Yt Dlp Cli

Community

tmchow

yt-dlp-cli

yt-dlp. Use when the user wants to download, extract audio, pull subtitles, clip, or archive a YouTube or other streaming-site URL, or when yt-dlp hits 403, bot-check, or only-360p. Not for local-file edit/transcode, watch/summarize without saving, search, or generic downloads.

Overview

Publisher	tmchow
Repository	`agent-skills`
Skill name	`yt-dlp-cli`
Stars	67
Forks	4
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by tmchow on GitHub. Read the source before you install it.

Installation

Install the Yt Dlp Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/tmchow/agent-skills/tree/main/yt-dlp-cli
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/tmchow/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/yt-dlp-cli .claude/skills/yt-dlp-cli

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yt Dlp Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Yt Dlp Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Yt Dlp Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

yt-dlp-cli - agent workflow

Result: After a user asks to download, extract, clip, subtitle, or archive media from a yt-dlp-supported URL, the agent has either produced the correct file(s) on disk and reported path/size/identity, or stopped on an explicit blocker (missing binary, auth required, rights unclear, playlist too large, YouTube bot wall).

Next consumer: The user (file on disk) and any later skill that transcribes/edits that file.

Done: File exists at the stated path, matches the requested job (video vs audio vs clip vs playlist range), and the agent reported what it did and how it verified. Or a named blocker with the next safe action.

Intent (changes the approach): Agents can already invoke yt-dlp <url> and they do it badly. This skill exists to close those failure modes, not to teach the CLI. Do not write a flag encyclopedia. Do not hide yt-dlp behind a Python wrapper.

Autonomy envelope

Invoking this skill authorizes local inspection, downloading the requested streaming-site URL, writing the resulting file(s) under the chosen destination, and running required local ffmpeg postprocessing for the requested media shape. It does not authorize downloading an unbounded playlist/channel, reading browser cookies or auth files, bypassing unclear rights, or supplying user-only inputs. Stop for confirmation only when rights are unclear, scope expands to a full playlist/channel without an agreed range/archive, cookies/auth are needed, or the next input can only come from the user.

Quote every URL in shell commands. Treat a watch URL as one video unless the user explicitly asked for the playlist; keep --no-playlist on single-video jobs. Check ffmpeg -version before merged video/audio, audio extraction or conversion, subtitle embedding, clips, or SponsorBlock postprocessing; missing ffmpeg is a blocker for those shapes.

Default download

For a single requested video, run this command first:

bash
yt-dlp --no-playlist -P "<dir>" -o "%(title).200B [%(id)s].%(ext)s" --merge-output-format mp4 --print after_move:filepath "<url>"

Use the path printed by --print after_move:filepath as the authoritative handoff path. Verify that file exists and is non-empty; for video, verify duration and resolution with ffprobe or equivalent.

Deltas from the default

Height cap: add -f "bv*[height<=1080]+ba/b[height<=1080]" and change only the numeric cap. Use yt-dlp --no-playlist -F "<url>" first only when the user requested a specific format ID or the first run returns the wrong shape; never invent format IDs.
Audio-only: replace --merge-output-format mp4 with -x; add --audio-format <format> only when the user requested a container/codec such as mp3 or m4a.
Subtitles: for subtitle-only jobs, replace media download/postprocessing with --skip-download --write-subs --sub-langs "<langs>". For video plus subtitles, keep the default download and add --write-subs --sub-langs "<langs>". Add --write-auto-subs only when generated captions are acceptable, and --embed-subs only when embedded subtitles are requested.
Output layout: change only -P "<dir>" and -o "<template>". Keep %(id)s in the template unless the user requested a different stable naming scheme.
SponsorBlock: add --sponsorblock-remove <categories> only for categories the user requested or approved.

Pinned fragile routes

For playlist or channel archive work, first confirm the range or archive scope. Then use an archive file so reruns skip completed entries:

bash
yt-dlp -I "1-10" --download-archive "<dir>/download-archive.txt" -P "<dir>" -o "%(playlist_title).120B/%(playlist_index)s - %(title).200B [%(id)s].%(ext)s" --print after_move:filepath "<playlist-or-channel-url>"

Keep -I for item ranges; remove it only after the user confirmed a full archive. The archive file is part of the handoff because it prevents duplicate downloads on rerun.

For clips or time sections, use --download-sections and verify the resulting duration against the requested span:

bash
yt-dlp --no-playlist --download-sections "*00:01:30-00:02:10" -P "<dir>" -o "%(title).200B [%(id)s] clip.%(ext)s" --merge-output-format mp4 --print after_move:filepath "<url>"

Change only the timestamps unless the user requested a different section.

Ordered hatch

Run the pinned default or fragile route first. If it exits non-zero, returns the wrong media shape, reports a bot/auth/version mismatch, or shows only 360p where higher formats should exist, take this order:

Preserve the command, exit status, and stderr.
Update yt-dlp, verify yt-dlp --version, then retry a low-cost inspection with yt-dlp --no-playlist -F "<url>" or yt-dlp --no-playlist --print ... "<url>".
For wrong shape or site-specific syntax drift, consult live yt-dlp --help / yt-dlp -h and adjust the smallest delta needed.
For YouTube 403, "confirm you're not a bot", missing higher qualities, nsig errors, PO-token paths, or header-sensitive HLS failures, read references/youtube-auth.md in full before retrying.
Stop with a blocker when rights, scope, auth, user-only input, or a missing binary prevents safe completion.

Report

The report may omit secondary detail, but it must preserve command, exit status, output path and size, media identity when available, verification performed, and stderr or blocker. For video include duration/resolution; for audio include audio-only confirmation; for playlists/channels include item count and archive-file path.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/youtube-auth.md3 KB

Frequently asked questions

What does the Yt Dlp Cli AI skill do?

Why use Yt Dlp Cli on TypingMind?

Because you install it once and use it with any model. Yt Dlp Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Yt Dlp Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tmchow/agent-skills/tree/main/yt-dlp-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Yt Dlp Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Yt Dlp Cli?

As many as you like. As long as a model supports skills, you can use Yt Dlp Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Yt Dlp Cli AI skill free?

Yes. It is published on GitHub by tmchow under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Facetime

openclaw

OrganizationPopular

Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetime_call.

Camsnap

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Fal Ai Media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

yt-dlp-cli - agent workflow

Autonomy envelope

Default download

Deltas from the default

Pinned fragile routes

Ordered hatch

Report

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now