qwen-mm-plugins
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
Its scripts were only partly scanned.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/QwenLM/Qwen-MM-Plugins with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/QwenLM/Qwen-MM-Plugins'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/qwenlm--qwen-mm-plugins)HTML
<a href="/listings/qwenlm--qwen-mm-plugins"><img src="/api/listings/qwenlm--qwen-mm-plugins/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
For agents
Ask your agent (replace `core` and `api` with the plugins you need):
Install the core and api plugins following https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/docs/en/installation.md
For users
The guided installer supports Claude Code, CodeBuddy, Codex, Qoder, OpenClaw, Qwen Code, and Gemini CLI. Shared configuration lives in `~/.qwen-mm-plugins/config`.
In-app setup for WorkBuddy, QoderWork, and QwenWork, plus manual setup for DeepSeek Harness, Hermes Agent, opencode, pi, and QwenPaw, is documented in the [other harness guide](docs/en/manual_harnesses.md).
curl -fsSL https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/install.sh | bash
Update the capabilities already installed in one harness:
curl -fsSL https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/install.sh | bash -s -- update
Released capabilities use independent, immutable tags. For local checkout installs, rollback, manual skill + MCP setup, dependencies, and Windows/WSL2, see the [installation guide](docs/en/installation.md).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 173 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "qwen-mm-plugins",
- "owner": {
- "name": "QwenLM",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins"
- },
- "metadata": {
- "description": "Qwen multimodal understanding plugins — Agent Skills + MCP servers",
- "version": "1.2.0"
- },
- "plugins": [
- {
- "name": "qwen-mm-plugins-core",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/core",
- "ref": "qwen-mm-plugins-core-v1.3.0"
- },
- "description": "Inspect local files and media, extract video frames, and crop or annotate images."
- },
- {
- "name": "qwen-mm-plugins-api",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/api",
- "ref": "qwen-mm-plugins-api-v1.4.0"
- },
- "description": "Understand images, audio, and video through model APIs, including OCR, object localization, and speech transcription."
- },
- {
- "name": "qwen-mm-plugins-search",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/search",
- "ref": "qwen-mm-plugins-search-v1.2.0"
- },
- "description": "Search the web, read pages, and identify objects or places with reverse-image search."
- },
- {
- "name": "qwen-mm-plugins-video-memory",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/video-memory",
- "ref": "qwen-mm-plugins-video-memory-v1.2.0"
- },
- "description": "Build searchable, hierarchical memory of long videos to summarize content and locate events, text, and dialogue."
- },
- {
- "name": "qwen-mm-plugins-omni-memory",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/omni-memory",
- "ref": "qwen-mm-plugins-omni-memory-v1.2.0"
- },
- "description": "Build and query audio-visual memory to track speakers, dialogue, sounds, and events across videos."
- },
- {
- "name": "qwen-mm-plugins-omni-video2note",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/omni-video2note",
- "ref": "qwen-mm-plugins-omni-video2note-v1.1.0"
- },
- "description": "Convert a local tutorial video into an illustrated PDF with resumable processing and offline status inspection."
- },
- {
- "name": "qwen-mm-plugins-video-edit",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/video-edit",
- "ref": "qwen-mm-plugins-video-edit-v1.2.0"
- },
- "description": "Edit existing footage into finished videos with pacing, sound, subtitles, and visual effects."
- },
- {
- "name": "qwen-mm-plugins-omni-chatcut",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/omni-chatcut",
- "ref": "qwen-mm-plugins-omni-chatcut-v1.1.0"
- },
- "description": "Omni ChatCut video creation with Music-to-MV, movie commentary, and speaker-preserving video translation."
- },
- {
- "name": "qwen-mm-plugins-video-spatio",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/video-spatio",
- "ref": "qwen-mm-plugins-video-spatio-v1.1.0"
- },
- "description": "Model-free 3D spatial reasoning (skill) + stateless geometry/BEV MCP tools."
- },
- {
- "name": "qwen-mm-plugins-edu-agent",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/edu-agent",
- "ref": "qwen-mm-plugins-edu-agent-v1.2.0"
- },
- "description": "Create narrated Mandarin math and science tutorial videos or interactive explainers from problem statements and images."
- },
- {
- "name": "qwen-mm-plugins-blender",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/blender",
- "ref": "qwen-mm-plugins-blender-v1.2.0"
- },
- "description": "Create, refine, and render 3D scenes and assets in Blender."
- },
- {
- "name": "qwen-mm-plugins-freecad",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/freecad",
- "ref": "qwen-mm-plugins-freecad-v1.2.0"
- },
- "description": "Create and edit parametric CAD models, technical drawings, and model exports in FreeCAD."
- },
- {
- "name": "qwen-mm-plugins-omni-skill-creator",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/omni-skill-creator",
- "ref": "qwen-mm-plugins-omni-skill-creator-v1.1.0"
- },
- "description": "Turns a demonstration video into a reusable Agent Skill. Needs a DashScope key and ffmpeg."
- },
- {
- "name": "qwen-mm-plugins-mhs",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/mhs",
- "ref": "qwen-mm-plugins-mhs-v1.2.0"
- },
- "description": "Operate physical hardware through Model Hardware Standard adapters: discover devices, read sensors and camera frames, send commands with host-side safety-limit enforcement, check health, and emergency-stop — as MCP tools. Adapters are run by the hardware's owner."
- },
- {
- "name": "qwen-mm-plugins-nifti",
- "description": "Inspect NIfTI header metadata and render slices with shared intensity ranges and window presets.",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/nifti",
- "ref": "qwen-mm-plugins-nifti-v1.1.0"
- }
- },
- {
- "name": "qwen-mm-plugins-omnidr",
- "description": "Research a video using audiovisual evidence and external sources, and produce a cited interactive report.",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
- "path": "src/capabilities/omnidr",
- "ref": "qwen-mm-plugins-omnidr-v1.0.0"
- }
- }
- ]
- }
README.md · README · 166 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Qwen-MM-Plugins
- **English** · [中文](README.zh.md)
- Native multimodal plugins for Qwen models. Make any agent harness multimodal-native.
- <div align="center">
- [](https://qwenlm.github.io/qwen-mm-plugins-hub/)
- [](https://github.com/QwenLM/Qwen-MM-Plugins/issues/72)
- [](https://join.slack.com/t/qwen-mm-plugins/shared_invite/zt-475c57729-K2rpYeb6EJKNJUd5Zun5Cg)
- </div>
- ## 📰 News
- - **2026-09-22**: 💬 Join our [**WeChat group**](https://github.com/QwenLM/Qwen-MM-Plugins/issues/72) or [**Slack community**](https://join.slack.com/t/qwen-mm-plugins/shared_invite/zt-475c57729-K2rpYeb6EJKNJUd5Zun5Cg) to discuss workflows, share projects, and suggest new features.
- - **2026-09-20**: 🚀 Added [**MHS**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/mhs/cookbook/) for operating physical hardware and [**video-spatio**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-spatio/cookbook/) for 3D spatial reasoning over images and video.
- - **2026-09-16**: 🛠️ Added [**omni-skill-creator**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-skill-creator/cookbook/) to turn demonstration videos into reusable Agent Skills.
- <details>
- <summary><b>Earlier updates</b></summary>
- - **2026-09-10**: 🎬 Added [**omni-chatcut**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-chatcut/cookbook/) for music videos, movie commentary, and video translation, plus [**omni-video2note**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-video2note/cookbook/) for turning tutorial videos into illustrated PDFs.
- - **2026-09-10**: 🌐 Added the [**Plugin Hub**](https://qwenlm.github.io/qwen-mm-plugins-hub/) to browse plugins, documentation, and cookbook examples with videos and interactive demos.
- - **2026-09-03**: 🧠 Added [**omni-memory**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-memory/cookbook/) to build and query audio-visual memory across long videos, including speakers, dialogue, sounds, and events.
- - **2026-08-11**: 🧩 Introduced standalone [**api**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/api/cookbook/) and [**search**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/search/cookbook/) plugins, separating Qwen VL/Omni model services and web search from local multimodal tools.
- - **2026-08-03**: 🎉 Initial release! [**core**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/core/cookbook/) brings native image, video, document, and 3D file reading; [**video-memory**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-memory/cookbook/) enables long-video QA; [**video-edit**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-edit/cookbook/) handles media generation and editing; [**Blender**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/blender/cookbook/) and [**FreeCAD**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/freecad/cookbook/) support 3D modeling and parametric CAD; and [**edu-agent**](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/edu-agent/cookbook/) creates educational videos and interactive explainers.
- </details>
- ## Architecture
- 
- ## Install
- ### For agents
- Ask your agent (replace `core` and `api` with the plugins you need):
- ```text
- Install the core and api plugins following https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/docs/en/installation.md
- ```
- ### For users
- The guided installer supports Claude Code, CodeBuddy, Codex, Qoder, OpenClaw, Qwen Code, and Gemini
- CLI. Shared configuration lives in `~/.qwen-mm-plugins/config`.
- In-app setup for WorkBuddy, QoderWork, and QwenWork, plus manual setup for DeepSeek Harness, Hermes
- Agent, opencode, pi, and QwenPaw, is documented in the
- [other harness guide](docs/en/manual_harnesses.md).
- ```bash
- curl -fsSL https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/install.sh | bash
- ```
- Update the capabilities already installed in one harness:
- ```bash
- curl -fsSL https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/install.sh | bash -s -- update
- ```
- Released capabilities use independent, immutable tags. For local checkout installs, rollback,
- manual skill + MCP setup, dependencies, and Windows/WSL2, see the
- [installation guide](docs/en/installation.md).
- ## Capabilities
- Each capability is installed independently as a **Skill** plus an optional **MCP server**, named
- `qwen-mm-plugins-<capability>`. Pick by your agent's main model. We strongly recommend the `core`
- plugin for multimodal models: it lets the main model read images, video and files natively, rather
- than routing them through a separate API or ad-hoc shell commands.
- **General**:
- | Capability | Use case | Cookbook |
- |---|---|---|
- | `core` | Reads local images and video frames, and visualizes documents, code, data, and 3D models for the agent to inspect. Includes media metadata, cropping, bounding-box annotation and page/frame export. No API key in the default native mode. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/core/cookbook/) |
- | `nifti` | Inspects NIfTI header metadata and renders configurable source-axis slices with volume-level intensity normalization, explicit window presets and effective-configuration reporting. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/nifti/cookbook/) |
- | `api` | Calls model services to understand images, video and audio: VL vision chat/OCR/grounding, Omni transcription/diarization/captioning/event analysis, dedicated ASR and SAM3 segmentation. Uses DashScope or compatible self-hosted services, configured per model family. With DashScope, oversized local audio and video can use model-bound temporary OSS automatically. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/api/cookbook/) |
- | `search` | For any model. Web search and page extraction with Serper, Exa, Tavily, Serply or Keenable; reverse-image search uses Serper. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/search/cookbook/) |
- | `mhs` | For any model. Operates real hardware — cameras, sensors, lamps, arms, lab equipment — through Model Hardware Standard adapters, with host-side safety-limit enforcement and an emergency stop. Adapters are run by the hardware's owner; no cloud key. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/mhs/cookbook/) |
- **Qwen VL series model** (e.g. **Qwen3.8-Max**, **Qwen3.7-Plus**):
- | Capability | Use case | Cookbook |
- |---|---|---|
- | `video-memory` | Builds a hierarchical memory of a long video, so questions about it are answered from the memory instead of re-watching. Needs a DashScope key and ffmpeg. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-memory/cookbook/) |
- | `video-edit` | Generates images, video and audio, and runs editing workflows over them. Needs a DashScope key, ffmpeg and Node. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-edit/cookbook/) |
- | `video-spatio` | Answers 3D questions about images and video — distance, size, orientation, left/right/front/behind, camera motion, 3D counting. The model does the perception; stateless geometry tools do the math. No API key for the geometry tools. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/video-spatio/cookbook/) |
- | `blender` | Drives a running Blender: modelling, materials, lighting and rendering. Needs Blender installed. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/blender/cookbook/) |
- | `freecad` | Drives a running FreeCAD: parametric CAD, STEP/STL and FEM. Needs FreeCAD installed. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/freecad/cookbook/) |
- | `edu-agent` | Creates Chinese math and science explainer videos and interactive pages. Skill-only; needs Node and ffmpeg. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/edu-agent/cookbook/) |
- **Qwen Omni series model** (e.g. **qwen3.8-omni-flash**):
- > Most harnesses cannot yet feed audio to the main model natively. For now, audio is handled through
- > the API instead.
- | Capability | Use case | Cookbook |
- |---|---|---|
- | `omni-chatcut` | Video-creation Skill collection for Music-to-MV, movie commentary, and speaker-preserving video translation. Needs the relevant generation/Omni services, ffmpeg/ffprobe, and an optional external dubbing service for translated voice output. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-chatcut/cookbook/) |
- | `omni-video2note` | Converts a local tutorial video into an illustrated PDF using Omni audio-video understanding, with review feedback. Needs a DashScope key and ffmpeg. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-video2note/cookbook/) |
- | `omni-skill-creator` | Turns a demonstration video into a reusable Agent Skill. Needs a DashScope key and ffmpeg. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-skill-creator/cookbook/) |
- | `omni-memory` | Builds an audio-visual memory of a long video: who is present, who said what, how they said it, and what it sounded like. The Omni model reads the video together with its audio track. Needs a DashScope key and ffmpeg. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omni-memory/cookbook/) |
- | `omnidr` | Conducts deep research around a video and the user's question, drawing on related webpages, videos, documents, and other external sources to produce an HTML report. | [Cookbook](https://qwenlm.github.io/qwen-mm-plugins-hub/plugins/omnidr/cookbook/) |
- Exact versions and optional extras are in the
- [installation guide](docs/en/installation.md#dependencies).
- ## Try it
- After installing a capability, reference a file and ask naturally; the Skill selects the relevant
- MCP tool.
- ```text
- @report.pdf Summarize page 3 and extract its table.
- @meeting.mp4 Transcribe this with speaker labels and timestamps.
- @place.jpg Identify where this photo was taken and verify it on the web.
- @lecture-2h.mp4 List the main points with timestamps.
- @tutorial.mp4 Create an illustrated PDF note at /absolute/path/tutorial-notes.pdf.
- ```
- `core` reads media at dynamic resolution, so manual resizing is normally unnecessary.
- For NIfTI header metadata, use the dedicated `nifti` plugin's `nifti_inspect` tool. Use
- `nifti_render_slices` directly for configurable viewing; inspection is not a prerequisite.
- It defaults to three interior slices on source axis 2 with a shared volume-level P1–P99 range.
- To try `nifti` before its first release, follow the [source development loop](docs/en/local_development.md#fast-source-loop).
- ## Requirements and configuration
- - [`uv`](https://docs.astral.sh/uv/) provides `uvx`, which installs Python dependencies on demand.
- - Local `core` tools need no API key in the default native-image mode. Text-only caption fallback,
- cloud, and search capabilities need their provider credentials.
- - Video, document, browser, Blender, and FreeCAD workflows may need system applications.
- Run the installer's **Configure** and **Verify** actions to set credentials and check dependencies.
- See [Installation](docs/en/installation.md#dependencies) for prerequisites and the
- [configuration reference](docs/en/configuration.md) for every setting.
- ## Documentation
- - [Installation](docs/en/installation.md)
- - [Configuration](docs/en/configuration.md)
- - [Contributing](CONTRIBUTING.md) · [Local development](docs/en/local_development.md)
- - [Add a new plugin](docs/en/how_to_add_new_capability.md) · [Hub authoring](docs/en/hub.md) · [Testing](docs/en/testing.md)
- ## Citation
- If you find this project useful in your research or work, please consider citing it:
- ```bibtex
- @misc{qwen_mm_plugins2026,
- title = {Qwen-MM-Plugins: Make any agent harness multimodal-native},
- author = {{Qwen Team}},
- year = {2026},
- url = {https://github.com/QwenLM/Qwen-MM-Plugins}
- }
- ```
- ## License
- Apache-2.0 — see [LICENSE](LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.