Record Demo
libnativeapi/nativeapi
Record a demo video of a desktop app — launch it, play a scripted scenario with smooth synthetic mouse input, and capture the screen (cursor and click highlights included) straight to an…
FFmpeg 多媒体处理技能 — 将自然语言描述转为正确的 ffmpeg 命令,覆盖视频剪辑、转码、水印、合成、提取、生成等操作。内置一键安装脚本(Windows/Mac/Linux)。触发词:ffmpeg、视频剪辑、视频裁剪、视频转码、视频压缩、去水印、加水印、视频拼接、视频合成、提取音频、视频转…
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jiushiwon/wg-skills ffmpeg-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .claude/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.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/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .claude/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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 install https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skillType 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.
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jiushiwon/wg-skills ffmpeg-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .agents/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .agents/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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.
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jiushiwon/wg-skills ffmpeg-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .cursor/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .cursor/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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 https://github.com/jiushiwon/wg-skills.git --path vibeCoding/video/ffmpeg-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jiushiwon/wg-skills ffmpeg-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .gemini/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.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/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .gemini/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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.
$ gh skill install jiushiwon/wg-skills ffmpeg-skillInstalls 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).
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .github/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.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/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .github/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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.
$ npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jiushiwon/wg-skills ffmpeg-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiushiwon/wg-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vibeCoding/video/ffmpeg-skill .opencode/skills/ffmpeg-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ffmpeg-skill" agent skill from https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/video/ffmpeg-skill into .opencode/skills/ffmpeg-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-skill", 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.
ffmpeg-skillFFmpeg 多媒体处理技能 — 将自然语言描述转为正确的 ffmpeg 命令,覆盖视频剪辑、转码、水印、合成、提取、生成等操作。内置一键安装脚本(Windows/Mac/Linux)。触发词:ffmpeg、视频剪辑、视频裁剪、视频转码、视频压缩、去水印、加水印、视频拼接、视频合成、提取音频、视频转…
Ffmpeg Skill is an agent skill from jiushiwon/wg-skills. FFmpeg 多媒体处理技能 — 将自然语言描述转为正确的 ffmpeg 命令,覆盖视频剪辑、转码、水印、合成、提取、生成等操作。内置一键安装脚本(Windows/Mac/Linux)。触发词:ffmpeg、视频剪辑、视频裁剪、视频转码、视频压缩、去水印、加水印、视频拼接、视频合成、提取音频、视频转 GIF、截取视频帧、调整播放速度、画中画、批量处理视频、给视频加字幕、修改分辨率、音频替换、倍速播放、视频倒放。
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including scripts and reference files (for example `README.md`, `references/codec-guide.md` and `references/commands-audio.md`).
It sits in Media & Creative, covering Video production. It works with FFmpeg and Linux. The licence is Apache-2.0.
10 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 3569fb8. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (PowerShell and Shell), which the agent can run.
Shell commands in SKILL.md call:
ffmpegbashFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ffmpeg Skill loads about 1.4k tokens when it runs, and up to ~8.8k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 256 words of instructions outside code blocks.
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.
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.
The full file from jiushiwon/wg-skills at commit 3569fb8, republished under its Apache-2.0 licence (© jiushiwon). 256 words, ~1,352 tokens.
.claude/skills/ffmpeg-skill/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.FFmpeg 多媒体处理技能 — 把自然语言指令转成正确、安全的 ffmpeg 命令。
本 skill 是 FFmpeg 的命令翻译层:用户说"把视频压缩到 10MB 以内",输出对应的 ffmpeg 命令行并执行。skill 不捆绑 FFmpeg 本体,只提供安装脚本和命令模板。
| 操作域 | 说明 | 关键命令/滤镜 |
|---|---|---|
| 安装检测 | 自动检测 + 一键安装脚本 | scripts/install-ffmpeg.ps1 / .sh |
| 剪辑 | 裁剪、分割、调速、倒放 | -ss, -t, setpts, reverse |
| 转码 | 格式转换、压缩、分辨率、帧率 | -c:v, -crf, scale, -r |
| 去水印 | 模糊遮盖固定区域水印 | delogo |
| 加水印 | 图片水印、文字水印、动态水印 | overlay, drawtext |
| 合成 | 拼接、画中画、多轨混合 | concat, overlay, amix |
| 提取 | 抽帧、提取音频/字幕、视频转 GIF | -vn, -an, -map, fps |
| 音频 | 替换音轨、音量、混音、淡入淡出 | volume, atempo, amix, afade |
| 生成 | 图片序列→视频、单图+音频、测试画面 | -loop, -framerate |
Step 0: 检测 FFmpeg 是否安装
→ 已安装 → Step 1
→ 未安装 → 提供安装选项:
"FFmpeg 未安装,请选择安装方式:"
- 运行 scripts/install-ffmpeg.ps1 (Windows)
- 运行 scripts/install-ffmpeg.sh (Mac/Linux)
- 参考 references/install-guide.md 手动安装
→ 用户确认后执行安装,然后进入 Step 1
Step 1: 解析用户意图 → 匹配操作域
Step 2: 查 references/ 中对应命令模板,填充参数
Step 3: 构造完整命令 → 确认文件不会误覆盖
Step 4: 通过 Bash 执行 ffmpeg 命令
Step 5: 验证输出文件,报告结果用户:帮我把 video.mp4 右上角的水印去掉
AI:
1. 先定位水印:
ffmpeg -i "video.mp4" -vf "delogo=x=W-250:y=10:w=240:h=60:show=1" -t 5 preview.mp4
2. 用户确认位置后执行:
ffmpeg -i "video.mp4" -vf "delogo=x=W-250:y=10:w=240:h=60" -c:a copy output.mp4用户:把 demo.mp4 从第 30 秒开始,剪出 15 秒
AI:
ffmpeg -ss 00:00:30 -i "demo.mp4" -t 00:00:15 -c:v libx264 -c:a aac output.mp4用户:把这个视频压缩到小一点,最好 720p
AI:
ffmpeg -i "input.mp4" -vf "scale=1280:-1" -c:v libx264 -crf 23 -preset medium -c:a aac -b:a 128k output.mp4用户:把 part1.mp4、part2.mp4、part3.mp4 拼成一个视频
AI:
生成文件列表 filelist.txt → 执行:
ffmpeg -f concat -safe 0 -i filelist.txt -c copy output.mp4用户:把这个视频的声音单独导出来,要 MP3
AI:
ffmpeg -i "video.mp4" -vn -c:a libmp3lame -q:a 2 audio.mp3用户:把 video.mp4 的 5~8 秒转成 GIF
AI:
先创建调色板再生成 GIF(两步,保证画质)
ffmpeg -ss 00:00:05 -t 3 -i "video.mp4" -vf "fps=10,scale=480:-1:flags=lanczos,palettegen" palette.png
ffmpeg -ss 00:00:05 -t 3 -i "video.mp4" -i palette.png -vf "fps=10,scale=480:-1:flags=lanczos,paletteuse" output.gif用户:把视频调成 1.5 倍速
AI:
ffmpeg -i "input.mp4" -vf "setpts=0.6667*PTS" -af "atempo=1.5" output.mp4用户:把 main.mp4 作为主画面,pip.mp4 放在右下角小窗
AI:
ffmpeg -i "main.mp4" -i "pip.mp4" -filter_complex "[1:v]scale=iw/4:ih/4[pip];[0:v][pip]overlay=W-w-10:H-h-10" -c:a copy output.mp4ffmpeg -version 是否可执行-y 覆盖:所有命令默认加 -y,但在执行前确认不会误覆盖用户重要文件-ss 位置规则:-i 前 → 快速 seek,精度 ±关键帧间隔 → 适合粗略裁剪-i 后 → 精确到帧,但慢 → 适合精确裁剪-ss 放 -i 前 + 重编码(不 -c copy)= 又快又准-c copy 只能在关键帧位置切割,不能与滤镜同时使用-f concat),不用重编码# 在 ffmpeg-skill 目录下
powershell -ExecutionPolicy Bypass -File scripts/install-ffmpeg.ps1脚本逻辑:检测 ffmpeg → winget 安装 → 失败则从 gyan.dev 下载 → 询问是否添加 PATH。
# 在 ffmpeg-skill 目录下
bash scripts/install-ffmpeg.sh脚本逻辑:检测 ffmpeg → Mac 用 brew → Linux 检测包管理器(apt/dnf/pacman 等)→ 自动安装。
参考 references/install-guide.md。
| 错误现象 | 原因 | 解决 |
|---|---|---|
No such file or directory | 路径有空格未加引号 | 用双引号包裹路径 |
-ss 位置不精确 | 用了 -c copy 在非关键帧位置剪 | 去掉 -c copy 改为重编码 |
| GIF 色彩像浆糊 | 直接转未先建调色板 | 用两步流程(palettegen + paletteuse) |
concat 拼接失败 | 编码格式或分辨率不一致 | 先统一转码后再拼接,或用 concat filter |
| 字幕乱码 | 未指定中文字体 | 加 fontsdir 指向系统字体目录 |
hevc 编码器不可用 | FFmpeg 构建不含 libx265 | 改用 libx264 |
详细陷阱和解决方案见 references/gotchas.md。
| 技能 | 关系 |
|---|---|
image-forge-skill | 互补:image-forge 处理静态图片,ffmpeg-skill 处理视频/音频 |
workflow-diagram-skill | 无直接关联 |
icon-image-catch-skill | 可用于抓取水印素材图片 |
| 文件 | 内容 |
|---|---|
references/install-guide.md | 三平台手动安装指引 |
references/gotchas.md | 常见陷阱与最佳实践 |
references/codec-guide.md | 编码器与容器格式速查 |
references/filter-guide.md | 滤镜参数速查(scale/crop/delogo/overlay/drawtext) |
references/commands-trim.md | 剪辑类命令模板 |
references/commands-convert.md | 转码类命令模板 |
references/commands-watermark.md | 水印类命令模板 |
references/commands-compose.md | 合成类命令模板 |
references/commands-extract.md | 提取类命令模板 |
references/commands-generate.md | 生成类命令模板 |
references/commands-audio.md | 音频类命令模板 |
© jiushiwon, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 14 other files (scripts, references) in vibeCoding/video/ffmpeg-skill of jiushiwon/wg-skills.
Open the folder on GitHubat commit 3569fb8
Ffmpeg Skill 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ffmpeg Skill this skilljiushiwon/wg-skills | 112 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Record Demolibnativeapi/nativeapi | 161 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Env Setupwwwzhouhui/skills_collection | 282 | — | ~3.5k | Automated safety check: Notes | None | |
| Youtube DownloaderOpenMinis/MinisSkills | 444 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Video EditingLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.7k | Automated safety check: Notes | MIT | |
| Video Clipping ReferenceRightNow-AI/openfang | 18k | — | ~4.1k | Automated safety check: Warn | Apache-2.0 |
libnativeapi/nativeapi
Record a demo video of a desktop app — launch it, play a scripted scenario with smooth synthetic mouse input, and capture the screen (cursor and click highlights included) straight to an…
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…
OpenMinis/MinisSkills
Download YouTube videos or extract audio using yt-dlp + ffmpeg in the Linux shell.
LeoYeAI/openclaw-master-skills
Automated video editing skill for talk/vlog/standup videos. An agent skill from LeoYeAI/openclaw-master-skills.
RightNow-AI/openfang
Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.
LeoYeAI/openclaw-master-skills
This skill should be used when the user wants to compress a PowerPoint (.pptx) file by reducing the size of embedded videos and large images.
jiushiwon/wg-skills
A skill your agent uses when generating UI for a specific scenario (mobile/PC/官网/管理端/营销页/文档/金融/原生/3D), when refactoring an existing HTML/Vue/React project to a unified design system, when extracting…
jiushiwon/wg-skills
A skill your agent uses when 用户想用一句话生成流程图、工作流图解、开发流程图、AI 流程图或任何步骤型图解,支持多风格输出(flat icon / 暖白手账风 / dark / cute),并提供现成模板一键出图。
jiushiwon/wg-skills
This skill should be used when the user wants to create a standardized uni-app project for WeChat mini-program, H5, and App from scratch.
jiushiwon/wg-skills
FastAPI 项目一键初始化技能。面向零基础小白,提供环境探测、自动安装、完整 Web 骨架生成、SSE 流式框架、JWT 鉴权、统一响应封装、文件上传接口、一键启动/重启脚本、Swagger 文档,内置 MySQL(默认)/ PostgreSQL / MongoDB 数据库选择。用户只需说"帮我搭一个 FastAPI 项目"即可一条命令完成从零到跑的完整链路。触发词:"FastAPI…
jiushiwon/wg-skills
A skill your agent uses when designing or reviewing the request layer of a frontend project (web / uni-app / mini-program), including request.ts wrappers, interceptors, deduplication, mocks, error…
jiushiwon/wg-skills
This skill should be used when the user wants to create a standardized React 18 + TypeScript + Vite + Zustand project from scratch.
Categories
FFmpeg 多媒体处理技能 — 将自然语言描述转为正确的 ffmpeg 命令,覆盖视频剪辑、转码、水印、合成、提取、生成等操作。内置一键安装脚本(Windows/Mac/Linux)。触发词:ffmpeg、视频剪辑、视频裁剪、视频转码、视频压缩、去水印、加水印、视频拼接、视频合成、提取音频、视频转…. Ffmpeg Skill is an agent skill from jiushiwon/wg-skills.
Ffmpeg Skill fits situations like: tasks that involve Video production.
Run `npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a claude-code`. Or copy the skill folder (vibeCoding/video/ffmpeg-skill in jiushiwon/wg-skills) into .claude/skills/ffmpeg-skill in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a codex`. Or copy the skill folder (vibeCoding/video/ffmpeg-skill in jiushiwon/wg-skills) into .agents/skills/ffmpeg-skill in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jiushiwon/wg-skills --skill ffmpeg-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ffmpeg-skill, .gemini/skills/ffmpeg-skill, .github/skills/ffmpeg-skill and .opencode/skills/ffmpeg-skill in your project.
Going by SKILL.md and its folder, Ffmpeg Skill needs PowerShell and a shell for the scripts in its folder and the command-line tools its instructions call (ffmpeg and bash). Our summary lists: A Bash shell; PowerShell.
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.
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.
Ffmpeg Skill is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.4k 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 7.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Ffmpeg Skill: Record Demo (libnativeapi/nativeapi, 161 stars), Env Setup (wwwzhouhui/skills_collection, 282 stars), Youtube Downloader (OpenMinis/MinisSkills, 444 stars) and Video Editing (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jiushiwon (a GitHub user) maintains it in jiushiwon/wg-skills, which has 112 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.
Source: jiushiwon/wg-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.