ingest-youtube
Pull a YouTube video transcript into a queryable markdown vault with yt-dlp subtitle discovery, VTT cleanup, metadata frontmatter, and capture-seed stubs.
- License 许可
- MIT
- 最近更新
- 2026-08-07
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- ingest-youtube
- risk
- safe
- plugin
- { "setup": { "docs": "SKILL.md", "type": "manual", "summary": "Install yt-dlp locally before running ingest.py; the script only accepts http(s) YouTube video URLs and writes markdown into the selected vault." } }
- source
- community
- license
- MIT
- upstream
- https://github.com/adelaidasofia/ai-brain-starter/tree/main/skills/ingest-youtube
- date_added
- 2026-05-09
- description
- Pull a YouTube video transcript into a queryable markdown vault with yt-dlp subtitle discovery, VTT cleanup, metadata frontmatter, and capture-seed stubs.
- source_repo
- adelaidasofia/ai-brain-starter
- source_type
- community
- license_source
- https://github.com/adelaidasofia/ai-brain-starter/blob/main/LICENSE
02 资源文件 1
- 脚本ingest.py12.4 KB
03 SKILL.md 正文
ingest-youtube — YouTube-to-vault connector
Pulls YouTube transcripts into a markdown vault as queryable typed-memory entries that downstream skills (knowledge graph extraction, voice-fingerprint training, content repurposing, action-item extraction) can act on.
Same pattern as ingest-slack, ingest-whatsapp, ingest-notion, ingest-linear, ingest-github, ingest-gmail. Adding YouTube means a new normalizer, not a new architecture.
When to use
- User pastes a YouTube URL and asks for a transcript or summary
- User says
/ingest-youtube <url>for a single video - User asks to capture, sync, ingest, transcribe, or pull a talk/podcast/keynote into the vault
Do NOT use for:
- Downloading the actual video file (use
yt-dlpdirectly with-f best) - Channel-wide ingestion or
--dayswindows; this script ingests one video URL at a time - Live streams (transcripts are not stable)
- Non-YouTube sources (Vimeo, Twitch, Twitter Spaces have their own connectors)
- One-off transcript reads where the user does not want a vault file (run
yt-dlp --write-auto-subdirectly and pipe to stdout)
How it works
- Parse the input as one YouTube video URL.
- Verify
yt-dlpis installed. If not, the script exits with install instructions:brew install yt-dlp(macOS) orpip3 install --user yt-dlp. - Validate the URL as a single http(s) YouTube video and call
yt-dlp --ignore-config --list-subs -- <url>to enumerate available subtitles. - Subtitle priority: manual subs > auto-generated captions. Manual subs preserve creator-provided punctuation and speaker labels; auto-gen is uppercase + no punctuation.
- Download the highest-priority subtitle as VTT via
yt-dlp --write-sub --sub-lang <lang> --skip-download. Default language preference:en,es(English first, Spanish second). - Strip VTT timing markers and merge into clean prose paragraphs. Deduplicate repeated lines (auto-generated VTTs are line-doubled). Preserve speaker labels if the source had them.
- Pull video metadata (title, channel, upload date, duration, video_id, URL) via
yt-dlp --print-json --skip-download. - Slugify the channel name and video title. Write to
External Inputs/YouTube/<channel-slug>/<YYYY-MM-DD>-<video-slug>.md. - Scan transcript for trigger keywords (decision, framework, model, principle, "the lesson is", playbook, anti-pattern, case study). For each match, create a writing-seed stub at
Meta/Captures/<YYYY-MM-DD>-youtube-<channel-slug>-<video-id>.mdso the seed lands in the captures aggregator. - Print summary: file path, transcript word count, language, seeds detected.
Invocation
python3 ingest.py <youtube-url> [--vault <path>] [--lang <code>]
Defaults:
--vault:$VAULT_ROOTenv var or current directory--lang:en,es(English first, Spanish second; matches a common bilingual default)--whisper: accepted as a future fallback flag, but this version writes a stub when no subtitles are available
Output contract
The vault file at External Inputs/YouTube/<channel-slug>/<YYYY-MM-DD>-<video-slug>.md has frontmatter:
---
type: external-input
source: youtube
video_id: <11-char ID>
url: https://www.youtube.com/watch?v=<id>
channel: <channel-name>
channel_url: https://www.youtube.com/<handle>
title: <video title>
upload_date: <YYYY-MM-DD>
duration_seconds: <int>
language: <ISO code>
subtitle_source: manual | auto | whisper
word_count: <int>
ingested_at: <ISO 8601 timestamp>
---
Body is the cleaned transcript as paragraph prose. If the source had speaker labels, format as **<speaker>:** <text> per turn.
Idempotency
Re-ingesting the same video URL overwrites the same vault file. The seed stub filenames hash the video_id, so the same source video produces the same stub filename across re-runs. Re-runs refresh, never duplicate.
Missing subtitles
If yt-dlp --list-subs returns no manual or auto subtitles, the script writes a stub vault note with the video metadata and source URL instead of failing silently. The --whisper flag is reserved for a future local transcription fallback and currently reports that the fallback is not implemented.
For a manual fallback today, download audio with yt-dlp, transcribe it with your local Whisper workflow, and add captions or transcript text before rerunning the ingest.
Limitations
- Ingests one YouTube video URL per run; channel handles, playlists, and
--dayswindows are out of scope. - Depends on subtitles returned by
yt-dlp; videos without subtitles produce a metadata stub, not a transcript. - Does not download video files or perform built-in Whisper transcription in this version.
- Network availability, YouTube subtitle access, and local
yt-dlpbehavior determine whether ingest succeeds.
Acceptance test
Run against the first YouTube video ever uploaded:
python3 ingest.py "https://www.youtube.com/watch?v=jNQXAC9IVRw" --vault /tmp/test
Expected output:
Wrote 39 words to /tmp/test/External Inputs/YouTube/jawed/2005-04-24-me-at-the-zoo.md. Language: en. Subtitle source: manual.
The output file contains valid frontmatter and a clean prose body.
Dependencies
yt-dlp(required): install viabrew install yt-dlporpip3 install --user yt-dlpwhisper-cpp(optional for a manual fallback outside this script)
Source
Bundled in adelaidasofia/ai-brain-starter, a verification harness around an AI agent so memory compounds instead of corrupts. The skill is part of the ingest-* family of vault connectors.
04 同仓库更多 Skills
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
stop-slop
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.
ogilvy-copywriting
Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.