ClipTalk Local Motion Renderer
SkillWeb & browsingLets your agent create animated video clips like title cards and intros using local HTML and FFmpeg rendering.
Available today. Use it from your connected AI after setup.
No other account needed.
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 ClipTalk Local Motion Renderer skill
About this skill
Generate local motion-graphics clips such as title cards, animated intros, visual explainers, and cover motion using the built-in HTML/Playwright/FFmpeg pipeline without external APIs.
What this skill tells your AI
The instructions your AI receives, as published by gml-mmgroup/cliptalk in skills/cliptalk-local-motion-renderer/SKILL.md and read by ahel’s review.
Use this skill when the user asks for Remotion-like, HyperFrames-like, HTML video, animated text, title-card, intro, dynamic cover, or visual explainer assets that can be rendered locally.
Hard boundaries:
- Do not call cloud rendering, TTS, music, image-generation, or video-generation APIs.
- Produce a separate local motion clip unless the user also asks to merge it into an existing cut; when they do, use
compose_motion_introto create a new output version. - Keep the output as an auditable preview artifact; formal delivery still needs the delivery-export skill.
- Prefer the project’s ClipTalk visual identity, dark UI palette, readable Chinese typography, and safe-area margins.
Execution:
- Inspect the workspace only to confirm the current task and any requested aspect ratio.
- Render the motion clip with
render_motion_graphics. - If the user asked for a motion intro on the current cut and the workspace has an output, compose it with
compose_motion_intro. - Run
run_delivery_qcon the generated local clip or composed output.
Signals
- GitHub stars
- 128
- Forks
- 9
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
cliptalk-local-motion-renderer- Source
- github.com/gml-mmgroup/cliptalk