Generate Asset

Documents

generate-asset

Generate Asset is an Agent Skill for documents published in the SamurAIGPT/muapi-cli repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generate a single media asset — image, video, audio, or 3D. Use when the user wants one output from a clear prompt. Calls muapi_select to pick the best model, then muapi_generate.

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/SamurAIGPT/muapi-cli/blob/HEAD/integrations/langchain/examples/creative-agent/skills/generate-asset/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/generate-asset, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Generate Asset

Use this skill for single-asset generation tasks.

Step 1 — Discover

Call muapi_select with the user's intent and kind:

muapi_select(intent="<user's prompt>", kind="<image|video|audio|3d>", tier="<best|balanced|fast>", limit=3)

Pick the top-ranked model from the result.

Step 2 — Generate

Call muapi_generate with the chosen model:

muapi_generate(
    prompt="<refined prompt>",
    kind="<kind>",
    model="<name from muapi_select>",
    tier="<best|balanced|fast>",
)

For edits, enhancements, image-to-video, or lipsync — pass input_asset_url too.

Step 3 — Return

Report the asset URL to the user. Include: model used, kind, and any relevant parameters.