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
- 所属仓库
- ASoudy/AGS
- 最近更新
- 2026-05-23
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ingest-youtube
- risk
- safe
- 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.py10.5 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. - Call
yt-dlp --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
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", or "typographic scale". Also trigger when choosing between system fonts and web fonts, optimizing font loading performance, or designing readable long-form content layouts. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.
ux-heuristics
Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "UX review", "users are confused", "heuristic evaluation", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "usability testing". Also trigger when reviewing a design for usability issues, improving form completion rates, or evaluating information architecture and navigation. Covers Nielsens 10 heuristics, severity ratings, and information architecture. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "Entrepreneurial Operating System", or "business operating system". Also trigger when a growing company needs meeting structure, goal-setting frameworks, or a systematic approach to solving recurring organizational issues. Covers the six EOS components: Vision, People, Data, Issues, Process, Traction. For team motivation design, see drive-motivation. For lean experimentation, see lean-startup.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "premium website", "portfolio site", "scroll animations", "Awwwards quality", "brand experience", "cinematic web design", "parallax storytelling", or "agency-quality site". Also trigger when building landing pages that need to impress, designing creative portfolios, or elevating a standard website to a memorable digital experience. Covers dramatic typography, purposeful motion, scroll-based composition, and performance-optimized animation. For foundational UI, see refactoring-ui. For type selection, see web-typography.
system-design
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "system design interview", "capacity planning", or "distributed architecture". Also trigger when estimating infrastructure requirements, choosing between microservices and monoliths, or designing for millions of concurrent users. Covers common system designs and back-of-the-envelope estimation. For data fundamentals, see ddia-systems. For resilience, see release-it.
storybrand-messaging
Clarify brand messaging using narrative structure that positions the customer as hero. Use when the user mentions "brand message", "website copy", "elevator pitch", "one-liner", "messaging isnt resonating", "brand script", "StoryBrand framework", or "customer as hero". Also trigger when rewriting homepage copy, crafting email nurture sequences, or creating consistent messaging across sales collateral and marketing materials. Covers landing page copy, marketing collateral, and consistent communication. For memorable messaging, see made-to-stick. For product positioning, see obviously-awesome.