visualize-uav-trajectory skill
A skill that turns drone flight video into a trajectory overlay figure with a zoom-in and an editable PPTX.
- 245 ★ on the repository
- Last commit
- GPL-3.0
Extended access
Why this level
- Runs video processing scripts and creates files in the working folder.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/visualize-uav-trajectoryDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs video processing scripts and creates files in the working folder.
This is third-party code. Review the repository files before installing.
What it does
The Codex skill `visualize-uav-trajectory` takes a flight video and optionally a reference picture, then returns a composite frame with the drone positions overlaid. It comes with a zoom-in on the final position, a combined publication figure and an editable PPTX presentation. The agent chooses and checks frames and masks itself, then saves the keyframe configuration, a manifest and the commands to rerun. The opacity of individual drone shadows and the layout can be changed with plain phrases. The rendering scripts are separate from the old graphical interface and run in Python.
Who it is for. Robotics researchers who need a drone trajectory figure for a paper or report without hand-tuning parameters.
Good fit when
- An experiment video is recorded and a paper needs one frame showing a chain of drone positions.
- A reference figure from another paper exists and its style must be reproduced on your own data.
- An editor wants a presentation where captions and images are separate objects.
- Several experiments must be laid out consistently to a journal's requirements.
Not a fit when
- You need metric measurements of trajectory or speed, which the figure does not replace.
- The video is low quality and a sharp frame is not possible.
- You need real-time stream processing.
Example request
Use $visualize-uav-trajectory to process /data/flight.mp4 following /data/ref.png and show only the stage from carrying to release.Limitations
The figure conveys the shape of motion but does not replace measuring trajectory and speed, as the README itself states. Sharpness of the final frame is limited by the source video. Final layout and PPTX export are done with tools available to the agent in the current environment, so output depends on the setup. The repository is built for Codex and describes no install path for other agents. The license is GPL-3.0. The last commit is dated September 2026.
How to disable. Delete the `visualize-uav-trajectory` folder from the Codex skills directory. Generated figures and manifests sit next to your data and are removed by hand.
FAQ
How do I install the skill into another project?
Ask Codex to install through `$skill-installer` from the `XXLiu-HNU/visualize_uav_trajectory` repository with the path `skills/visualize-uav-trajectory`. Then call the skill by name.
What do I get at the end?
An overlay at original resolution, a zoom-in on the trajectory end, a composite figure, a PPTX and files with settings for rerunning.
Can I adjust the result in words?
Yes. You can ask to keep the frame selection and strengthen the first shadows, equalize brightness or place the title on the photo. The agent rebuilds the figure and the PPTX.
Is a reference picture required?
No. Without one it is enough to describe which action to show. A reference is needed only to repeat a specific layout.
Is it suitable for a journal paper?
Yes, you can name the journal and column width, for example a two-column figure. PDF, SVG and TIFF files are added on request.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that renders images, SVGs and scripts as hand-drawn whiteboard videos, with 30 styles and narration
A skill that turns narration text into a 20-second chunky-pixel explainer at 1920×1080 with voice-over and an editable project.
A skill that turns a script into a finished video with voice-over, subtitles, a cover and a publish text, frames drawn by code.
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
README in short
The README is mostly in Chinese and covers the skill quick start, sample results and the old graphical interface. Manual workflow details live in separate documents.