Stickman Video Director: stickman videos from a topic or script
kaomei/stickman-video-director
Your AI assistant turns a topic, an article or a script into a stickman video for YouTube or TikTok. In one mode it writes the story and shot-by-shot prompts that you paste into a video generator yourself. In the other it makes a finished video with voice, captions and sound effects on your computer, after you approve the script and a short sample.
Pack description by its author: “Your AI assistant turns a topic, an article or a script into a stickman video for YouTube or TikTok. In one mode it writes the story and shot-by-shot prompts that you paste into a video generator yourself. In the other it makes a finished video with voice, captions and sound effects on your computer, after you approve the script and a short sample.”
Video, images and mediaKnowledge and rules for your assistantGives your assistant new abilities with scripts
1. Changes your files
Skills that write or edit files: directing-stickman-videos · B Autopilot.
github.com/kaomei/stickman-video-director/blob/8658f9e/2. Runs code on your machine
Install: No install hook, no background task. Nothing runs until the assistant runs a script. Autopilot setup (npm ci): Installs @napi-rs/canvas 0.1.100 and sharp 0.35.5 into the skill folder; this downloads packages from npm.
github.com/kaomei/stickman-video-director/blob/8658f9e/3. Sends data
The finished-video mode runs bundled Node and Python scripts and installs two npm packages; read them before use. Keep API keys in environment variables. The A6 Renoise route uses a promotion link from the pack.
github.com/kaomei/stickman-video-director/blob/8658f9e/4. Commercial use
MIT: keep the copyright and license notice
github.com/kaomei/stickman-video-director/blob/8658f9e/Checked against the pack's files at commit 8658f9e, on Nov 12, 2026. Tap a verdict to see its source.How we checkedReport an error
The pack has changed since AgentGid checked it on Nov 12, 2026. Some details may be out of date.
Good for you if
- You run or plan a YouTube channel without showing your face and want animated stickman explainers or stories
- You have a topic, a link or a script and want a story plan, scene prompts or a finished narrated video from it
- You use Codex, Claude Code, Cursor or another assistant that can work with files
Probably not for you if
- You want a finished video but your assistant can only chat: the full video needs an assistant that works with files and runs programs
- You don't want to pay for any outside service: pictures, voice and video clips come from services you connect and pay for yourself
What you'll notice
- Questions first: screen shape (16:9 or 9:16), length and one of 11 named styles, such as A3 Prehistoric Cave or B1 Minimal Line Art
- It stops for your approval: a story plan before prompts, or a script and a 20-second sample with sound before the full video
- Before anything that costs money, it says what it will call and asks first
- After you accept the final video, one offer of a matching thumbnail, five titles, a description and a pinned comment
What you need
- Codex, Claude Code, Cursor, Antigravity
- Mixed, MIT license
- Ask your assistant to install it from the GitHub link; it reads the instructions and walks you through setup
- The story-and-prompt mode needs no keys. The finished-video mode needs Node.js 20 or later, FFmpeg and a picture and voice service you choose (for example Google Gemini with an API key, or ai33/ElevenLabs for the B4 style).
Words on this page
- Skill
- A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
- API
- A way for programs to talk to a service, usually with a key.
- MCP
- A standard way to connect an AI assistant to outside tools and data.
- CLI
- A program you run by typing commands in a terminal.
| Repository | kaomei/stickman-video-director |
|---|---|
| Also on AgentGid | Stickman Video Director as an agent: usage, releases and alternatives |
| GitHub stars | 6,355 |
| Skills | 1 · 1 with scripts |
| Category | Video, images and media |
| License | MIT |
| Last updated | Nov 14, 2026 · card checked Nov 12, 2026 at commit 8658f9e |
| Install counts | kaomei/stickman-video-director on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
kaomei/stickman-video-director popularity over time
What Stickman Video Director does
- One skill, two modes. A · Director plans the story and writes standalone video prompts; B · Autopilot builds a finished MP4
- Director: asks for screen shape, length (in 10-second steps, 60 seconds by default) and style, writes a proposal and stops for approval, then writes one prompt per roughly 10-second clip
- Director scripts follow a five-stage arc: hook, broken assumption, hidden mechanism, main truth, closing question
- Autopilot: script and voice plan, a configuration check, a 20-second sample with sound, then the full video after you approve that sample
- Autopilot renders on your computer with bundled Node scripts and FFmpeg; pictures and voice come from the services you connect
- Optional finishing for both modes: thumbnail, five titles, description and tags, a pinned comment and a pre-publish checklist
Never cut, per the skill: narration and synchronized subtitles in every Autopilot video; your approval of the exact sample before the full render; asking before any paid call.
From the pack's SKILL.md files, summarised by AgentGid.
The 3 skills, explained
directing-stickman-videos · A Director
Writes the story plan and shot-by-shot prompts; you make the clips and edit them yourself
You give
- A topic, copy or brief
- Screen shape: 16:9 or 9:16
- Length in 10-second steps (60 seconds if you don't say)
- A style: A1 to A6
You get
- Director's proposal: title, hook, narration in English with a translation, voice plan, colours, music and a scene table
- After your approval: one standalone prompt per clip
- A stitching guide for joining the clips
directing-stickman-videos · B Autopilot
Makes a finished narrated video with captions and sound effects on your computer
You give
- A topic, article, post, news link or script
- Length, screen shape and a style: B1 to B5
- Narration language and voice (English and a default voice if you don't say)
- Access to a picture and a voice service
You get
- A short script and voice plan to approve
- A 20-second sample with sound
- The full MP4 with subtitle files (SRT/VTT)
- A contact sheet, a verification report and the project folder
directing-stickman-videos · Thumbnail & Publishing Kit
Makes a matching cover and the text you paste into YouTube Studio
You give
- Your approved video, or its approved script for drafts
- The publishing language
You get
- One 16:9 thumbnail image (when an image tool is available and its cost approved)
- Five title options
- Description, tags and checked timestamps
- One pinned-comment question
- A pre-publish checklist with pending items marked
Its rules, in pictures
The page it plans
Fonts it uses
B1 Minimal Line Art paper and the red headline accent in its bundled example
Drawn by AgentGid from the values in the skill's files. This is not output of the skill; sample text is ours.
See it in action
The skill defines what its answer looks like. Its own example:
A runnable B1 Minimal Line Art project with the author's bundled narration (narration.m4a) and hand-drawn art: timed captions ("Want a YouTube channel without being on camera?", "Start with a stick figure."), shots with text, pose and image layers that slide and tilt, and sound cues. It shows the project format the renderer reads; it is not a new showcase video.
From skills/directing-stickman-videos/examples/b1/project.json.
The skill defines what its answer looks like. Its own example:
A worked example from a short Chinese source about overthinking: the setup question, then a 16:9, 60-second proposal on a black background with white stickmen. It names three accent colours, a voice profile, a music plan that switches tempo at 0:40, an emotion curve and a timed scene table with English narration, followed by the clip prompts.
From skills/directing-stickman-videos/references/examples.md.
When to reach for it
| You want | Use |
|---|---|
| Shot prompts for Google Flow or another video tool | A · Director, styles A1–A5 |
| A cinematic amber-and-shadow story made from generated clips | A6 Amber Noir (Google Flow in the browser or the Renoise service) |
| A finished long narrated explainer with captions | B · Autopilot, B1 Minimal Line Art or B2 Colorful Hand-Drawn |
| A suspense or survival story | B4 Survival Thriller |
| An avatar presenter beside stickman comedy | B5 Character Explainer |
| A cover | Thumbnail & Publishing Kit |
Skills in kaomei/stickman-video-director
| Skill | In plain words | Changes files? | What it does (author) |
|---|---|---|---|
| directing-stickman-videos | — | — | Turn topics, requirements, articles or scripts into stickman videos. Director mode creates approved storyboards and standalone video prompts; Autopilot mode produces narrated, captioned illustration-and-micro-animation videos through configured generation tools and a local renderer. Also guide… has scriptsnpx skills add kaomei/stickman-video-director --skill directing-stickman-videos |
The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.
Good to know before you install
- Two modes, two kinds of help: A gives you prompts to paste into a video tool such as Google Flow; only B delivers a finished video file.
- Outside services cost money and need your own accounts: Gemini for pictures and voice, ai33/ElevenLabs for the B4 narrator, Google Flow or Renoise for A6 clips. The assistant asks before each paid call.
- Finished-video mode installs two packages (sharp and a canvas library) into the skill folder and needs Node.js 20+ and FFmpeg on your computer.
- Your project files live in a separate folder, not inside the installed skill.
- Nothing is uploaded or published for you; you copy the cover and text into YouTube Studio yourself.
- Use only avatars and characters you have rights to. The B5 example uses a Spider-Man-inspired presenter, and the pack grants no rights to it.
Before you start
Works in
- Codex: skills folder (agents/openai.yaml included)
- Claude Code, Cursor, Antigravity: skills folder
- Chat-only assistants: Director mode only
You will need
- Node.js 20+: Autopilot renderer
- FFmpeg and FFprobe: Encoding and probing media
- A picture and voice service (e.g. Gemini API key): Autopilot pictures and narration; the bundled adapter needs GEMINI_API_KEY
- Python with openai-whisper (optional): Word timing for captions
Steps only you can do
- Choose and sign in to a picture and voice service (for example create a Gemini API key and set GEMINI_API_KEY) (skills/directing-stickman-videos/references/autopilot-runtime.md)
Then: The assistant runs the optional Gemini script or another route you chose, after you approve the cost - For B4, register or log in at ai33 and approve credit use for the Brian voice (skills/directing-stickman-videos/references/b4-audio-direction.md)
Then: The assistant records the narration with that voice - For A6, sign in to Google Flow in the browser, or install and authorize the Renoise MCP server yourself (skills/directing-stickman-videos/references/amber-noir.md)
Then: The assistant generates the clips and assembles the film - Install Node.js 20+ and FFmpeg if missing (skills/directing-stickman-videos/references/autopilot-runtime.md)
Then: The assistant runs npm ci and the doctor check - Watch and approve the 20-second sample, then the final video (In the chat)
Then: The assistant renders the full film, then offers the thumbnail kit
Mistakes to avoid
Expect a finished video from Director mode
Pick Autopilot (B) for a video file; Director gives prompts you paste into a video tool
Director's output is prompts, not generated videoRun Autopilot in a chat-only assistant
Use Codex, Claude Code or Cursor with file access and command execution
Autopilot renders locally and needs files and commandsPaste an API key into the chat
Put it in an environment variable such as GEMINI_API_KEY
The pack forbids pasted keysRecord approval and render the full film because the sample encoded fine
Let the person watch and approve the exact 20-second sample first
Approval binds the reviewed sample and must come from the personTreat a set Gemini key or a passing doctor check as proof generation works
Report login, model access, quota and billing as not yet verified
doctor only checks local tools and key presence
Which one to pick
| If you need | Pick |
|---|---|
| You want stickman explainers or stories for a faceless channel, as prompts or a finished narrated video | This pack |
| You want a black-canvas narrated explainer from a topic in one Claude Code or Codex skill | Vincentwei1021/anything2explainer |
| You want polished product promo videos built with Remotion | Vincentwei1021/video-shotcraft |
| You want short single-file canvas animations in any style | cth9191/animate |
Works well with
- openai-codex: The author made and tested the showcase videos in Codex
- claude-code: Autopilot runs in agents with file access and commands, Claude Code included
- ffmpeg: The local renderer encodes the MP4 with FFmpeg
- google-veo: A6's verified sample used Veo 3.1 Fast clips in Google Flow
May I use it like this?
| Use | Answer | Condition |
|---|---|---|
| In a commercial app | Yes | MIT: keep the copyright and license notice |
| Work for clients | Yes | MIT for the pack; provider-generated media follow each service's terms |
| Passing the files on | With conditions | MIT for code and original B1 art; keep the SIL OFL font notices, the Lucide license and the Kevin MacLeod CC BY 4.0 credit for the B5 example; third-party characters are not licensed |
What leaves your machine
- Approved narration text or an image prompt, plus reference images you pass with --reference → Google Gemini API (generativelanguage.googleapis.com), Only when the optional gemini-media.mjs script runs with --allow-network. Opt out: Use another tool or your own recordings and images; the renderer accepts local files
- Narration script, prompts and reference images → The services you choose (ai33/ElevenLabs for B4, Google Flow or Renoise for A6), Only during generation you approved. Opt out: Choose another provider or supply your own recordings
- A Whisper model download → Your computer, from the Whisper model host, Only with align_captions.py --allow-model-download. Opt out: Supply aligned captions or a cached model
Install Stickman Video Director
Official commands from the repository
The README gives no install command. It asks you to send the repository link to your assistant and ask it to install the skill; the skill folder is skills/directing-stickman-videos. Codex reads agents/openai.yaml for the display name and default prompt.
Remove: delete the installed directing-stickman-videos folder
Director mode works in a normal chat window; Autopilot needs file access and commands.
Or with the open-source skills CLI: npx skills add kaomei/stickman-video-director. Skills are instructions your agent follows: read them before installing.
What it installs and runs on your machine
Read in the code at commit 8658f9e, Nov 12, 2026
| When | What happens |
|---|---|
| Install | No install hook, no background task. Nothing runs until the assistant runs a script. |
| Autopilot setup (npm ci) | Installs @napi-rs/canvas 0.1.100 and sharp 0.35.5 into the skill folder; this downloads packages from npm. |
| node scripts/autopilot.mjs doctor | Checks Node, FFmpeg, FFprobe, fonts and whether GEMINI_API_KEY is set. No network, key value never printed. |
| init / validate / preview / approve / render | Reads a declarative project.json and writes the MP4, SRT/VTT, contact sheet, report, shot cache and checkpoint into the project's output/ folder; FFmpeg is called locally. Remote URLs and code in the project file are rejected. |
| gemini-media.mjs speech|image (optional) | One POST to Google's Gemini API per call with your narration text or image prompt (and reference images only if passed). Refuses to run without --allow-network and GEMINI_API_KEY; writes a .request.json receipt next to the output. |
| align_captions.py (optional) | Local Whisper word timing; reads the model from ~/.cache/whisper and downloads it only with --allow-model-download. |
| B4, B5 and A6 checks | Local checks and renderers (opening-audio check, production ledger, style lock, B5 character renderer, A6 finishing with Pillow). No network calls found in these scripts. |
| Director mode (A1–A5) | Text only. Nothing runs. |
The author's numbers, as reported
AgentGid did not run these tests
- Hundreds of channels monetize stickman narrative videos under the YouTube Partner Program. Source
Settings
GEMINI_API_KEY: Key for the optional Gemini speech and image script; read from the environment, never pasted in chatFFMPEG: Path to the ffmpeg executableFFPROBE: Path to the ffprobe executableAUTOPILOT_FONT: Font file for captions and text
Quick answers
- Is it free?
- The pack is MIT-licensed and free. The picture, voice and video services you connect are paid by you.
- Does it work in a normal chat without a terminal?
- Director mode, yes. Autopilot needs an assistant that can read and write files and run commands.
- Will it upload to YouTube for me?
- No. You copy the cover and text into YouTube Studio or TikTok yourself.
- Does it send my data anywhere?
- Only when you choose a service: the optional Gemini script sends your narration text or image prompt to Google, and only with --allow-network and your key set. Director mode runs no code.
- Are the videos safe to monetize?
- The author says many channels monetize such videos, but the pack's own checklist says Content-ID and monetization eligibility cannot be certified.
Checked by AgentGid on Nov 12, 2026 against commit 8658f9e of the pack's own files. agent.md for AI agents · Report a mistake
More video, images and media skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
OpenMontageInc/OpenMontage Your AI coding assistant becomes a small video studio. You describe a video in plain words; it researches the topic, writes the s…
|
92 | 80.6K | 2026-11-09 |
| 2 |
emilkowalski/skills Fifteen design playbooks for your AI assistant, most of them about animation. It builds animations with set speeds and curves, sa…
|
19 | 57K | 2026-11-13 |
| 3 |
latent-spaces/brag Your AI assistant turns a project you built into a 15 to 25 second launch video. It reads your project, writes a plan and a story…
|
2 | 21.5K | 2026-10-23 |
| 4 |
Vincentwei1021/video-shotcraft Your AI assistant turns your website or app into a short promo film. It screenshots your real pages and picks camera moves from a…
|
1 | 19.8K | 2026-11-11 |
| 5 |
greensock/gsap-skills Eight reference guides from the makers of GSAP, a JavaScript library for animating websites. Your assistant learns how to write G…
|
8 | 18.5K | 2026-07-29 |
| 6 |
lemomo-ai/lemo-opuscar A toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo fi…
|
1 | 16.4K | 2026-11-12 |