Content Extractor

SkillDev tools

Lets your agent find and pull together specific passages from content, like quotes, explanations, or topics.

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 Content Extractor skill

About this skill

Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.

What this skill tells your AI

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

Turn the requested subject and boundaries into a traceable content-selection plan.

  • Inspect reusable transcripts and indexes before scheduling a search.
  • Search for meaning and supporting visual evidence, not keywords alone.
  • Preserve enough context for statements and demonstrations to remain understandable.
  • Make ordering and overlap handling explicit before proposing the timeline.
  • Keep the semantic target separate from duration, variant, subtitle, aspect-ratio, and delivery instructions. Those explicit deliverables are composed after content selection rather than mixed into the search query.
  • A find-only request ends with evidence rather than creating an unrequested cut. For a combined cut, autonomous-review mode may select valid candidates and apply its timeline proposal without interrupting the user; stepwise-review mode requires candidate and timeline confirmation.
  • Autonomous-review mode must finish with a low-resolution review preview. Stepwise-review mode prepares subtitles or a review preview only when requested. Never treat a preview as a formal export.

Signals

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