Agent Skills › jegly/Box › mood-music

mood-music

GitHub

根据用户情绪、文本或媒体内容，通过Loudly API生成匹配的音乐。支持分析图像/音频以识别氛围，并调用JS工具获取流派后合成音乐。

skills/featured/mood-music/SKILL.md jegly/Box

Trigger Scenarios

用户请求特定情绪的音乐用户询问符合某种氛围的歌单用户上传图片或音频并要求匹配音乐

Install

npx skills add jegly/Box --skill mood-music -g -y

More Options

Non-standard path

npx skills add https://github.com/jegly/Box/tree/main/skills/featured/mood-music -g -y

Use without installing

npx skills use jegly/Box@mood-music

指定 Agent (Claude Code)

npx skills add jegly/Box --skill mood-music -a claude-code -g -y

安装 repo 全部 skill

npx skills add jegly/Box --all -g -y

预览 repo 内 skill

npx skills add jegly/Box --list

SKILL.md

Frontmatter

{
    "name": "mood-music",
    "metadata": {
        "homepage": "https:\/\/github.com\/google-ai-edge\/gallery\/tree\/main\/skills\/featured\/mood-music",
        "require-secret": true,
        "require-secret-description": "you can get api key from https:\/\/www.loudly.com\/developers\/apps after registering an account"
    },
    "description": "A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API."
}

Mood Music

Instructions

You MUST use a strict two-step process to generate music. This ensures you only request musical genres that are currently supported by the Loudly API.

Step 1: Fetch Available Genres

Call the run_js tool with get_genres.html as the script name and an empty JSON payload ({}).

This will return a list of currently available genres and their descriptions.
You MUST review this list to understand the available musical palettes.

Step 2: Analyze and Generate

Once you have the valid genres, map the user's request to the best fit and call run_js with index.html to generate the track.

Handling Inputs:

Text Inputs: Translate abstract mood requests into a concrete, matching genre from the fetched list, along with an appropriate energy level.
Media Inputs (Images/Audio): If the user provides an image or audio clip, analyze the media to determine its underlying mood, atmosphere, or vibe. Translate this analysis strictly into one of the fetched genres.

Generation Payload (for index.html): Your JSON payload for index.html MUST strictly use these text fields to represent the vibe:

genre: String, Required. MUST be an exact match to a genre name retrieved in Step 1.
genre_blend: String, Optional. A secondary genre to blend (also from Step 1).
duration: Integer, Optional. Length in seconds (30-420). Default is 120.
energy: String, Optional. Vibe ("low", "high", "original").
bpm: Integer, Optional. Specific tempo in Beats Per Minute.