AGENT SKILL

download-media

Download video, audio, playlists, clips or subtitles from a supported URL using yt-dlp. Use when the user wants media files on disk; use MarkItDown for text extraction and the loop skills for local loop editing.

License 许可
MIT
最近更新
2026-11-11
Stars
★ 5
Forks
0

01 前言 Front Matter

name
download-media
license
MIT
metadata
{ "author": "coroboros", "sources": "github.com/yt-dlp/yt-dlp" }
description
Download video, audio, playlists, clips or subtitles from a supported URL using yt-dlp. Use when the user wants media files on disk; use MarkItDown for text extraction and the loop skills for local loop editing.
when_to_use
When the user has a media URL and wants the file on disk — video, audio-only, playlist, clip, or subtitles. Keywords — download video, yt-dlp, youtube, save video, extract audio, mp3, rip, playlist, clip, subtitles, 1080p. Skip when the user wants the transcript or text content (/markitdown), wants to loop or re-encode a local file (/video-loop, /audio-loop), or targets DRM-protected streaming services (Netflix, Disney+, Spotify…) — yt-dlp does not bypass DRM and neither does this skill.
allowed-tools
Bash(bash *) Bash(yt-dlp *) Bash(command *) Read
argument-hint
[-a] [-b] [-p] [-i] [-c A-B] [-u langs] [-r height] [-d dir] <url> [yt-dlp args]
compatibility
Requires bash and an installed yt-dlp CLI. FFmpeg is required for audio extraction, clipping and applicable merges; some extractors require additional documented runtimes or authentication.

02 资源文件 1

03 SKILL.md 正文

Download Media

Download video or audio from any yt-dlp-supported site using the yt-dlp CLI. The skill validates the input, composes the right flags for the intent, downloads under ~/.agents/output/<project>/download-media/<slug>/ (or a -d destination), and reports the final file paths — fully expanded, no tilde, no magic.

The deterministic work — install checks, slug derivation, destination, flag composition, final-path capture — happens in scripts/download-media.sh. The skill parses $ARGUMENTS, hands them to the script, and turns the script's RESULT: lines into a human report.

Scope

Personal and authorized use: public content, the user's own uploads, Creative Commons and licensed material. yt-dlp cannot bypass DRM and this skill never attempts to; decline requests to rip paid streaming catalogs (Netflix, Disney+, Spotify…) or to evade a site's paywall. Downloading may still be restricted by a site's terms of service and local copyright law — when a request is plainly about piracy, say so and stop.

Install

brew install yt-dlp        # macOS
pipx install yt-dlp        # any platform
brew install ffmpeg        # strongly recommended — merging, mp3 extraction, clipping

Binaries for other setups: yt-dlp releases. For full YouTube support yt-dlp also wants a JavaScript runtime (deno recommended) — see the EJS wiki. Extractors break when sites change; a failing download is often fixed by updating: brew upgrade yt-dlp or pipx upgrade yt-dlp.

Parameters

Flag Default Effect
-a off Audio only, mp3 (yt-dlp preset -t mp3; needs ffmpeg; rejects the video flags -r/-b)
-b off Best native quality — skip the mp4 compatibility preset
-p off Full playlist into a <playlist title>/ subfolder, files named NNN - title [id].ext (default: single video)
-i off Inspect only — list available formats, no download; wins over the download flags
-c A-B — Clip a time range, e.g. -c 10:15-12:30 (needs ffmpeg)
-u <langs> — Subtitles as sidecar files, e.g. -u "en.*,fr" (includes auto-generated)
-r <height> — Cap resolution, e.g. -r 1080
-d <dir> convention path Destination directory

Everything after the URL passes to yt-dlp verbatim — the escape hatch to the full CLI (see Recipes).

Default download: -t mp4 preset — h264/aac preferred, remuxed to mp4, plays everywhere. -b keeps yt-dlp's native best (often webm/mkv, higher fidelity, less compatible).

Workflow

  1. Resolve the media URL from arguments or unambiguous session context. Ask only when it is missing or ambiguous.

  2. Run the helper:

    $SKILL_DIR = this skill's folder — ${CLAUDE_SKILL_DIR} in Claude Code, the directory containing this SKILL.md elsewhere.

    bash "$SKILL_DIR"/scripts/download-media.sh -a 'https://example.com/watch?v=123&list=456'
    

    Parse arguments as data and quote each URL, path and flag value separately. Never splice raw $ARGUMENTS into shell code or use eval; URL metacharacters such as & must remain literal.

  3. The script emits RESULT: key=value lines — one path per downloaded file, then files, dest, slug (order not guaranteed; parse by key). With -i it prints yt-dlp's format table instead.

  4. Parse the RESULT: lines and produce the report below.

  5. ERR: yt-dlp not installed (exit 127) or ERR: -a and -c need ffmpeg (exit 3) → print the matching command from ## Install and stop. Never auto-install on the user's behalf.

  6. Any other ERR: (exit 2 — missing or non-URL input, unknown flag, missing flag value, invalid -r, conflicting flags) → relay the message verbatim and stop. A non-zero exit with RESULT: lines means a partial playlist success — report the downloaded files and the failure. A yt-dlp extraction failure → surface its stderr and suggest updating yt-dlp first (see Install).

Output

downloaded: <n> file(s) → <dest>
  <path>            # one line per file

Subtitle sidecars (-u) sit next to the media file but are not listed in RESULT: lines — mention they are in dest.

Examples

/download-media https://youtu.be/dQw4w9WgXcQ                 # video, mp4, best compatible
/download-media -a https://youtu.be/dQw4w9WgXcQ              # mp3
/download-media -r 1080 <url>                                 # cap at 1080p
/download-media -p <playlist-url>                             # whole playlist
/download-media -c 10:15-12:30 <url>                          # clip a segment
/download-media -u "en.*" <url>                               # video + English subtitles
/download-media -i <url>                                      # list formats, download nothing
/download-media -d ~/Downloads <url>                          # custom destination
/download-media <url> --embed-thumbnail --embed-metadata      # passthrough after the URL

Recipes — passthrough after the URL

Intent Append after the URL
Logged-in / member content --cookies-from-browser firefox (or chrome, safari…)
Strip sponsor segments --sponsorblock-remove sponsor (needs ffmpeg)
Incremental playlist sync --download-archive <dir>/archive.txt
Split by chapters --split-chapters
Embed thumbnail + metadata --embed-thumbnail --embed-metadata
Only playlist items 3–7 -I 3:7 (with -p)
Frame-accurate clip cuts --force-keyframes-at-cuts (with -c; slow, re-encodes)
Gentle on rate limits -t sleep (preset: spaced requests)
Site needs TLS impersonation --extractor-args per site, or install curl_cffi

Compose other yt-dlp flags the same way when an intent is not covered — the full option surface is yt-dlp --help.

Notes

  • Final paths are captured, not guessed — the script uses --print-to-file after_move:filepath so the reported paths are the real ones after merge/remux (--print would silence download progress).
  • Playlist URLs holding a v= too (watch-page URLs) download the single video by default; -p switches to the whole playlist.
  • Unavailable playlist entries don't lose the run — yt-dlp skips them and exits non-zero; the script still reports every downloaded file, then propagates the exit code.
  • -c takes a time range only (START-END, HH:MM:SS or seconds). Chapter-regex sections go through passthrough: --download-sections "intro".
  • Custom -o output templates passed through work, but an absolute -o makes yt-dlp ignore the destination dir (-P) — prefer -d for relocation.
  • No silent overwrites — yt-dlp skips already-downloaded files by default and the slug-namespaced destination keeps runs predictable.

Why the wrapper

yt-dlp is already a superb CLI; this skill exists to (a) put downloads under the repo's global output convention with the final paths reported deterministically, (b) translate "get me the audio" into the right preset without the user remembering -t mp3 vs -x --audio-format, and (c) keep the full flag surface reachable through verbatim passthrough instead of re-wrapping ~200 options.

04 同仓库更多 Skills

coroboros
coroboros/agent-skills

foo

Fixture skill for repo-kind classifier tests.

★ 5
coroboros
coroboros/agent-skills

foo

Fixture for compound skills + npm tooling detection.

★ 5
coroboros
coroboros/agent-skills

write-clear-readme

Author, restructure, audit or polish a project README for clarity and scannability. Reads repository truth, preserves anchors and code, and verifies rendering. Explicit author/polish requests apply local changes; audit/propose stays read-only. Use for README creation, wording, structure and navigation, including skill collections and CLI/SDK docs.

内容创作者写作与文案Skill与智能体开发
★ 5
coroboros
coroboros/agent-skills

video-loop

Prepare a background video loop for a website with optional crossfade, MP4/WebM encoding and poster extraction. Use for loop joins or web delivery of an existing clip.

图像与多媒体
★ 5
coroboros
coroboros/agent-skills

ultrapex

Adaptive implementation when the user explicitly selects /ultrapex or asks for this adaptive workflow. Establish accepted outcomes, implement, and verify the final result. Generic implementation requests use /apex; use /forge for decisions only and /oneshot for small focused changes.

Skill与智能体开发
★ 5
coroboros
coroboros/agent-skills

suno-produce

Create and revise Suno v5.5 prompt artifacts from a song, track or album brief. Produces TRACK.md, ALBUM.md for explicit multi-track work, and optional ARTIST.md identity. Validates prompt fields and preserves supplied lyrics. Artifact-only; audio generation stays in Suno. Pure lyric writing and audio post-production use other skills.

内容创作者图像与多媒体写作与文案
★ 5