Skip to content

axel-pm/watch-n-learn / skills/watch-and-learn

watch-and-learn

Verified

Watch a how-to / tutorial / demo video and turn the procedure it teaches into one or more working Claude Code skills. Use when the user wants to "turn this video into a skill", "watch this tutorial and make a skill", "learn how to do X from this video", "build a skill from this screencast/demo/talk", or capture a repeatable workflow shown in a video. Sends an agent to watch the video (local file or URL) with a local, free, no-API toolchain, breaks the procedure down, authors the skill(s), and verifies they actually work.

scripts/install-tools.sh

View on GitHub
#!/usr/bin/env bash
# One-time setup for the "watch-and-learn" skill's video toolchain.
#
# Builds a self-contained Python venv with everything needed to "watch" a video:
#   - av (PyAV)        frame extraction + audio decode  (bundles ffmpeg libs; no system ffmpeg)
#   - Pillow           save frames / build the contact sheet
#   - faster-whisper   local transcription (CTranslate2, NO torch; models cache on first use)
#   - yt-dlp           download videos from URLs
#
# No global installs, no ffmpeg binary, no torch, no API keys. Runs on any machine with python3.
#
# The venv is created at ~/.video-watch-tools/venv — a stable location in your home dir, on
# purpose: the skill itself may live in a plugin cache that gets replaced on every update, so the
# toolchain must live OUTSIDE it. watch.py already looks here automatically, so once this has run
# you never touch it again.
#
# Usage:  bash install-tools.sh
# Override the location by exporting VIDEO_WATCH_TOOLS=/some/dir before running (watch.py honors it).
set -euo pipefail

TOOLS="${VIDEO_WATCH_TOOLS:-$HOME/.video-watch-tools}"
PYBIN="${PYTHON:-python3}"

echo "→ Creating venv at $TOOLS/venv"
mkdir -p "$TOOLS"
"$PYBIN" -m venv "$TOOLS/venv"
"$TOOLS/venv/bin/pip" install -q --upgrade pip

echo "→ Installing packages (av, Pillow, faster-whisper, yt-dlp) — this can take a minute"
"$TOOLS/venv/bin/pip" install -q av Pillow faster-whisper yt-dlp

echo "→ Verifying imports"
"$TOOLS/venv/bin/python" - <<'PY'
import av, PIL, faster_whisper, yt_dlp
print("imports OK:", "av", av.__version__, "| Pillow", PIL.__version__,
      "| faster_whisper", "| yt_dlp", yt_dlp.version.__version__)
PY

echo "✓ Toolchain ready at $TOOLS/venv"
echo "  You won't need to run this again on this machine."
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall