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
avis-dsh-pluginilps2/avis-dsh-pluginCatalog AnalyzedAVIS 视频语义层 DSH 社区Plugin：给视频建可检索的语义索引，agent 毫秒级零 token 定位片段CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdeepseek-visionToryReina/deepseek-visionCatalog AnalyzedDSH plugin from ToryReina/deepseek-visionCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-auto-visiondsh-auto-visionCatalog AnalyzedAuto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a vision tool.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.4.0Evidence updated2026-09-07Public signals2 stars · 1117 downloadsdsh-bccaixlb/dsh-bccCatalog Analyzed包拆拆 for DeepSeek Harness: video to script/storyboard/style guide. dsh-plugin.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-bilibiliCZX2244/dsh-bilibiliCatalog AnalyzedBilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals9 starsdsh-eyesqing9835/dsh-eyesCatalog AnalyzedDSH 视觉模型Plugin：为无视觉能力的文本模型提供图片识别。粘贴/拖入/导入的图片自动交给 OpenAI 兼容视觉模型识别为文字并发送进对话，支持多轮复核（vision_ask）、多提供商配置。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-gemini-multimodaldsh-gemini-multimodalCatalog AnalyzedDeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.2Evidence updated2026-09-09Public signals767 downloadsdsh-imggmleong/dsh-imgCatalog AnalyzedGive text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh Plugin。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-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CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.5Evidence updated2026-09-10Public signals1006 downloadsdsh-plugin-deepeyeFavio8/dsh-plugin-deepeyeCatalog AnalyzedDeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-plugin-local-visionlinktao159357/dsh-plugin-local-visionCatalog AnalyzedDSH plugin from linktao159357/dsh-plugin-local-visionCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-plugins#dsh-vision-toolTZHR-invest/dsh-pluginsCatalog AnalyzedAgent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-tool-accurate-visiondsh-tool-accurate-visionCatalog AnalyzedModel-facing accurate_vision tool: precise image spatial reasoning via a vision modelCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-09Public signals431 downloadsdsh-video-lensdsh-video-lensCatalog AnalyzedGive text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解Plugin（场景感知抽帧 + VLM + 可选语音转录）CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.1Evidence updated2026-09-08Public signals346 downloadsdsh-video-sherlockjo32/dsh-video-sherlockCatalog AnalyzedA local-first, evidence-backed video investigation app for DeepDeck.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-video-understanddsh-video-understandCatalog AnalyzedLow-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Self-contained engine, no external dependencies.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.5.2Evidence updated2026-09-06Public signals9 stars · 1120 downloadsdsh-visionAnyi-qaq/dsh-visionCatalog Analyzed⚠️ 已归档，不再维护，不可用（archived & unavailable）CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-visionTerry12138qy/dsh-visionCatalog AnalyzedDeepSeek Harness 识图Plugin：为不具备原生识图能力的模型提供识图能力（阿里云百炼 qwen3.5-omni-plus，失败自动切换智谱 glm-4.6v-flash）。Composed of claude-vision-skill 移植适配。 | Vision tool for DeepSeek HarnessCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.