agentleFS
Sign inStart free
MmbugraaslanMmbugraaslan/motion-plus/skills/talking-head-edit/SKILL.md

talking-head-edit

Skill0 starsChanged 5 days agoMITView on GitHub

Auto-edit a raw talking-head recording into a social-ready vertical video, with silence cuts, punch-in zooms, word-by-word captions and loudness at -14 LUFS. Use when the user sends a selfie/face-cam clip to edit for Instagram, TikTok or Shorts.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the review-loop skill.

    line 35
  2. Distinctive:

    No caption page spans two sentences.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Talking-Head Edit

1. Inspect the clip

ffprobe -v error -show_entries stream=codec_type,width,height,avg_frame_rate:format=duration -of default=nw=1 input.mp4

Tell the user if the clip is lower than 1080x1920: messaging apps (Telegram, WhatsApp) compress video, so ask for the original file. Keep going with what you have; the script upscales.

2. Auto-cut + transcribe

pip install faster-whisper --break-system-packages   # first time
python3 scripts/talking_head.py input.mp4 --name my-reel --lang en
  • --lang: spoken language (en, tr, es…). Always set it.
  • --model: faster-whisper model name (small default, medium for better accuracy) or a local CTranslate2 folder.
  • --fix "wrong=right": correct misheard words (repeatable). Brand names, product names and English tech words are the usual suspects.
  • --emphasize word …: words that get a pop animation.

This writes studio/public/footage/my-reel.mp4 (1080x1920, 30 fps, -14 LUFS) and studio/edits/my-reel.json (cut list + caption groups, one per sentence). Read the printed transcript, compare it with what the user meant to say and fix words with --fix or by editing the JSON.

3. Render

bash scripts/render.sh edits/my-reel.json --comp TalkingReel

4. Overlays (optional)

For callouts, badges, code cards, B-roll or a comment-style CTA, add <Sequence> blocks on top of TalkingReel timed to caption word times (startMs in the edit JSON). Keep overlays out of the face area (top ~55% of frame on a typical selfie) and above the captions.

5. Review

Run the review-loop skill. Also check:

  • First frame: eyes open, face visible. If not, suggest picking a cover frame in the app.
  • No caption page spans two sentences.
  • Cuts land between words, not mid-word (adjust --pre / --post).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free