Menu

Individual skill

qwen-mm-plugins-omni-skill-creator

0upvotes

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 SKILL.md plus the frames, clips, and audio a consumer needs. Make sure to use this skill whenever someone hands over a video, tutorial, or screen recording and wants a reusable skill out of it, including when they say "learn from this video", "turn this tutorial into a skill", or "extract a skill from this recording" — and also when they describe wanting an agent to reproduce a workflow they have on video, even if they never use the word "skill".

src/capabilities/omni-skill-creator/skill/SKILL.md

Read pinned source

Source commit 8c2bd5c46b6a00814624202203a30284e4e6b43c

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
3,201
Repository last updated
Nov 10, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Omni Skill Creator

A skill for creating new skills from teaching videos and validating what it creates.

At a high level, the process of creating a skill goes like this:

- **Perceive the video** — read `references/perceiver.md` and perceive the teaching video, building a timestamped event log (`video_events.md`) as you go.
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill, along with a media plan for multimodal assets
- Run `validate_skill` (L1 structural check) before proceeding to evals
- Create a few test prompts and test the skill with them
- Review the results both qualitatively and quantitatively according to the selected feedback mode
  - While the runs happen in the background, draft quantitative assertions if there aren't any; in human-feedback mode explain them to the user, and in agent-self-iterate mode record their rationale in the iteration analysis
  - In human-feedback mode, present each test case's outputs and benchmark metrics to the user; in agent-self-iterate mode, inspect the same artifacts yourself without inventing human feedback
Back to top