昆虫识别、植物识别、护照识别、港澳台通行证识别、银行卡识别、营业执照识别、驾驶证识别、行驶证识别、动物识别、电动自行车检测、手机检测、手势检测、火焰检测、香烟检测、人头人体检测、野生动物检测、鸟类识别、宠物情绪识别、菜品识别、Security帽人体检测、行人检测、反光衣检测、车辆检测、图像Category、目标检测、旋转目标检测、人体姿态估计和万物识别。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.