DSH Plugin HubDSH 插件市场

dundunhan/dsh-video-lens

Plugin插件 Native原生 ⭐ 113 MIT Vision & Media视觉与多媒体

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native plugin built exclusively for DeepSeek Harness (DSH) that enables text-only DSH agents to work with local video files. It ships with three distinct tools to handle different video processing needs: video_probe extracts compact metadata like container format, duration, resolution, and codec info via ffprobe, video_analyze runs scene-change-aware frame sampling and optional timestamped ASR transcription before passing frames to an OpenAI-compatible vision model, and video_ask handles time-anchored questions by pulling matching frames from the queried time window. To install via npm, users run pnpm add dsh-video-lens in their DSH profile directory and add the package to the bundles array in their profile’s package.json, then export API keys and restart DSH.

When a user asks the DSH agent to analyze a local video, the agent automatically calls video_probe first to get basic metadata about the file. Next, it calls video_analyze to get structured evidence including detected scene boundaries, sampled frames, optional transcript, and a visual analysis of content across the timeline. If the user asks a specific question that references a time or keyword, the agent calls video_ask to locate the relevant segment, resample frames from that window, and return a grounded answer with supporting timestamps. This plugin is designed for DSH users who want their agents to process and answer questions about local video files.

This plugin requires Node.js version 20 or newer, and ffmpeg 6.0 or newer with ffprobe available on the system PATH. All vision and ASR functionality uses OpenAI-compatible endpoints, so users must export API keys for these services as environment variables before running DSH; ASR is optional and visual analysis will still work if no ASR key is set. The project is released under the open source MIT license, it has been tested on macOS and Linux but has not been tested on Windows, and users are responsible for reviewing the plugin’s code before running it as DSH does not review third-party plugins for security.

这是专为DeepSeek Harness（DSH）开发的原生插件，为DSH的纯文本大语言模型代理提供本地视频文件理解能力。插件提供三个工具：video_probe借助ffprobe快速获取视频的容器、时长、分辨率、编码、音轨字幕等元数据；video_analyze可基于场景变化采样帧，搭配可选ASR语音转文字，通过兼容OpenAI的视觉模型输出结构化分析结果；video_ask支持带时间锚点的问答查询。

当用户让DSH代理分析本地视频时，代理会先调用video_probe获取视频基础元数据，再调用video_analyze得到结构化分析结果，包括场景分界、采样帧、转写文本和视觉分析内容。如果用户提出带明确时间参考的特定问题，代理会调用video_ask定位对应时间窗口，重新采样帧后给出带依据的回答。适合需要让DSH代理处理本地视频内容、提取视频信息的开发者和普通用户使用。

插件要求Node.js ≥20版本，系统PATH中需要有≥6.0版本的ffmpeg和ffprobe，视觉模型和ASR都需要配置兼容OpenAI的API端点和密钥，ASR功能是可选的，不配置也不影响视觉分析运行。项目采用MIT许可证开源，目前已在macOS和Linux系统测试，Windows系统未经过测试。安装需要将插件加入DSH配置文件，重启后即可使用。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-video-lens（dundunhan/dsh-video-lens）
仓库：https://github.com/dundunhan/dsh-video-lens
本站详情页：https://www.yhbd.top/plugins/dundunhan-dsh-video-lens/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 113 · 最近提交 2026-09-19 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号（星标、许可证、更新活跃度、清单完整度）
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add github:dundunhan/dsh-video-lens

把 dundunhan/dsh-video-lens 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

9.8 KB · 缓存于 2026-09-18 19:38:36 · 9.8 KB

dsh-video-lens

Video understanding for DeepSeek Harness — give text-only agents eyes and ears on video.

A DeepSeek Harness (DSH) plugin that lets text-only LLM agents understand local video files. It provides two tools:

Tool What it does
video_probe Cheap, instant metadata via ffprobe: container, duration, resolution, fps, codecs, audio tracks, subtitles.
video_analyze Content understanding: scene-change-aware frame sampling (ffmpeg scdet), optional ASR transcript (speech with timestamps), fused with any OpenAI-compatible vision model into structured evidence JSON.
video_ask Time-anchored Q&A: parses explicit time references ("at 3:20", "第2分钟") or locates relevant speech via transcript keyword matching, re-samples frames from the matched windows, and answers with grounded evidence (answer + confidence + supporting timestamps).

v0.3.2. The plugin never locks you into a provider: vision and ASR are both OpenAI-compatible endpoints configured via baseUrl + model + key env var.

How it works

video file ──► video_probe ──► ffprobe ──► compact metadata JSON
           └─► video_analyze ──► scdet scene detection ──► shot boundaries
                                 ├─► ffmpeg frame sampling (one representative frame per shot, capped)
                                 ├─► ffmpeg audio extract ──► ASR transcript (timestamped)   [optional]
                                 └─► OpenAI-compatible vision API ──► evidence JSON
  • Scene changes are detected with ffmpeg's scdet filter (ffmpeg ≥ 6.0). Videos without detectable cuts fall back to uniform midpoint sampling.
  • ASR is strictly additive: if asrApiKeyEnv is unset or the provider fails, the visual analysis still completes and transcript is null.
  • All media work is delegated to ffmpeg/ffprobe on PATH — no native decoding in the agent.

Install

Prerequisites: Node.js ≥ 20, ffmpeg ≥ 6.0 (recommended) with ffprobe on PATH (brew install ffmpeg / apt install ffmpeg).

Option A — npm (recommended)

# in your DSH profile directory (the one containing package.json)
pnpm add dsh-video-lens

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 dundunhan/dsh-video-lens 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev opencode2dsh 下一个 Next DeepSeekHarnessDesktop →