ワンクリックで
yt-dlp
Download videos, extract audio, or fetch metadata from YouTube, Twitter/X, Instagram, TikTok, and many more sites.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Download videos, extract audio, or fetch metadata from YouTube, Twitter/X, Instagram, TikTok, and many more sites.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Bounded auto-iteration for a prompt with explicit stop predicates.
Memory hygiene workflow to classify, deduplicate, and promote durable knowledge across local memory layers.
Bounded simplification pass for a file or hunk that preserves behavior while reducing complexity.
Turn a repeatable workflow into a reusable local SKILL.md with explicit steps, criteria, and safe defaults.
Bounded auto-debug loop for failing build/test commands with evidence-first diagnosis.
Safely update Nexo config files with read-before-write merges, schema-aware mapping, and reload/restart awareness.
| name | yt-dlp |
| description | Download videos, extract audio, or fetch metadata from YouTube, Twitter/X, Instagram, TikTok, and many more sites. |
| requires | {"bins":["yt-dlp"],"env":[]} |
Wraps the yt-dlp CLI. Use for metadata extraction, format listing, and
(gated) downloads to local disk.
openai-whisper for transcription (download audio → whisper)summarize with video metadata + captionsstatus — yt-dlp binary version + output dirinfo — url → title, duration, channel, upload date, webpage URLformats — url → list of available formats (id, ext, resolution, codecs, size)download — url + optional mode (video default / audio), format (yt-dlp -f selector),
audio_format (mp3 default / m4a / opus), output_dirdownload requires YTDLP_ALLOW_DOWNLOAD=true. Without it, returns -32041.
| Var | Default |
|---|---|
YTDLP_BIN | yt-dlp |
YTDLP_OUTPUT_DIR | $TMPDIR/agent-yt-dlp |
YTDLP_ALLOW_DOWNLOAD | — (must be true to download) |
info to confirm the URL is valid and preview title/duration.download with mode=audio for podcast-style content, then feed the
output_path into openai-whisper → summarize.