article-optimizer
Use when the user wants to improve a specific article under a fixed viral-scoring rubric, iterate on one article to raise its score, or run single-article…
Use when the user wants to download or inspect online audio/video directly with the installed `yt-dlp` CLI. Best for single videos, playlists, audio extraction, subtitle download, format inspection, output templates, cookies-from-browser flows, and practical troubleshooting of
$ npx -y skills add xiaomoBoy/claude-writing-skills --skill yt-dlp-direct --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/yt-dlp-directContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user wants to download or inspect online audio/video directly with the installed `yt-dlp` CLI. Best for single videos, playlists, audio extraction, subtitle download, format inspection, output templates, cookies-from-browser flows, and practical troubleshooting of
name: yt-dlp-direct description: Use when the user wants to download or inspect online audio/video directly with the installed `yt-dlp` CLI. Best for single videos, playlists, audio extraction, subtitle download, format inspection, output templates, cookies-from-browser flows, and practical troubleshooting of `yt-dlp` commands.
这个 skill 只负责一件事:
不负责:
一句话原则:如果用户要下载、提音频、拿字幕、看格式、抓播放列表,优先直接用 `yt-dlp`,不要先写一堆脚本。
适用场景:
不适用场景:
开始前先确认:
1. `yt-dlp` 在 PATH 中 2. 当前目录或目标目录可写 3. 如果任务涉及合并视频音频、转码、嵌入缩略图,最好已有 `ffmpeg`
优先检查:
which yt-dlp yt-dlp --version
如需判断 `ffmpeg` 是否可用,可再看:
ffmpeg -version ffprobe -version
先判断链接能不能被 extractor 识别:
yt-dlp --simulate --print "%(title)s" "<url>"
如果只是想看元信息而不下载:
yt-dlp --dump-single-json "<url>"
当用户要指定清晰度、编码、音轨,先看格式:
yt-dlp -F "<url>"
如果用户没明确要求,通常优先:
yt-dlp -f "bv*+ba/b" "<url>"
这也是 yt-dlp 当前默认偏好的组合思路。
默认建议带输出模板:
yt-dlp -o "%(title)s [%(id)s].%(ext)s" "<url>"
如果需要固定目录:
yt-dlp -P "/target/dir" -o "%(title)s [%(id)s].%(ext)s" "<url>"
用户要音频时,优先:
yt-dlp -x --audio-format mp3 "<url>"
更保守地保留高质量音频格式时:
yt-dlp -x --audio-format m4a "<url>"
只下字幕,不下视频:
yt-dlp --write-subs --write-auto-subs --skip-download "<url>"
如果用户只要特定语言:
yt-dlp --write-subs --sub-langs "en,zh-Hans,zh-Hant" --skip-download "<url>"
用户给 playlist 时,先提醒量级。常用命令:
yt-dlp --flat-playlist "<playlist-url>" yt-dlp -I 1:10 "<playlist-url>" yt-dlp -o "%(playlist_index)s - %(title)s [%(id)s].%(ext)s" "<playlist-url>"
先用 `--flat-playlist` 看条目,再决定是否全下。
如果用户只有关键词,没有直接链接,可以用搜索前缀:
yt-dlp "ytsearch5:Claude Code skills"
只拿结果,不立即下载时:
yt-dlp --simulate --print "%(title)s | %(webpage_url)s" "ytsearch5:Claude Code skills"
很多站点或私有内容需要登录态。优先顺序:
1. `--cookies-from-browser` 2. `--cookies <file>` 3. 用户名/密码或 netrc
高频用法:
yt-dlp --cookies-from-browser chrome "<url>" yt-dlp --cookies-from-browser safari "<url>" yt-dlp --cookies cookies.txt "<url>"
如果站点要求浏览器指纹或 TLS 模拟,可考虑:
yt-dlp --impersonate chrome "<url>"
默认模板建议:
%(title)s [%(id)s].%(ext)s
播放列表常用:
%(playlist_index)s - %(title)s [%(id)s].%(ext)s
按上传者归档:
%(uploader)s/%(upload_date>%Y-%m-%d)s - %(title)s [%(id)s].%(ext)s
常见例子:
yt-dlp -S "res:1080,ext:mp4:m4a" "<url>" yt-dlp --remux-video mp4 "<url>" yt-dlp --embed-thumbnail --add-metadata "<url>"
`yt-dlp` 支持站点很多,但“列在清单里”不等于今天一定能用。
判断顺序:
1. 先尝试 `--simulate` 2. 再看报错是否为登录、区域、格式、站点变更 3. 真要确认 extractor 名称,再看支持站点清单
需要时读取:
执行后,回复里至少说明:
1. 跑了什么命令 2. 是探测成功、格式已列出,还是实际已下载 3. 文件落在哪里 4. 如果失败,卡在 extractor、认证、格式、网络,还是本地依赖
先看版本:
yt-dlp --version
如果太旧,提醒用户更新。
优先检查:
ffmpeg -version
优先试:
yt-dlp --cookies-from-browser <browser> "<url>"
先加详细日志:
yt-dlp -v "<url>"
先用:
yt-dlp --flat-playlist "<url>"
A toolkit of Claude Code skills for long-form content creators — research, score, rewrite, and publish, end to end. 中文版: README.zh-CN.md 5 skills extracted from a real working writing setup. They are opinionated, narrow in scope, and meant to compose.
Use when the user wants to improve a specific article under a fixed viral-scoring rubric, iterate on one article to raise its score, or run single-article…
Use when the user has a finished blog master draft and wants to publish it to multiple content platforms (知乎/掘金/CSDN/公众号 等) via the @wechatsync/cli tool.…
Use when the user wants to collect research material for an article or topic by gathering YouTube videos and web articles into a NotebookLM notebook, then…
Use when the user wants to iterate on a viral-article scoring system itself, calibrate or improve a scoring prompt against labeled samples, or run batch…