Music Search Skill

Search for music resources (songs, albums, lossless music), crawl resource pages deeply through real-time crawlers, and obtain publicly shared resource links from various cloud drive platforms.

Prerequisites

web-search skill (required, used to search and discover resource pages)
Python 3 (required, used for deep page crawling with cloudscraper. Dependencies are automatically installed to
```
.venv
```
on first run)

Commands

Search Resources

bash

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "关键词" [选项]

Options:

Parameter	Description	Default Value
`--pan <type>`	Filter cloud drive type: `quark` , `baidu` , `aliyun` , `uc` , `all`	`all`
`--format <f>`	Filter audio format: `flac` , `ape` , `wav` , `dsd` , `hires` , `mp3` , `aac` , `all`	`all`
`--limit <n>`	Maximum number of results per platform	`5`
`--engine <e>`	Search engine: `deep` , `web`	`deep`

Engine Description:

```
deep
```
(default, recommended) — web-search to discover resource pages + cloudscraper deep crawling to extract cloud drive links and access codes, most accurate results
```
web
```
— Extract links only from web-search engine snippets (fast, but lower accuracy, no deep crawling)

Examples:

bash

# 搜索所有平台的音乐资源（默认使用深度搜索）
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西"

# 只搜夸克网盘 FLAC 资源
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西" --pan quark --format flac

# 搜索 Hi-Res 高解析音乐
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "邓紫棋 光年之外" --format hires

# 限制结果数量
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "林俊杰 她说" --limit 10

# 使用浅层搜索（不深度抓取页面）
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "陈奕迅 十年" --engine web

For Windows systems, use the PowerShell script:

powershell

powershell -File "$SKILLS_ROOT/music-search/scripts/music-search.ps1" search "周杰伦 范特西" --pan quark

Hot Recommendations

bash

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" hot "2025年热门专辑"

It essentially calls the search with recommendation keywords and returns relevant cloud drive resources.

Parse Redirect Links

bash

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" resolve "https://example.com/goto/xxx"

Use this command to parse the real cloud drive address when the link in the search results requires secondary redirection.

Agent Usage Process

User says "Help me find XXX's music" → Execute
```
search "XXX"
```
Parse the returned JSON and extract cloud drive links
Group and present to users by cloud drive type and audio format
If there is an access code (
```
extractCode
```
) in the result, display it to the user together
If there is a
```
pageUrl
```
but no direct
```
url
```
in the result, use the
```
resolve
```
command to get the real address

Sample Conversation:

User: Help me find the lossless resources of Jay Chou's Fantasy album, in FLAC format

Agent:
Execute
search "周杰伦 范特西" --format flac
Extract matching items from JSON results

Return: Title + Format + Cloud drive link + Access code (if any)

Output Format

All commands output JSON with the following structure:

json

{
  "success": true,
  "data": {
    "query": "周杰伦 范特西",
    "total": 5,
    "results": [
      {
        "title": "资源标题",
        "pan": "quark",
        "url": "https://pan.quark.cn/s/xxx",
        "format": "FLAC",
        "extractCode": "ab12",
        "source": "deep-search",
        "pageUrl": "https://example.com/resource/123"
      }
    ]
  }
}

Field Description:

```
pan
```
: Cloud drive type —
```
quark
```
(Quark),
```
baidu
```
(Baidu),
```
aliyun
```
(Alibaba),
```
uc
```
(UC),
```
magnet
```
(Magnet)
```
format
```
: Detected audio format —
```
FLAC
```
,
```
APE
```
,
```
WAV
```
,
```
DSD
```
,
```
Hi-Res
```
,
```
AIFF
```
,
```
MP3
```
,
```
AAC
```
,
```
OGG
```
, empty string means not detected
```
source
```
: Result source —
```
deep-search
```
(Deep crawling),
```
web-search
```
(Search snippet)
```
url
```
: Cloud drive sharing link (directly accessible)
```
extractCode
```
: Access code/password (if detected)
```
pageUrl
```
: Result source page URL

Configuration

Edit

music-search/.env

to customize preferences:

bash

# 偏好的网盘类型（逗号分隔，排在前面的优先展示）
MUSIC_SEARCH_PREFERRED_PAN=quark,aliyun,baidu,uc

# 深度搜索开关（推荐开启）
MUSIC_SEARCH_DEEP_ENABLED=true

# 每次搜索最多访问的结果页面数
MUSIC_SEARCH_DEEP_MAX_PAGES=6

# 并发抓取页面数
MUSIC_SEARCH_DEEP_CONCURRENCY=4

Notes

It is recommended to use Chinese singer name + album name or song name for search, which gives the best results
Deep search (
```
--engine deep
```
) takes 2-3 seconds more than shallow search, but the results are much more accurate
Python cloudscraper will be automatically installed to
```
.venv
```
on first use (Python 3 required)
Deep search requires web-search skill to be enabled, first search may need to wait for browser startup
Cloud drive sharing links may expire at any time, it is recommended to use them as soon as possible

Disclaimer

This tool is for personal learning and research use only. It does not host, distribute, or provide any copyrighted content, only aggregates publicly accessible links on search engines. Please comply with the laws and regulations of your region.

music-search

NPX Install

Tags

SKILL.md Content (Chinese)

Music Search Skill

Prerequisites

Commands

Search Resources

Hot Recommendations

Parse Redirect Links

Agent Usage Process

Output Format

Configuration

Notes

Disclaimer