Smart Reframe

SkillDev tools

Reframes a video into 9:16, 4:5, 1:1, or 16:9 using blurred background padding so no footage gets cropped.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Smart Reframe skill

About this skill

Adapts an existing accepted ClipTalk cut to 9:16, 4:5, 1:1, or 16:9 while preserving the complete source frame with blurred background padding unless the user explicitly requests cropping.

What this skill tells your AI

The instructions your AI receives, as published by gml-mmgroup/cliptalk in skills/cliptalk-smart-reframe/SKILL.md and read by ahel’s review.

Create a review-only format version from the current accepted cut.

  • Verify that the source is the active accepted output for the current task; never reuse a render, cover, or crop track from another task.
  • Honor the explicit aspect ratio. When the source and target ratios differ, preserve the complete frame at the largest readable size and fill the remaining canvas with a blurred duplicate of the same frame.
  • Keep faces, product details, subtitles, and on-screen text inside the safe area. Crop only when the user explicitly requests crop-to-fill or supplies a focal direction.
  • Keep the original accepted cut unchanged. Render a separate preview, run delivery QC on that preview, and report the fit policy and measured output ratio.

Signals

GitHub stars
128
Forks
9
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
cliptalk-smart-reframe
Source
github.com/gml-mmgroup/cliptalk