#8484th of 118 in Agent frameworks and SDKsFor image, video and design, video and animation
stickman-video-director
Agent Skill that turns a topic or script into stickman explainer videos
- Stars
- 5.6k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- JavaScript
447 on 3 Aug 20265,567 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An installable Skill for AI assistants (Codex, Claude Code, Cursor and similar) that plans stickman videos from a topic, link or script. Director Mode produces a treatment, storyboards and per-scene prompts for an external video generator such as Google Flow, Runway, Luma or Kling. Autopilot Mode runs inside a coding agent to generate illustrated scenes, voiceover, captions and sound effects, then renders a finished video.
Who it is for: Faceless YouTube creators who already use a coding agent
Strengths
- Two workflows: prompt-only Director Mode and end-to-end Autopilot rendering for 10+ minute videos
- Ten visual styles, each with animated example clips
- Supports 9:16, 16:9 and 1:1 aspect ratios and a choice of narration language
- Script and 20-second preview approval steps before the full render
Weaknesses
- Director Mode clips must be generated in third-party video tools, then edited by hand
- Autopilot needs a coding agent with file and terminal access; results vary by agent
- Image generation and voiceover providers are not named in the visible README
- Author recommends Codex; other agents may differ from the showcase output
What it needs
- Needs Codex, Claude Code, Cursor or similar coding agent, Google Flow, Runway, Luma or Kling (Director Mode), CapCut or Premiere (Director Mode editing)
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is stickman-video-director open source?
Yes. Its code is on GitHub under the MIT license.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |