Agent skill

Youtube

by axoviq-ai in axoviq-ai/synthadoc

Extract transcripts from YouTube videos via the YouTube caption system

AGPL-3.0-or-laterAuto-check passedKnowledge Management

Install Youtube

skills CLI
$ npx skills add axoviq-ai/synthadoc --skill youtube -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install axoviq-ai/synthadoc youtube --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/axoviq-ai/synthadoc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/synthadoc/skills/youtube .claude/skills/youtube && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
youtube
GitHub stars
1.6k
Token cost
~634 tokens
SKILL.md length
139 words
Files
4 (incl. scripts)
Skills in repo
9
Repo updated
First seen
Licence
AGPL-3.0-or-later

At a glance

Extract transcripts from YouTube videos via the YouTube caption system

  • Knowledge Management work in your project
  • SKILL.md covers Setup, Standalone usage, When this skill is used and Limitations
  • Runs Python scripts from its folder; calls pip; reaches youtube.com and youtu.be

What it does

Youtube is an agent skill from axoviq-ai/synthadoc. Extract transcripts from YouTube videos via the YouTube caption system

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/__init__.py` and `scripts/main.py`).

It sits in Knowledge Management. It works with YouTube and Obsidian. The repository describes itself as: Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional… The licence is AGPL-3.0-or-later.

When your agent uses it

  • Knowledge Management work in your project

Example prompts

  • “/youtube”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 90d0db7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • youtube.com
    • youtu.be
    • youtubekids.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Youtube loads about 634 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 139 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~634

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from axoviq-ai/synthadoc at commit 90d0db7, republished under its AGPL-3.0-or-later licence (© axoviq-ai). 139 words, ~634 tokens.

Download SKILL.mdSave it as .claude/skills/youtube/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
youtube
description
Extract transcripts from YouTube videos via the YouTube caption system
version
1.0
entry.script
scripts/main.py
entry.class
YoutubeSkill
triggers.extensions
https://www.youtube.com/, https://youtu.be/, https://www.youtubekids.com/
requires
youtube-transcript-api
author
axoviq.com
license
AGPL-3.0-or-later

YouTube Skill

Extracts the transcript (captions) from a YouTube video using the YouTube caption system — no API key or audio download required. Optionally uses a vision-capable LLM to produce a structured summary (Overview, Topics, Key takeaways) before the raw transcript.

Setup

bash
pip install youtube-transcript-api

Standalone usage

Transcript only (no LLM required):

python
import asyncio
from synthadoc.skills.youtube.scripts.main import YoutubeSkill

skill = YoutubeSkill()          # no provider — returns raw timestamped transcript

async def main():
    result = await skill.extract("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
    print(result.text)          # "[0:00] text [0:04] text ..."
    print(result.metadata)      # {"video_id": "...", "title": "...", "url": "..."}

asyncio.run(main())

With LLM summarization (pass any provider that implements complete()):

python
skill = YoutubeSkill(provider=my_provider)
result = await skill.extract(url)
# result.text contains:
#   ## Executive Summary
#   <Overview / Topics / Key takeaways>
#
#   ## Transcript
#   [0:00] ...

The provider must implement:

python
async def complete(messages, system=None, temperature=0.0, max_tokens=4096)
    -> object with .text (str), .input_tokens (int), .output_tokens (int)

Message (used to build the messages list) is importable from synthadoc.skills.base:

python
from synthadoc.skills.base import Message

When this skill is used

  • Source starts with https://www.youtube.com/, https://youtu.be/, or https://www.youtubekids.com/

To search YouTube by topic instead of ingesting a specific URL, use the web search skill — it filters Tavily results to YouTube domains automatically:

bash
synthadoc ingest "youtube Moore's Law"
synthadoc ingest "youtube kids: Sesame Street"
synthadoc ingest "search for youtube: history of computing"

Limitations

  • Only works for videos that have captions (auto-generated or manually added). If no captions are available the source is skipped with a warning.
  • Private or deleted videos are skipped gracefully.

© axoviq-ai, AGPL-3.0-or-later. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in synthadoc/skills/youtube of axoviq-ai/synthadoc.

  • SKILL.md
  • requirements.txt
  • scripts/__init__.py
  • scripts/main.py

Open the folder on GitHubat commit 90d0db7

Compare with similar skills

Youtube next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Youtube compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Youtube this skillaxoviq-ai/synthadoc1.6k—~634Automated safety check: PassAGPL-3.0-or-later
Subscription Videos MetadataEfficientStreet/youtube-subscriptions-ingest180—~7.1kAutomated safety check: NotesMIT
Youtube Transcriptglebis/claude-skills391—~613Automated safety check: PassMIT
Researchiusztinpaul/ai-research-os-workshop179—~17kAutomated safety check: PassMIT
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0

Similar skills

  • Subscription Videos Metadata

    EfficientStreet/youtube-subscriptions-ingest

    Pull metadata from YouTube subscription videos into a second-brain vault as a real cross-linked knowledge graph — not just a flat archive.

    180 GitHub stars~7.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check: notes
  • Youtube Transcript

    glebis/claude-skills

    Extract YouTube video transcripts with metadata and save as Markdown to Obsidian vault.

    391 GitHub stars~613 tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed
  • Research

    iusztinpaul/ai-research-os-workshop

    Build, extend, AND query a persistent LLM-maintained wiki for any research topic.

    179 GitHub stars~17k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed
  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed
  • Multi-Source to NotebookLM Processor

    joeseesun/qiaomu-anything-to-notebooklm

    Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.

    6.2k GitHub stars~3.6k tokensUpdated 6 days ago
    Knowledge ManagementAuto-check passed

More from axoviq-ai/synthadoc

All 9 skills in this repo
  • Image

    axoviq-ai/synthadoc

    Extract text from images using a vision LLM. An agent skill from axoviq-ai/synthadoc.

    1.6k GitHub stars~544 tokensUpdated today
    Auto-check passed
  • Session

    axoviq-ai/synthadoc

    Extract conversation turns from AI session history files (.jsonl)

    1.6k GitHub stars~902 tokensUpdated today
    Auto-check passed
  • PPTX

    axoviq-ai/synthadoc

    Extract text from Microsoft PowerPoint presentations. An agent skill from axoviq-ai/synthadoc.

    1.6k GitHub stars~248 tokensUpdated today
    Auto-check passed
  • DOCX

    axoviq-ai/synthadoc

    Extract text from Microsoft Word documents. An agent skill from axoviq-ai/synthadoc.

    1.6k GitHub stars~207 tokensUpdated today
    Auto-check passed
  • PDF

    axoviq-ai/synthadoc

    Extract text from PDF documents

    1.6k GitHub stars~293 tokensUpdated today
    Auto-check passed
  • URL

    axoviq-ai/synthadoc

    Fetch and extract text from web URLs

    1.6k GitHub stars~371 tokensUpdated today
    Auto-check passed

Works with

Questions about Youtube

What does Youtube do?

Extract transcripts from YouTube videos via the YouTube caption system. Youtube is an agent skill from axoviq-ai/synthadoc.

When should I use Youtube?

Youtube fits situations like: knowledge Management work in your project.

How do I install Youtube in Claude Code?

Run `npx skills add axoviq-ai/synthadoc --skill youtube -a claude-code`. Or copy the skill folder (synthadoc/skills/youtube in axoviq-ai/synthadoc) into .claude/skills/youtube in your project. Claude Code loads it when a task matches its description.

How do I install Youtube in Codex?

Run `npx skills add axoviq-ai/synthadoc --skill youtube -a codex`. Or copy the skill folder (synthadoc/skills/youtube in axoviq-ai/synthadoc) into .agents/skills/youtube in your project. Codex loads it when a task matches its description.

Can I use Youtube in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add axoviq-ai/synthadoc --skill youtube -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/youtube, .gemini/skills/youtube, .github/skills/youtube and .opencode/skills/youtube in your project.

What does Youtube need to run?

Going by SKILL.md and its folder, Youtube needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Youtube access the network?

SKILL.md names 3 domains. In commands or code: youtube.com, youtu.be and youtubekids.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Youtube safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Youtube use?

Youtube is published under the AGPL-3.0-or-later licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Youtube use?

About 634 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Youtube?

Skills that share tags, products or a category with Youtube: Subscription Videos Metadata (EfficientStreet/youtube-subscriptions-ingest, 180 stars), Youtube Transcript (glebis/claude-skills, 391 stars), Research (iusztinpaul/ai-research-os-workshop, 179 stars) and Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Youtube?

axoviq-ai (a GitHub organization) maintains it in axoviq-ai/synthadoc, which has 1,578 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 10, 2026.

Source: axoviq-ai/synthadoc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.