Skills for Real Engineers. Straight from my .agents directory.
automate-this
Agent skill fromgithub/awesome-copilot
Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.
How to install automate-this
npx skills add github/awesome-copilot# or add only this skill to Claude Code: copy the folder
skills/automate-this/
# into
~/.claude/skills/automate-this/ (all projects)
.claude/skills/automate-this/ (one project)
1# Automate This23Analyze a screen recording of a manual process and build working automation for it.45The user records themselves doing something repetitive or tedious, hands you the video file, and you figure out what they're doing, why, and how to script it away.67## Prerequisites Check89Before analyzing any recording, verify the required tools are available. Run these checks silently and only surface problems:1011```bash12command -v ffmpeg >/dev/null 2>&1 && ffmpeg -version 2>/dev/null | head -1 || echo "NO_FFMPEG"13command -v whisper >/dev/null 2>&1 || command -v whisper-cpp >/dev/null 2>&1 || echo "NO_WHISPER"14```1516- **ffmpeg is required.** If missing, tell the user: `brew install ffmpeg` (macOS) or the equivalent for their OS.17- **Whisper is optional.** Only needed if the recording has narration. If missing AND the recording has an audio track, suggest: `pip install openai-whisper` or `brew install whisper-cpp`. If the user declines, proceed with visual analysis only.1819## Phase 1: Extract Content from the Recording2021Given a video file path (typically on `~/Desktop/`), extract both visual frames and audio:2223### Frame Extraction2425Extract frames at one frame every 2 seconds. This balances coverage with context window limits.2627```bash28WORK_DIR=$(mktemp -d "${TMPDIR:-/tmp}/automate-this-XXXXXX")29chmod 700 "$WORK_DIR"30mkdir -p "$WORK_DIR/frames"31ffmpeg -y -i "<VIDEO_PATH>" -vf "fps=0.5" -q:v 2 -loglevel warning "$WORK_DIR/frames/frame_%04d.jpg"32ls "$WORK_DIR/frames/" | wc -l33```34…
Excerpt shown under the repository's MIT license.
More skills in awesome-copilot
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
