Person Editor

SkillDev tools

Creates cuts based on who appears on screen. Use when the user wants to keep, remove, follow, or compare visible people rather than select by spoken content alone.

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

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Person Editor skill

What this skill tells your AI

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

Discover visual identities before editing by person.

  • Reuse a compatible person catalog and saved selection when their source and analysis revisions still match; otherwise schedule discovery or confirmation.
  • Require structured user confirmation before binding a discovered face to a requested person.
  • Keep identity uncertainty visible and never infer a real name from appearance.
  • Preserve explicit include, exclude, compare, or per-person rules instead of converting every request into an include operation.
  • Propose the timeline from confirmed rules. Autonomous-review mode may validate and apply that proposal and finish with a review sample; stepwise-review mode requires the user to apply the draft.
  • Identity confirmation does not authorize a preview, render, or export that the user did not request.

Signals

GitHub stars
126
Forks
8
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
cliptalk-person-editor
Source
github.com/gml-mmgroup/cliptalk