Multi-topic Assembler

SkillDev tools

Lets your agent assemble video clips that cover every required topic or category and reports any that are missing.

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 Multi-topic Assembler skill

About this skill

Builds balanced clips from multiple required topics or categories, such as one segment per appliance, speaker, product, feature, or scene type, and reports missing categories instead of filling with unrelated footage.

What this skill tells your AI

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

Create a reviewable timeline where each requested category is represented by reliable evidence.

  • Parse category requirements from the user's words and keep them as required branches.
  • Search once when the current task lacks compatible evidence, then select per-category candidates from reliable matches only.
  • If a required category is missing, stop with a structured evidence gap; do not use unrelated scenes, filler, or "possible" matches to satisfy the category.
  • When a total duration is explicit, distribute it across categories and expand around evidence anchors while respecting source boundaries.
  • Preserve source order unless the user asks for a narrative order.
  • Aspect ratio, subtitles, cover, and QC are delivery add-ons after the category selection is stable.

Signals

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