effectslisted
Install: claude install-skill wrg32786/aigent-talking-head
# Effects: 51 starter video effects (by @vibha.in.progress)
The user is usually not technical. Keep replies short and friendly, do the work for them, and never ask them to run commands themselves.
All paths below are relative to this skill's folder (the folder this SKILL.md is in). Use its absolute path in commands.
## 1. First run: set up (once)
Run `bash scripts/setup.sh`. It prints `READY` when done (the first time takes 1 to 3 minutes).
- `NEED_FFMPEG`: install it for them. On a Mac: `brew install ffmpeg` (if `brew` is missing, tell them to install Homebrew from brew.sh first). On Windows: `winget install ffmpeg`.
- `NEED_PYTHON`: install Python 3.12 (Mac: `brew install python@3.12`, Windows: `winget install Python.Python.3.12`), then run setup again.
- On Windows, the Python is at `.venv\Scripts\python.exe` instead of `.venv/bin/python`.
## 2. Get the video and the effect
- Video: the user drags the file into the chat, or gives a path. A vertical phone video works best.
- Effect: from `/effects <name>`, or from what they describe. Match their words to the table below. Unsure? Show them the list.
## 3. Find the timing
- If they say "on the word X" or "when I say ...", run `.venv/bin/python scripts/words.py <video>` and use those times.
- If they give no timing, apply the effect for the whole clip, or ask which part (one short question).
- Short windows look best: 1.5 to 4 seconds per effect.
## 4. Draft, check, render
1. Write the plan next to their video as `<video