youtube-processor

A tool for turning a YouTube video into an Obsidian note. Obsidian is an app for storing linked plain-text notes; the tool gets the video's transcript and uses it to create a summary.

In plain words
What is it for?
Use it to summarize videos, extract insights, create notes, or prepare source material for a newsletter. The output is Markdown, a plain-text format supported by Obsidian.
Why use it?
It saves you from watching a video solely to extract its main ideas and from formatting the notes by hand. It works from a YouTube link.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/youtube-processor
Any agent
npx skills add nicepkg/ai-workflow --skill youtube-processor
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.01379
Opus 5 $0.00033 $0.00690
Sonnet 5 $0.00013 $0.00276
Haiku 4.5 $0.00007 $0.00138

Measured 2d ago against content hash 1200461e69d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

youtube-processor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (api/main.py, tools/get_transcript.py, tools/process_video.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/content-creator-workflow/.claude/skills/youtube-processor/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Processor

What This Does

Takes a YouTube URL, extracts the transcript, and you (Claude) summarize it. Outputs Obsidian-ready markdown. Zero friction: share a link, get actionable notes.

When to Use

  • "Summarize this video: [URL]"
  • "Turn this YouTube into notes"
  • "What's this video about?"
  • "Process this for my newsletter"
  • Any YouTube URL shared for processing

Location

This skill's tools live at:

/Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools/

How It Works

Step 1: Python extracts the transcript (no API key needed) Step 2: You (Claude) summarize using your intelligence + context Step 3: You write the Obsidian-formatted output

This approach means you can use mission-context, newsletter-coach, and other skills during summarization.


Instructions

Which Method to Use

Environment Method
Claude Code Local Python script (Step 1a)
Claude.ai / Mac Client API via WebFetch (Step 1b)

Step 1a: Extract Transcript (Claude Code)

Run the Python tool to get the transcript:

cd /Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools && \
python3 get_transcript.py --url "[URL]"

For JSON output (easier to parse):

python3 get_transcript.py --url "[URL]" --json

Step 1b: Extract Transcript (Claude.ai / Mac Client)

Use the API endpoint via WebFetch:

WebFetch: https://youtube-processor-eight.vercel.app/transcript?url=[VIDEO_URL]

The API returns JSON:

{
  "success": true,
  "video_id": "abc123",
  "language": "en",
  "transcript": "...",
  "char_count": 5000,
  "word_count": 850
}

Example prompt for WebFetch: "Extract the transcript text from the response"


Step 2: Summarize the Transcript

Once you have the transcript, summarize it based on what the user needs:

Quick Summary:

  • Headline (1 sentence)
  • Key points (3-5 bullets)
  • Main takeaway

Read the full file on GitHub · 243 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 243 lines · 66 tokens per session scan A 1200461e69d8

Subscribe to this mod's changes

youtube-processor is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 66 tokens to every session and 1,379 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.