muapi-media-generation — 技能 — openclaw中文资讯站

技能详情（站内镜像，无评论）

Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5

媒体与内容

作者：Anil Chandra Naidu Matcha @anil-matcha

许可证：MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本：v1.0.0

统计：⭐ 0 · 114 · 0 current installs · 0 all-time installs

⭐ 0

安装量（当前） 0

🛡 VirusTotal ：良性 · OpenClaw ：可疑

Package：anil-matcha/muapi-media

安全扫描（ClawHub）

VirusTotal ：良性
OpenClaw ：可疑

OpenClaw 评估

The skill's scripts appear to implement the claimed muapi.ai media features, but the package metadata omits required environment variables and runtime files (schema_data.json) and so the bundle is internally inconsistent — review before installing or running with real credentials.

目的

The scripts match the stated purpose (image/video/audio generation via api.muapi.ai). However the registry metadata declares no required env vars or binaries while SKILL.md and the scripts explicitly require MUAPI_KEY, curl, jq, and python3, and the scripts expect schema_data.json for dynamic model/endpoint resolution. The missing declarations and missing schema_data.json file are incoherent with the stated quick-start and make the package inc…

说明范围

Runtime instructions and scripts operate within the expected domain (calling api.muapi.ai endpoints, uploading local files when requested, polling results, downloading outputs). They read and write a local .env file (storing MUAPI_KEY) and may upload any file the user supplies to the muapi.ai upload endpoint — which is expected for an upload utility but is sensitive behavior that should be explicit. The scripts also expect a local schema_data.…

安装机制

No install spec; this is an instruction-only skill with included shell scripts. No external archives or remote downloads are performed by the skill itself at install time.

证书

The scripts require a MUAPI_KEY API key passed via environment or stored in a .env file, but the skill metadata did not declare this required credential or the required binaries. Requiring a single API key is proportionate for the advertised functionality, but the metadata omission is an important mismatch to surface.

持久

The skill does not request elevated platform privileges or always:true. It writes a .env file and creates local output directories under relative paths; this is local persistence but limited in scope to the working directory.

安装（复制给龙虾 AI）

将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「muapi-media-generation」。简介：Generate AI images, videos, music, and audio from the terminal via muapi.ai — s…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/anil-matcha/muapi-media/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

---
slug: muapi-media
name: muapi-media-generation
version: "0.1.0"
description: Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5
acceptLicenseTerms: true
---

# 🎨 MuAPI Media Generation

**Schema-driven generation primitives for images, videos, and audio.**

Generate professional-grade media directly from the terminal using 100+ state-of-the-art AI models. All scripts are powered by `schema_data.json` for dynamic model and endpoint resolution.

## Available Scripts

| Script | Description | Default Model |
| :--- | :--- | :--- |
| `generate-image.sh` | Text-to-image generation | `flux-dev` |
| `generate-video.sh` | Text-to-video generation | `minimax-pro` |
| `image-to-video.sh` | Animate a static image into video | `kling-pro` |
| `create-music.sh` | Music creation, remix, extend, text/video-to-audio | Suno V5 |
| `upload.sh` | Upload local files to CDN for use with other skills | — |

## Quick Start

```bash
# Generate an image
bash generate-image.sh --prompt "a sunset over mountains" --model flux-dev --view

# Generate a video
bash generate-video.sh --prompt "ocean waves at golden hour" --model minimax-pro --view

# Animate an image
bash image-to-video.sh --image-url "https://..." --prompt "camera slowly pans right" --model kling-pro

# Create music
bash create-music.sh --style "lo-fi hip hop" --prompt "chill beats for studying"

# Upload a local file
bash upload.sh --file ./my-image.jpg
```

## Common Flags

All scripts support: `--async`, `--view`, `--json`, `--timeout N`, `--help`

## Requirements

- `MUAPI_KEY` environment variable (set via `core/platform/setup.sh`)
- `curl`, `jq`, `python3`