- Home
- Skills
- Agents & Orchestration
- moshFilm
Works with the AI Agents you already use
moshFilm
Build and edit short motion-graphics films via CLI with synced narration, sound effects, and responsive SVG scenes.
Free
moshFilm
Example session with this skill installed
Create a 3-scene film about the benefits of renewable energy. Start by proposing the scenes based on a calm tone.
- Read your context and instructions
- Compiled the moshfilm
I have analyzed the topic and prepared a 3-scene proposal for the renewable energy film.
Film Proposal: Benefits of Renewable Energy
| Scene ID | Title | Narration Text | Length | Status |
|---|---|---|---|---|
| s1 | The Sun's Power | Solar energy provides a clean, infinite source of power for our planet. | 6s | planned |
| s2 | Wind and Water | Harnessing natural flows creates electricity without carbon emissions. | 7s | planned |
| s3 | A Green Future | Transitioning today ensures a sustainable world for generations to come. | 6s | planned |
I have submitted this proposal to the editor.
Next steps
- Review and Approve the proposal in the moshFilm chat panel.
- I will then begin writing the
scenes/s1.jslogic and setting the "building" status. - Once approved, I'll also configure a
calmmusic bed to match the tone.
Connects securely to your tools. The creator never sees your data.
About this skill
Video production is often slowed down by the friction between scripting, motion design, and asset management. This skill bridges that gap by allowing you to build short motion-graphics films directly through a browser-based editor and command-line interface.
What it does
- Scene Orchestration: Translates scripts and documents into structured scene lists with voice narration and timing.
- Dynamic Scene Writing: Generates ES modules using DOM, SVG, and CSS to create deterministic, responsive motion graphics.
- Narration Syncing: Manages voice-over generation and ensures scene lengths align perfectly with spoken audio.
- Multi-Shape Layouts: Validates and adjusts visuals to fit various aspect ratios including 16:9, 9:16, 1:1, and 4:5.
- Audio Integration: Layers music beds and sound effects based on mood, tempo, and visual cues.
How it works
- Initialize: Use
moshfilm opento launch the editor andmoshfilm watchto establish a real-time connection for chat and events. - Propose: Submit a JSON scene list for approval, defining the narrative flow and duration.
- Develop: Write scene logic in
scenes/*.jsfiles using thesetupandrenderlifecycle methods. - Audit: Run
moshfilm checkto catch layout overflows, non-deterministic code, or audio timing conflicts. - Finalize: Generate narration with
moshfilm voiceand export the final MP4 or GIF.
Frameworks & tools
The skill utilizes a custom CLI tool, moshfilm, for orchestration. Scenes are written in vanilla JavaScript (ES modules) using standard Web APIs for rendering, specifically DOM and SVG.
Why this beats prompting it yourself
Writing motion graphics code requires strict adherence to deterministic rendering and responsive layout math that generic prompts often ignore. This skill handles the boilerplate of state management, coordinate scaling, and audio-visual synchronization that manual prompting misses.
Use cases
- Generating social media clips from blog posts or articles.
- Creating automated technical explainers with synced narration.
- Rapidly prototyping motion graphic concepts in multiple aspect ratios.
- Building data-driven animations using CSS and SVG.
Known limitations
Requires the moshfilm CLI to be installed and available on the system PATH. Does not support external libraries, network assets, or non-deterministic APIs like Math.random.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires moshfilm CLI. No external JS libraries or network assets allowed. Scenes must be deterministic. Pinned user edits take precedence over agent changes.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 days ago
- Free with an Agensi account
- Accounts
GitHub
Vuejs
Evil
0
- Software
Python
Git
Permissions
Allowed Hosts