All skills
Animated ads · Advibly Skill

Stickman Animation Ads

Give your agent a brand, product, or campaign idea. It invents an original concept and beat list, locks a clean black-outline stick-figure world with one brand-color accent, renders a consistent storyboard, animates every beat with snappy limited motion, then adds narration, comic sound effects, music, and a final composition. The style stays fixed; the story is designed fresh for every brief.

Stick figure2D comic9:16Narrated
Stickman animation ad
Just ask

Say the word, it runs.

The skill fires on natural requests like these. No commands to memorize.

Make a stickman ad for my brandCreate a stick-figure animationTurn this idea into a minimalist line-animation adMake a doodle-style comic video
The pipeline

What the skill does for you.

  1. 1

    Read the brand and choose the accent

    The skill reads the brand, product, audience, and campaign angle. The brand's primary color becomes the single expressive accent in an otherwise black, white, and gray visual system.

  2. 2

    Invent and approve the story

    It develops a bespoke concept, cast, recurring props, and a beat list sized to the idea. The story can be a gag, visual metaphor, slice of life, mock demo, or problem-to-solution pitch; no stock plot is required.

  3. 3

    Render the flat storyboard

    One high-quality 9:16 still is generated per beat with uniform black outlines, flat fills, a white void, no shading, and the approved brand-color system. The first frame anchors line weight and recurring silhouettes.

  4. 4

    Animate with limited motion

    Approved frames become SFX-only clips while prompts protect the flat 2D linework from unwanted volume and shading. A step-frame pass creates the signature on-twos snap after generation.

  5. 5

    Narrate, score, and compose

    One consistent narrator reads the approved lines, music supports the arc, comic foley punctuates the action, and the assets are assembled into a finished vertical ad.

The model stack

Right model, right job.

gpt-image-2Flat vector storyboard stills
Gemini Omni FlashImage-to-video limited motion
Seedance 2.0Controlled transformation fallback
xAI TTS + MiniMax 2.6Narration and music
ffmpegOn-twos step-frame cadence
What you get

The deliverable.

  • A finished narrated 9:16 stick-figure comic ad
  • An original concept, cast sheet, and editable beat list
  • One flat storyboard still and animated clip per beat
  • Separate narration, music, and sound-designed video assets
Install

Add it in seconds.

Install the skill, then make sure the Advibly MCP is connected so it has tools to call. Works with every skills-capable agent.

Claude Code
Claude
Cursor
Codex
VS Code
OpenClaw
Hermes
ChatGPT
Connect the Advibly MCP first
One command (any agent)
npx skills add advibly/skills -s stickman-animation

Works with Claude Code, Claude Desktop, Cursor, and any agent that supports skills. Pulls straight from GitHub.

Manual (Claude Code)
git clone https://github.com/advibly/skills.git
cp -R skills/stickman-animation ~/.claude/skills/

Or in Claude Desktop: Settings → Skills → Install and select the skill folder.

Bundled references

The playbook.

Each skill ships with reference docs the agent loads on demand, so the craft is baked in.

cast-and-story.md

A creative toolkit for original concepts, characters, narrative devices, beat design, and narration timing.

storyboard-prompts.md

The locked flat-line style, color system, still-prompt scaffold, and storyboard QA rules.

animate-prompts.md

Motion prompts that preserve flat linework, control comic action, and keep clips speech-free.

audio-and-gotchas.md

The on-twos post pass, narration and music workflow, SFX direction, and common failure fixes.

Honest limits

What to watch for.

  • The visual system is intentionally strict: black outlines, white field, gray problem accent, and one brand-color accent.
  • Products are redrawn as flat 2D props rather than inserted as photoreal objects.
  • The authentic limited-animation cadence requires a local step-frame pass after smooth model generation.
  • Narration is generated separately; video clips remain dialogue-free so voices do not change between beats.