Skill rating

Create a new Agent Skill from a teaching video, screen recording, or demonstration. Reads the recording as one audio-visual timeline — what is shown and what is said, time-aligned — then writes a SKIL

Reason about distance, size, orientation, relative position, camera motion, and object counts in images and video. Ground objects and estimate their depths, then use stateless geometry tools to comput

Use whenever a task involves parametric CAD in FreeCAD — modeling parts and assemblies, editing object properties, technical drawings, importing/exporting STEP/STL/OBJ/DXF, PDF/Excel reports from a mo

Use whenever a task involves building or editing a 3D scene or asset in Blender — modeling, characters/people, architecture/interiors, terrain/landscapes, props, materials, lighting, or rendering. Cov

Web search and page extraction MCP tools (Serper, Exa, Tavily, or Serply) plus Serper Lens reverse-image search for confirming facts — web_search (find facts), web_extractor (read a page in depth), im

Inspect local NIfTI (.nii/.nii.gz) header metadata or render slices with shared intensity normalization and window presets. Use for checking volume geometry, NIfTI viewing, choosing slices or windows,

Operate physical hardware (cameras, sensors, lamps, arms, lab equipment) through Model Hardware Standard adapters — mhs_discover (what devices exist), mhs_meta_info (what one device can do and its saf

Translate an existing video's speech and optionally produce a speaker-preserving dubbed video: analyze speech and visible subtitles, author a timed translation plan, synthesize reference-guided voices

Turn an existing movie or long-form video into a finished narrated commentary cut: build complete chronological Omni evidence, author a grounded narration plan, render resumable shards with subtitles

Read and visualize any file — images, video, documents, code, data, 3D models, and more — with MCP tools. Use when the agent needs to inspect file contents or media metadata, crop an image, draw bound

Understand images, video, and audio using hosted or self-hosted model services through MCP tools. Use for visual questions, OCR, object grounding, speech transcription, speaker diarization, timestampe

Example/template capability — a minimal MCP server whose demo tools (echo, make_swatch, make_film_strip, describe, config_probe) show how a Qwen-MM-Plugins capability is structured: the content-return

Turn local music, an existing music caption, or a validated storyboard into an MV: analyze music for visual planning, author or validate a timed storyboard, generate or resume image and video assets,

Build and query persistent stateful audio-visual memory for long videos, including people, speaker-attributed dialogue, paralinguistics, non-speech sound, events, semantic facts, and selective source-

Convert a local tutorial, lesson, demonstration, or screen recording into an illustrated PDF note using Omni audio-video understanding and visual evidence.

Conduct video-based deep research: deeply read one video, investigate text and visual anchors using external articles, papers, images and watched related videos, independently check comparisons and da

Triggered for long videos (30+ minutes), whether a single file or a directory of multiple videos. Vision-language MCP tools designed for efficient reading and semantic analysis of long videos (30+ min

Editing-director skill that OWNS every video task built from EXISTING REAL FOOTAGE the user supplies (vlog, montage, intro, recap, eating/travel/family edits, style replication, compositing, subtitles

Generate step-by-step math problem-solving tutorial videos in Chinese (Mandarin). Use when: (1) a user provides a math problem and wants an explanation video, (2) someone says "make a math tutorial",