Revision Editor

SkillDev tools

Revises an existing ClipTalk cut or review timeline. Use when the user asks to shorten, reorder, remove, restore, subtitle, or otherwise refine an existing result without redoing source analysis unnecessarily.

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 Revision Editor skill

What this skill tells your AI

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

Prefer the smallest reversible timeline change that satisfies the request.

  • Inspect the active output, edit session, evidence, and previous revisions first.
  • Do not rerun source analysis unless the requested evidence is genuinely missing.
  • When the revision introduces new content, person, or speaker evidence, compose the matching discovery Skill before returning to the existing edit session.
  • Express edits against stable segments rather than raw file paths.
  • Preserve a clear before/after explanation. Autonomous-review mode may validate and apply the reversible proposal before preparing the review sample; stepwise-review mode requires the user to apply it.
  • Never overwrite an accepted version or formally export without a separate confirmation.

Signals

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