eat

# /eat — Knowledge Extraction Skill ## Quick Reference | Source | Method | |--------|--------| | YouTube | yt-dlp subtitles → Groq audio fallback → local Whisper fallback | | Instagram / TikTok / X video | yt-dlp (cookie-authenticated) → local Whisper → frame extraction | | Podcast / direct audio | yt-dlp download → Groq transcription → local Whisper fallback | | X/Twitter thread | X API v2 (X_BEARER_TOKEN required) | | Web article | defuddle (preferred) or WebFetch | | Local file / PDF | Read tool | | Paywalled content | Extract what's accessible, note the wall | Output always starts with **Source:** [title] — [URL] then knowledge by category. ### Auth & Tools - **yt-dlp cookies:** Global config at `~/.config/yt-dlp/config` points to Brave browser cookies. Authenticated access to Instagram, X, TikTok — no extra flags needed. - **Local Whisper:** `whisper` CLI (openai-whisper). Use as fallback when Groq is unavailable or for quick local transcription. Base model is fast enough for most content. - **defuddle:** `defuddle parse <url> --md` — cleaner article extraction than WebFetch, strips nav/ads/clutter. --- ## Workflow ### Step 1: Identify source type and fetch content **YouTube video** (youtube.com or youtu.be): Run `scripts/fetch_youtube.sh <url>` — tries subtitle extraction first, falls back to Groq audio transcription. Outputs transcript to stdout. If it fails: tell the user exactly what failed and stop. --- **Instagram / TikTok / X video** (instagram.com, t...