cocoloop-skill-fetcher
Fetches all skill listings from CoCoLoop hub (api.cocoloop.cn) with pagination and saves name, subtitle, brief, category and URL to a file. Invoke when the user wants to query, export or back up CoCoLoop skills.
来源信息
- 仓库
- smart-open/skills
- 最近来源活动
- 2026年7月24日 07:25
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 12
- 分支
- 1
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
文件资源管理器
2 个文件正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- cocoloop-skill-fetcher
- description
- Fetches all skill listings from CoCoLoop hub (api.cocoloop.cn) with pagination and saves name, subtitle, brief, category and URL to a file. Invoke when the user wants to query, export or back up CoCoLoop skills.
# CoCoLoop Skill Fetcher
Fetches the complete skill catalog from the CoCoLoop store API and writes it to a local text file.
## What it does
- Paginates through `https://api.cocoloop.cn/api/v1/store/skills`
- Extracts: `name`, `subtitle`, `brief`, `category`, `id`
- Builds per-skill page URL: `https://hub.cocoloop.cn/skills/{id}`
- Outputs one skill per line, tab-separated, to `skills.txt`
## Usage
Run the helper script from the skill directory:
```bash
node .trae/skills/cocoloop-skill-fetcher/scripts/fetch.js
```
The script will:
1. Auto-detect total pages from the API
2. Fetch 100 items per page
3. De-duplicate by skill id
4. Write results to `skills.txt` in the current working directory
## Output format
```
name\tsubtitle\tbrief\tcategory\turl
```
Example line:
```
Self-Improving Agent\t让AI记住教训，不再重复犯错\t安全的自改进日志系统...\t专业技能\thttps://hub.cocoloop.cn/skills/12277
```
## Parameters
- `pageSize` — items per page (default: 100)
- `outputFile` — destination path (default: `./skills.txt`)
- `delayMs` — delay between pages in ms (default: 800)
在 GitHub 查看