메뉴
Download videos from YouTube and 1000+ other sites using yt-dlp
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Decide whether a task in the current project is worth running as an agent loop. Analyzes the repo for evidence first (tests/CI/bench scripts = available verifiers; issue+PR queues = recurring work; module boundaries), then interviews the user one question at a time on the genuine decisions, and returns one of three verdicts — don't loop (stay in the loop yourself), timer loop (/loop, /schedule), or goal loop (/goal) — with cited evidence and, when looping is warranted, a drafted four-part contract (goal / verification / boundary / stop) bound to real commands found in the repo. Recommending NO loop is a first-class outcome. Use when the user asks 值不值得 loop / should I loop this / 要不要上 /goal / 这个活能不能挂个循环自动跑, or wants to apply loop engineering to a project.
GitHub backlog governance manager-loop. Triage open issues (type + routing labels), complete thin descriptions, maintain a bounded ready queue (Todo ≤ 5) on a GitHub Projects board, and repair board drift (closed issue still "In Progress" etc.). Config-driven — reads .claude/backlog-manager.yaml from the target repo; runs an init flow to generate it if missing. DRY-RUN by default, pass "apply" to execute writes. Use for recurring backlog grooming / issue triage of any GitHub repo, standalone or driven by /loop. Requires gh CLI with repo + project scopes.
Generate images (Nano Banana Pro / Imagen) and videos (Veo 3.1) through Google Flow using the account's Ultra/Pro SUBSCRIPTION credits instead of the metered Gemini/Vertex API — no per-call API cost. Use when the user wants to create a thumbnail, cover, poster, b-roll clip, image, or short video with AI and wants to avoid API billing, or explicitly mentions Flow / gflow / Veo / Nano Banana via subscription. Wraps the gflow-cli tool; encodes this machine's Flow new-UI quirk (PREFER_CLASSIC) and credit-safe retry rules learned the hard way. NOT for the paid Gemini-API nano-banana-pro path (that costs money) — this is the subscription path.
Generate a printer-receipt styled PNG bill of AI token usage and cost from local ccusage data, for the 绿皮火车 channel. Use when the user wants a token usage "账单"/"小票"/"收银台"/receipt/invoice, a shareable spend breakdown by model / input / output / cached / by day, or 节目素材 about token 消耗/花费. Triggers on "生成账单", "token 收据", "做张小票", "用量账单", "token receipt", "spend breakdown image".
本地把音频/视频文件或在线视频 URL 转录成文字稿(txt/srt/vtt/json)。基于 Apple Silicon 上的 mlx_whisper,支持中英文等多语言、自动语言检测、模型规格选择。当用户想要"转录""生成字幕/文稿/transcript""把这段音频/视频转成文字""提取台词""做 SRT 字幕",或给出一个音视频文件/YouTube 等链接要文字内容时使用。
Jordan Peterson(乔丹·彼得森,「龙虾教授」)的思维框架与表达方式。基于著作、长访谈/辩论 transcript、X发帖、外部批评、决策记录、完整时间线共6维度216个来源(一手占比约48%)的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA,并内置其已被外部验证的失效模式标注。 用途:作为思维顾问,用彼得森的视角分析个人困境、意义危机、责任与成长、文化争议、叙事与神话。 当用户提到「用彼得森的视角」「Jordan Peterson会怎么看」「彼得森」「皮特森」「龙虾教授」「JP模式」「JBP」 「peterson perspective」「人生十二法则」「12条法则」时使用。 即使用户只是说「整理好你的房间」「混乱与秩序」「先承担责任」 「帮我用彼得森的角度想想」「切换到彼得森」也应触发。 用户讨论「躺平」「内卷」「精神内耗」「年轻人迷茫」「人生没有意义」等话题且明确想要某种视角分析或建议时也可触发。 不要在用户只是泛泛倾诉、求安慰、查心理学概念,或寻求真实医疗/心理咨询时触发—— 这是思维框架skill,不是心理治疗。
| name | youtube-downloader |
| description | Download videos from YouTube and 1000+ other sites using yt-dlp |
Download videos from YouTube and 1000+ other sites using yt-dlp.
A powerful video downloader skill based on yt-dlp that supports YouTube, Bilibili, Twitter/X, TikTok, and many other platforms. Features include format selection, audio extraction, subtitle download, playlist support, and metadata preservation.
Use this skill when users:
python scripts/download_video.py "VIDEO_URL" [OPTIONS]
Download single video (best quality):
python scripts/download_video.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
Download video in specific quality:
python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" -f 1080
Extract audio only (MP3):
python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" --audio-only
Download with subtitles:
python scripts/download_video.py "https://www.youtube.com/watch?v=VIDEO_ID" --subtitles
Download playlist:
python scripts/download_video.py "https://www.youtube.com/playlist?list=PLAYLIST_ID" --playlist
Download N videos from playlist:
python scripts/download_video.py "https://www.youtube.com/playlist?list=PLAYLIST_ID" --playlist -n 5
Specify output directory:
python scripts/download_video.py "URL" -o /path/to/output
| Argument | Description | Default |
|---|---|---|
url | Video/Playlist URL (required) | - |
-o, --output | Output directory | Current directory |
-f, --format | Video quality: best, 1080, 720, 480, 360 | best |
--audio-only | Extract audio only (MP3) | False |
--subtitles | Download subtitles | False |
--sub-lang | Subtitle language(s) | en,zh-Hans |
--playlist | Enable playlist download | False |
-n, --count | Number of videos from playlist | All |
--metadata | Save video metadata JSON | True |
--thumbnail | Download thumbnail | False |
--cookies | Path to cookies file (for age-restricted content) | None |
# Install yt-dlp
pip install yt-dlp --break-system-packages
# For audio extraction (optional)
# macOS
brew install ffmpeg
# Ubuntu/Debian
apt-get install ffmpeg
OutputDir/
├── Video Title [VIDEO_ID].mp4 # Video file
├── Video Title [VIDEO_ID].json # Metadata (if --metadata)
├── Video Title [VIDEO_ID].jpg # Thumbnail (if --thumbnail)
└── Video Title [VIDEO_ID].en.vtt # Subtitles (if --subtitles)
OutputDir/
└── PlaylistName/
├── playlist_info.json
├── 001 - Video Title.mp4
├── 001 - Video Title.json
├── 002 - Another Video.mp4
└── ...
{
"title": "Video Title",
"uploader": "Channel Name",
"upload_date": "2024-01-15",
"duration": 300,
"view_count": 1000000,
"description": "Video description...",
"tags": ["tag1", "tag2"],
"video_file": "Video Title [VIDEO_ID].mp4"
}
When user requests video download:
Read skill documentation:
view("/mnt/skills/user/youtube-downloader/SKILL.md")
Install dependencies (if needed):
pip install yt-dlp --break-system-packages
Execute download:
python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
"USER_URL" -o /mnt/user-data/outputs
Present files to user:
present_files(["/mnt/user-data/outputs/..."])
yt-dlp supports 1000+ sites. Run yt-dlp --list-extractors for full list.
Q: Age-restricted videos?
A: Use --cookies with exported browser cookies: --cookies cookies.txt
Q: Format not available? A: Some videos may not have all quality options. Script will auto-select best available.
Q: Download speed slow? A: This is usually server-side throttling. Consider using a VPN or waiting.
Q: Need to login for private videos?
A: Export cookies from your browser after logging in, then use --cookies.
Q: Audio extraction fails?
A: Install ffmpeg: brew install ffmpeg (macOS) or apt install ffmpeg (Linux)
User: "帮我下载这个 YouTube 视频: https://www.youtube.com/watch?v=dQw4w9WgXcQ"
Claude:
# Install yt-dlp
pip install yt-dlp --break-system-packages
# Download video
python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
"https://www.youtube.com/watch?v=dQw4w9WgXcQ" \
-o /mnt/user-data/outputs
# Present files
present_files([...])
User: "下载这个 YouTube 视频的音频，我只要 MP3"
Claude:
python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
"VIDEO_URL" \
--audio-only \
-o /mnt/user-data/outputs
User: "Download this playlist, but only the first 5 videos"
Claude:
python /mnt/skills/user/youtube-downloader/scripts/download_video.py \
"PLAYLIST_URL" \
--playlist -n 5 \
-o /mnt/user-data/outputs
This skill wraps yt-dlp with sensible defaults:
This tool is for personal use only. Please respect:
Only download content you have the right to access. Do not redistribute copyrighted material.
v1.0 (Current)