A knowledge-extraction skill that pulls practical ideas, methods, and frameworks from sources such as web pages, files, PDFs, videos, and podcasts.

Extracting structured knowledge from articles, social-media videos, podcasts, local files, and PDFs.

It helps you learn the useful parts of a source without having to consume the entire item yourself.

eat — Skill for Claude Code by catcatcatstudio

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.

Any agent

npx skills add catcatcatstudio/cat-skills --skill eat

Clone the repo

git clone --depth 1 https://github.com/catcatcatstudio/cat-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/eat/github.svg)](https://agentmods.dev/skills/catcatcatstudio/cat-skills/eat)

Your own site

<a href="https://agentmods.dev/skills/catcatcatstudio/cat-skills/eat"><img src="https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/eat/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/catcatcatstudio/cat-skills/eat"><img src="https://agentmods.dev/badge/skills/catcatcatstudio/cat-skills/eat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,123 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.03123
Opus 5	$0.00041	$0.01562
Sonnet 5	$0.00016	$0.00625
Haiku 4.5	$0.00008	$0.00312

Measured 10d ago against content hash 6373be6bec7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

eat scanned grade A with 1 finding 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 10d ago.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://cdn.syndication.twimg.com/tweet-result?id=<TWEET_ID>&token=a"

.agents/skills/eat/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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, tiktok.com, x.com with video):

yt-dlp is configured with Brave cookies — authenticated access, no extra flags needed.

# 1. Metadata first (always start here)
yt-dlp --print title --print description --print duration --print uploader --skip-download "<url>"

# 2. Download to tmp
yt-dlp -o "/tmp/extract-%(id)s.%(ext)s" "<url>"

# 3. Transcribe audio with local Whisper
ffmpeg -i /tmp/extract-<id>.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 /tmp/extract-<id>-audio.wav
whisper /tmp/extract-<id>-audio.wav --model base --language en --output_format txt --output_dir /tmp/

# 4. Extract key frames (one every ~10 seconds)
mkdir -p /tmp/extract-frames
ffmpeg -i /tmp/extract-<id>.mp4 -vf "fps=1/10" -q:v 2 /tmp/extract-frames/<id>-%02d.jpg

# 5. Read frames visually — look for on-screen text, diagrams, handwritten notes, visual content
# 6. Synthesize: transcript + visuals + caption
# 7. Trash all temp files when done

Read the full file on GitHub · 299 lines

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.

10d ago First seen · 299 lines · 82 tokens per session scan A 6373be6bec7a

Subscribe to this mod's changes

eat is a skill published in the GitHub repository catcatcatstudio/cat-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 3,123 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Learning and teaching Research agent-skills ai-agent claude-code-plugin claude-code-skill claude-skills

writer-style

Write original educational and long-form technical content in a specific author's authentic voice — courses, lessons, explainers, deep-dives, threads — using a two-layer voice pack (an always-on PRIMARY voice that reproduces the author's idiolect + SECONDARY craft borrowed from master writers, applied not…

solanabr/writer-style-skill · 255 tokens

learn-from-fix

Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.

oliver-kriska/claude-elixir-phoenix · 46 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

examples

Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.

oliver-kriska/claude-elixir-phoenix · 57 tokens

intro

Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.