Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Stick Reel — Animated Stories & Shorts

    1

    Fast and lightweight models (Gemini Flash, Claude Haiku, GPT-4o-mini) produce the exact same studio-quality animation as large frontier models.

    $2.49

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Stick Reel — Animated Stories & Shorts

    Stick Reel — Animated Stories & Shorts

    Example session with this skill installed

    Create a 30-second stick figure reel explaining why compound interest is powerful. Use a teacher character and a student. Narration should be female.

    • Read your context and instructions
    • Compiled the stick reel
    • Generated the image

    I have drafted the script for the compound interest reel and initialized the project. I will use the "chandrika" voice for the narration.

    SceneNarrationAction
    1Imagine a single penny doubling every day for a month.Teacher points to a penny prop.
    2By day thirty, you have over ten million dollars.Student acts surprised, eyes wide.
    3That is the power of compound interest working for you.Teacher cheers, text "10M+" appears.

    Reel Project: compound-interest

    {
      "slug": "compound-interest",
      "cast": {
        "teacher": { "hair": "bun", "color": "blue" },
        "student": { "hair": "short", "color": "red" }
      },
      "scenes": [
        {
          "say": "Imagine a single penny doubling every day for a month.",
          "set": "classroom",
          "actors": [
            { "id": "teacher", "x": 30, "facing": "right", "action": [{ "at": "penny", "do": "point_up" }] }
          ]
        },
        {
          "say": "By day thirty, you have over ten million dollars.",
          "set": "classroom",
          "actors": [
            { "id": "student", "x": 70, "facing": "left", "action": [{ "at": "ten", "do": "shock" }] }
          ],
          "text": [{ "content": "$10,737,418", "at": "million" }]
        }
      ]
    }
    

    Next steps

    1. Run node src/build.mjs to validate the story structure.
    2. Execute src/voice.sh to generate the Sarvam narration tracks.
    3. Review the QA snapshots in videos/compound-interest/qa/sheet.jpg before final render.

    sheet.jpg

    PNG · 1536×1024

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stick Reel — AI-Powered Animated Stick Figure Stories

    stick-reel is an agent skill that produces smooth, studio-quality animated stick-figure story reels and shorts (Instagram Reels, YouTube Shorts, and TikTok, 1080×1920 vertical, 25–60s) using HyperFrames.

    Just ask your agent for a reel on any topic — the agent writes a concise script and a single story.json file. A bundled deterministic animation engine (stick.js) brings it to life with full character rigs, natural walk cycles, facial expressions, lip sync, props, dynamic camera moves, scene transitions, voiceover, and procedural sound effects.

    🌟 Key Highlights

    • Model-Agnostic Quality: The LLM never writes animation code or fragile CSS/HTML — it only outputs a validated JSON story format. Fast and lightweight models (Gemini Flash, Claude Haiku, GPT-4o-mini) produce the exact same studio-quality animation as large frontier models.
    • Full Character Rig & Animation:
      • Over 48 built-in poses, hand gestures, and body postures.
      • Procedural walk cycles with realistic easing, stride calculation, and follow-through.
      • Expressive faces (happy, sad, shock, smirk, thinking) with synchronized talking mouth cycles.
      • Natural left/right/front facing turns and inverse-kinematic reach.
    • Cinematic Production:
      • Seamless transitions: whip pans, slides, zooms, dissolves, cuts.
      • Dynamic camera work: pushes, pulls, pans, and tracking.
      • Multi-layer sets with interactive props, furniture, vehicles, and text callouts.
      • Built-in safe-zone validation for mobile feeds.
    • Sound & Voice Integration:
      • Automatic voiceover synthesis (integrated with Sarvam AI or custom WAV audio).
      • Word-level cue timing: character actions sync frame-perfectly to spoken words.
      • Procedural SFX generation (pops, whooshes, thuds) and soft background music beds.

    🚀 Example Prompt

    Once installed in your agent (Claude Code, Gemini CLI, Cursor, Codex, OpenClaw), simply ask:

    "Make a stick figure reel about why humans procrastinate." "Create a 45-second animated reel explaining compound interest with stick figures."

    The agent handles scriptwriting, staging, pacing, cue timing, audio synthesis, and final MP4 rendering automatically.


    ⚙️ Requirements

    • Node.js: 18+ (rendering uses npx hyperframes, downloaded on first run)
    • ffmpeg: for video encoding and audio merging
    • Python 3 (optional, for voice & SFX): numpy, soundfile, scipy (pip install -r requirements.txt)
    • Voiceover: Works out of the box with Sarvam AI key (SARVAM_API_KEY) or by dropping WAV files into assets/vo/.

    Requires Sarvam API key for voice. Limited to cataloged poses/props. Vertical 1080x1920 only. Needs Node.js 18+ and ffmpeg. Audio synthesis requires specific Python libraries.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 17 days ago

    Requires

    Sarvam
    hyperframes
    Node.js
    Python

    Permissions

    Terminal / Shell
    Environment Variables
    Network Access

    Allowed Hosts

    sarvam.ai

    Optional neural TTS voiceover generation via Sarvam AI API (https://api.sarvam.ai/text-to-speech ). Only spoken narration lines from story.json are sent. Animation and video rendering operate 100% locally and offline when voiceover is not used."

    Listed18 days ago
    Updated17 days ago

    What's inside

    Frequently Asked Questions

    Every model! Because the agent only writes a validated story.json while the bundled engine handles physics, kinematics, easing, and video rendering, lightweight models (like Gemini Flash, Claude Haiku) generate the exact same smooth, high-fidelity animation as large frontier models.

    It exports vertical 9:16 (1080×1920) MP4 video at 30/60 fps, perfectly formatted for Instagram Reels, YouTube Shorts, and TikTok. A typical reel runs between 25 and 60 seconds.

    No. You and your agent never edit HTML or animation code. The agent writes narration and cues in a clean JSON structure, and the bundled engine handles all rigging, walk cycles, camera transitions, and rendering automatically.

    New in Image & Video