Agent skill

UAV Trajectory Overlay from Video

by XXLiu-HNU in XXLiu-HNU/visualize_uav_trajectory

Composites several moments from real drone footage into one still with ghost trails, then lays out paper figures and an editable PowerPoint file.

GPL-3.0Auto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install UAV Trajectory Overlay from Video

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/visualize-uav-trajectory .claude/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .claude/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/visualize-uav-trajectory .agents/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .agents/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/visualize-uav-trajectory .cursor/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .cursor/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/XXLiu-HNU/visualize_uav_trajectory.git --path skills/visualize-uav-trajectory

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/visualize-uav-trajectory .gemini/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .gemini/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/visualize-uav-trajectory .github/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .github/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install XXLiu-HNU/visualize_uav_trajectory visualize-uav-trajectory --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XXLiu-HNU/visualize_uav_trajectory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/visualize-uav-trajectory .opencode/skills/visualize-uav-trajectory && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "visualize-uav-trajectory" agent skill from https://github.com/XXLiu-HNU/visualize_uav_trajectory/tree/main/skills/visualize-uav-trajectory into .opencode/skills/visualize-uav-trajectory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualize-uav-trajectory", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: visualize-uav-trajectory
GitHub stars: 242
Token cost: ~535 tokens
SKILL.md length: 68 words
Files: 5 (incl. scripts, references)
Skills in repo: 1
Repo updated: Sep 26, 2026
First seen: Oct 7, 2026
Licence: GPL-3.0

At a glance

Composites several moments from real drone footage into one still with ghost trails, then lays out paper figures and an editable PowerPoint file.

Works in 6 steps: 检查输入。… → 选择方法。固定镜头、静止背景的快速预览可用原仓库… → 选真实帧。… → …
Illustrating a drone transport, grasp, placement or release with ghosted frames
SKILL.md covers 工作流, 命令入口 and 证据边界
Runs Python scripts from its folder; calls python

What it does

This skill builds chronophotography images from real drone video: several moments from one clip are layered onto a single background frame, with the source pixels, timestamps and masks kept so the result can be checked and reproduced. Frames are chosen again for every video rather than reused from other experiments. The script scripts/video_chronophoto.py offers inspect and render commands and needs Python that can import cv2 and numpy.

The workflow starts with a timed contact sheet and asks you a question only when the scope, such as the full flight or transport to release, would change the picture. A quick preview can use the original repository's legacy method for a fixed camera and still background, while the skill's keyframe masking suits swaying curtains, people, shadows and slow hovering. Failed automatic masks are repaired with added or excluded regions or hand-drawn outlines, and each frame is reviewed through mask_audit.jpg and terminal.png.

Default deliverables are an unannotated PNG at original resolution, a laid-out figure, a small preview, an editable .pptx, the config, a manifest and the reproduction commands, plus PDF, SVG or TIFF and English captions for papers. The skill is strict about evidence: it never draws or moves drones, payloads or paths, uneven ghost spacing is not a speed comparison, and metric trajectories need calibration or logs.

When your agent uses it

Illustrating a drone transport, grasp, placement or release with ghosted frames
Making a paper figure from real experiment footage
Producing an editable PowerPoint version of a trajectory overlay figure
Checking mask quality frame by frame before an overlay goes into a paper

Example prompts

“Make a chronophotography figure from flight.mp4 showing the payload release.”
“Overlay the drone positions at three moments from ./videos/grasp.mp4 on the first frame and lay it out as a paper figure.”
“Build the editable PPTX for the trajectory overlay, with the zoom inset as its own object.”

Requirements

Python with opencv (cv2) and numpy
A real video of the drone experiment

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

检查输入。读取参考图及视频元数据，导出带时间的联系表并实际查看。先明确用户要全流程、运输至释放或末端局部；已有选择直接沿用。仅在范围会改变出图时提一个问题，期间继续检查素材。
选择方法。固定镜头、静止背景的快速预览可用原仓库 legacy。摆动窗帘、人物、阴影、慢速悬停、需要清晰末端帧时，用本 skill 的关键帧局部蒙版。原仓库 improved…
选真实帧。粗略扫片后细看动作附近。选择能看清释放/放置的背景帧，并按空间间距选择较早机影，减少悬停重叠。把箱体、夹爪、分离载荷一起考虑。记录请求时间和实际解码帧编号；背景帧不等于精确释放时刻。
保存配置并合成。使用脚本与配置说明。原图像素选框，框内归一化多边形。自动分割失败时先检查原裁剪：漏载荷用补充蒙版，带入背景用排除蒙版，复杂帧用人工轮廓覆盖。保留分离部件，不只留下最大连通域。在最终排版尺寸下确认最早机影仍可辨认，必要时提高不透明度下限，不机械套用脚本默认值；…
逐帧审核。打开 mask_audit.jpg、terminal.png 和最终图，核对螺旋桨、夹爪、载荷、窗帘/网格/障碍物误入及机影间距。验证尺寸、背景区域一致性和真实帧来源。若局部反复失败，回看原裁剪并直接修正该帧轮廓或更换关键帧，避免反复全片调阈值。
排版与交付。阅读最终排版与可编辑 PPTX。默认交付原分辨率无标注 PNG、排版图、小预览、可编辑 .pptx、配置、manifest及复现命令；用户明确限定格式时按其要求缩小输出范围。论文图按目标版式增加 PDF/SVG/TIFF 与英文图注。PPT…

What it can do on your machine

Read from SKILL.md and the folder at commit cb8797b. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UAV Trajectory Overlay from Video loads about 535 tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 68 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~75
When it runs · the whole SKILL.md, loaded when a task matches: ~535
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from XXLiu-HNU/visualize_uav_trajectory at commit cb8797b, republished under its GPL-3.0 licence (© XXLiu-HNU). 68 words, ~535 tokens.

Download SKILL.mdSave it as .claude/skills/visualize-uav-trajectory/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: visualize-uav-trajectory
description: Create UAV/drone video trajectory overlays, chronophotography, 渐变残影 and 实物实验轨迹叠影 from real footage, with paper figure layouts and editable PPTX output. Use for transport, grasping, placement and release illustrations, not metric ROS bag/CSV plots or fictional flight imagery.

UAV video chronophotography

把真实视频中的多个时刻叠到一张实景图里。保留源像素、时间和蒙版，便于核对与复现；根据每段视频重新选帧，不沿用其他实验的坐标。

工作流

检查输入。 读取参考图及视频元数据，导出带时间的联系表并实际查看。先明确用户要全流程、运输至释放或末端局部；已有选择直接沿用。仅在范围会改变出图时提一个问题，期间继续检查素材。
选择方法。 固定镜头、静止背景的快速预览可用原仓库 legacy。摆动窗帘、人物、阴影、慢速悬停、需要清晰末端帧时，用本 skill 的关键帧局部蒙版。原仓库 improved 有颜色、左侧起始及向右单调运动假设，不能当成任意方向的真实跟踪；它会缓存片段全部帧，长4K片段不要直接套用。镜头移动明显时，先配准并核查静态地标，或选稳定片段；本脚本不自动稳像。
选真实帧。 粗略扫片后细看动作附近。选择能看清释放/放置的背景帧，并按空间间距选择较早机影，减少悬停重叠。把箱体、夹爪、分离载荷一起考虑。记录请求时间和实际解码帧编号；背景帧不等于精确释放时刻。
保存配置并合成。 使用脚本与配置说明。原图像素选框，框内归一化多边形。自动分割失败时先检查原裁剪：漏载荷用补充蒙版，带入背景用排除蒙版，复杂帧用人工轮廓覆盖。保留分离部件，不只留下最大连通域。在最终排版尺寸下确认最早机影仍可辨认，必要时提高不透明度下限，不机械套用脚本默认值；轮廓属于人工辅助，不宣称全自动识别。
逐帧审核。 打开 mask_audit.jpg、terminal.png 和最终图，核对螺旋桨、夹爪、载荷、窗帘/网格/障碍物误入及机影间距。验证尺寸、背景区域一致性和真实帧来源。若局部反复失败，回看原裁剪并直接修正该帧轮廓或更换关键帧，避免反复全片调阈值。
排版与交付。 阅读最终排版与可编辑 PPTX。默认交付原分辨率无标注 PNG、排版图、小预览、可编辑 .pptx、配置、manifest及复现命令；用户明确限定格式时按其要求缩小输出范围。论文图按目标版式增加 PDF/SVG/TIFF 与英文图注。PPT 中标题、主图和末端放大必须是独立可编辑对象；不能只把整张合图贴进幻灯片就称为可编辑版。局部放大从真实源帧裁剪，保留无标注原图并披露编辑范围和残余抠图问题。

命令入口

<skill-dir> 是当前 SKILL.md 所在目录，无需原仓库在场。使用能导入 cv2 和 numpy 的 Python；缺依赖时在项目虚拟环境安装 opencv-python-headless numpy。

bash

python "<skill-dir>/scripts/video_chronophoto.py" inspect \
  --video flight.mp4 --times 0,10,20 --output output/inspection
python "<skill-dir>/scripts/video_chronophoto.py" render \
  --video flight.mp4 --config keyframes.json --output output/render

先用 --help 核对选项。联系表仅用于定位；绘制蒙版时查看对应原帧，不把缩略图坐标当作原图坐标。此脚本负责叠影与审核材料，不直接生成 PPTX。最终排版和 PPTX 由助手使用当前环境可用的图片、演示文稿工具完成；不得把 PNG 改扩展名作为 PPTX。

证据边界

使用原始画面进行可解释的合成；不生成、移动或补画无人机、载荷、飞行路径来冒充观测结果。
非等间隔机影不能直接比较速度。米制轨迹、速度和命中精度需要额外标定/日志；仅凭文件名不推断任务成功。
示例尺寸、帧率、时间、任务名称和取框均不是默认实验参数。多个视频分别出配置。
对于可变帧率视频，脚本的秒数换算是名义 FPS 近似；需要精确事件时序时另查原始 PTS，不把近似值写成测量真值。

Files

SKILL.md and 4 other files (scripts, references) in skills/visualize-uav-trajectory of XXLiu-HNU/visualize_uav_trajectory.

SKILL.md
agents/openai.yaml
references/publication.md
references/rendering.md
scripts/video_chronophoto.py

Open the folder on GitHubat commit cb8797b

Compare with similar skills

UAV Trajectory Overlay from Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

UAV Trajectory Overlay from Video compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
UAV Trajectory Overlay from Video this skillXXLiu-HNU/visualize_uav_trajectory	242	—	~535	Automated safety check: Pass	GPL-3.0	14 days ago
AI Image PowerPoint Generatorbytedance/deer-flow	84k	4 repos	~7.1k	Automated safety check: Pass	MIT	today
Academic Paper to PPTXYuan1z0825/nature-skills	47k	—	~1.1k	Automated safety check: Pass	Apache-2.0	today
SenseNova Image Base ToolsOpenSenseNova/SenseNova-Skills	5.7k	—	~3.2k	Automated safety check: Pass	MIT	2 days ago
Env Setupwwwzhouhui/skills_collection	283	—	~3.5k	Automated safety check: Notes	None	5 days ago
Nature Paper2pptCitrus-bit/Anaxa	120	1 repos	~5.9k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

AI Image PowerPoint Generator
bytedance/deer-flow
Creates a PowerPoint deck by planning the slide structure, generating one AI image per slide in a chosen visual style, and assembling the images into a PPTX file.
84k GitHub starsUsed in 4 repos~7.1k tokens
Documents & OfficeAuto-check passed
Academic Paper to PPTX
Yuan1z0825/nature-skills
Creates or revises a Chinese-language academic PPTX deck from a scientific paper or reading notes, reusing the paper's figures and adding speaker notes.
47k GitHub stars~1.1k tokensUpdated today
Documents & OfficeAuto-check passed
SenseNova Image Base Tools
OpenSenseNova/SenseNova-Skills
Low-level SenseNova tools for image generation, image editing, image recognition with a VLM and text optimization with an LLM, meant to be called by higher-level skills rather than directly.
5.7k GitHub stars~3.2k tokensUpdated 2 days ago
Media & CreativeAuto-check passed
Env Setup
wwwzhouhui/skills_collection
Checking and provisioning the machine's environment for the video-agent-kit plugin — probing for ffmpeg/ffprobe that actually carry the encoders and filters we render with (libx264/aac/libmp3lame…
283 GitHub stars~3.5k tokensUpdated 5 days ago
Media & CreativeAuto-check: notes
Nature Paper2ppt
Citrus-bit/Anaxa
Build a complete but efficient Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes.
120 GitHub starsUsed in 1 repo~5.9k tokens
Documents & OfficeAuto-check passed
Beamer Deck
flonat/flonat-research
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme.
146 GitHub stars~3.2k tokensUpdated 11 days ago
Documents & OfficeAuto-check passed

Works with

Questions about UAV Trajectory Overlay from Video

What does UAV Trajectory Overlay from Video do?

Composites several moments from real drone footage into one still with ghost trails, then lays out paper figures and an editable PowerPoint file. This skill builds chronophotography images from real drone video: several moments from one clip are layered onto a single background frame, with the source pixels, timestamps and masks kept so the result can be checked and reproduced. Frames are chosen again for every video rather than reused from other experiments.

When should I use UAV Trajectory Overlay from Video?

UAV Trajectory Overlay from Video fits situations like: illustrating a drone transport, grasp, placement or release with ghosted frames; making a paper figure from real experiment footage; producing an editable PowerPoint version of a trajectory overlay figure; checking mask quality frame by frame before an overlay goes into a paper.

How do I install UAV Trajectory Overlay from Video in Claude Code?

Run `npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a claude-code`. Or copy the skill folder (skills/visualize-uav-trajectory in XXLiu-HNU/visualize_uav_trajectory) into .claude/skills/visualize-uav-trajectory in your project. Claude Code loads it when a task matches its description.

How do I install UAV Trajectory Overlay from Video in Codex?

Run `npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a codex`. Or copy the skill folder (skills/visualize-uav-trajectory in XXLiu-HNU/visualize_uav_trajectory) into .agents/skills/visualize-uav-trajectory in your project. Codex loads it when a task matches its description.

Can I use UAV Trajectory Overlay from Video in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add XXLiu-HNU/visualize_uav_trajectory --skill visualize-uav-trajectory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visualize-uav-trajectory, .gemini/skills/visualize-uav-trajectory, .github/skills/visualize-uav-trajectory and .opencode/skills/visualize-uav-trajectory in your project.

What does UAV Trajectory Overlay from Video need to run?

Going by SKILL.md and its folder, UAV Trajectory Overlay from Video needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python with opencv (cv2) and numpy; A real video of the drone experiment.

Does UAV Trajectory Overlay from Video access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is UAV Trajectory Overlay from Video safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does UAV Trajectory Overlay from Video use?

UAV Trajectory Overlay from Video is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does UAV Trajectory Overlay from Video use?

About 535 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.

What are the alternatives to UAV Trajectory Overlay from Video?

Skills that share tags, products or a category with UAV Trajectory Overlay from Video: AI Image PowerPoint Generator (bytedance/deer-flow, 84k stars), Academic Paper to PPTX (Yuan1z0825/nature-skills, 47k stars), SenseNova Image Base Tools (OpenSenseNova/SenseNova-Skills, 5.7k stars) and Env Setup (wwwzhouhui/skills_collection, 283 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UAV Trajectory Overlay from Video?

XXLiu-HNU (a GitHub user) maintains it in XXLiu-HNU/visualize_uav_trajectory, which has 242 GitHub stars. The repository was last updated on September 26, 2026.

Source: XXLiu-HNU/visualize_uav_trajectory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install UAV Trajectory Overlay from Video

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

UAV video chronophotography

工作流

命令入口

证据边界

Files

Compare with similar skills

Similar skills

AI Image PowerPoint Generator

Academic Paper to PPTX

SenseNova Image Base Tools

Env Setup

Nature Paper2ppt

Beamer Deck

Related

Questions about UAV Trajectory Overlay from Video