Agent-Skills.md

Agent Skills: Get YouTube Transcript (Raw)

Capture a YouTube video transcript as raw material using `ytt`, storing it in the raw/ directory with minimal metadata for later distillation.

youtubetranscriptyttcontent-extractionraw-data
content-creationID: dudarev/ai-assisted-software-development/get-youtube-transcript-raw

Install this agent skill to your local

pnpm dlx add-skill https://github.com/dudarev/ai-assisted-software-development/tree/HEAD/skills/get-youtube-transcript-raw

Skill Files

Browse the full folder contents for get-youtube-transcript-raw.

Download Skill

Loading file tree…

skills/get-youtube-transcript-raw/SKILL.md

Skill Metadata

Name
get-youtube-transcript-raw
Description
Capture a YouTube video transcript as raw material using `ytt`, storing it in the raw/ directory with minimal metadata for later distillation.

Get YouTube Transcript (Raw)

When to use

Use when you need the raw transcript (plus YouTube title/description) saved to raw/ for later distillation.

Keywords: youtube, transcript, captions, ytt, raw, capture

Inputs

Required:

  • url (string): YouTube URL (e.g., https://www.youtube.com/watch?v=... or https://youtu.be/...)

Optional:

  • title_hint (string): Used only if ytt can’t provide a title.

Outputs

This skill produces:

  1. A new Markdown file in raw/ named YYYYMMDD-HHMMSSZ--<slug>.md
  2. YAML front matter aligned with docs/distillation/distillation-pipeline.md:
    • title (best-effort)
    • source_url (the provided URL)
    • captured_at (UTC ISO timestamp)
    • capture_type: youtube_transcript
    • capture_tool: ytt
    • raw_format: markdown
    • status: captured
  3. Body content: the raw transcript text emitted by ytt (no summarization).

On failure in “fetch” mode, the script exits non-zero and does not write a placeholder raw note.

Prerequisites

  • ytt (this repo’s YouTube transcript utility)
  • python3 (used by the bundled script for slugging and safe YAML string escaping)

Quick start

Capture directly (uses ytt fetch --no-copy internally):

./scripts/ytraw "<youtube_url>"

If the current environment can’t access YouTube (common in sandboxes), run ytt locally and pipe:

ytt fetch --no-copy "<youtube_url>" | ./scripts/ytraw

Manual execution (Fallback)

If you encounter persistent issues capturing a transcript within the sandbox (e.g., network restrictions or tool failures), inform the user they can run the script manually on their local machine.

The script ./scripts/ytraw is designed to extract the URL directly from the clipboard if no arguments are provided.

Instructions for the user:

  1. Copy the YouTube URL to your clipboard.
  2. Run the following command in your terminal: 
    ./scripts/ytraw
  3. If manual adjustments are required, you can edit the file directly. If you prefer the model to perform adjustments, share the file path or URL with it.

Optional: shell alias (zsh)

Add to ~/.zshrc:

ytraw () { ytt fetch --no-copy "$1" | /path/to/repo/scripts/ytraw --from-stdin }

References

  • Pipeline and front matter schema: docs/distillation/distillation-pipeline.md