Loading...
Loading...
Compare original and translation side by side
Skill by ara.so — Hermes Skills collection
由ara.so开发的Skill — Hermes Skills合集
npx minionsaihttp://localhost:6969npx minionsaihttp://localhost:6969minions --version
npm view minionsai versionminions --version
npm view minionsai version~/.minions/~/.minions/undefinedundefinedundefinedundefinedhttp://localhost:6969http://localhost:6969// Tasks are displayed in real-time Kanban columns
// Watch live streaming output in the task detail view
// Completion judge runs after each agent turn// 任务会实时显示在Kanban列中
// 在任务详情页查看实时流输出
// 完成度判断会在Agent每轮操作后运行// Example: Daily website monitoring routine
{
name: "Check competitor pricing",
schedule: "0 9 * * *", // 9 AM daily
prompt: "Visit competitor.com and extract current pricing, compare to yesterday",
workspace: "./data/competitive-intel"
}// 示例：每日网站监控例行任务
{
name: "Check competitor pricing",
schedule: "0 9 * * *", // 每日上午9点
prompt: "Visit competitor.com and extract current pricing, compare to yesterday",
workspace: "./data/competitive-intel"
}// Task prompt:
"Research the top 10 AI coding assistants launched in 2025.
Create a comparison table with: name, pricing, key features, GitHub stars.
Save as markdown in research/ai-coding-tools.md"
// Agent will:
// 1. Search for AI coding assistants
// 2. Visit documentation sites
// 3. Gather pricing and feature data
// 4. Format as markdown table
// 5. Save file and propose completion// 任务提示：
"Research the top 10 AI coding assistants launched in 2025.
Create a comparison table with: name, pricing, key features, GitHub stars.
Save as markdown in research/ai-coding-tools.md"
// Agent会执行以下操作：
// 1. 搜索AI代码助手
// 2. 访问文档站点
// 3. 收集定价和功能数据
// 4. 格式化为markdown表格
// 5. 保存文件并提交完成申请// Routine configuration:
{
name: "Daily HackerNews trending",
schedule: "0 */6 * * *", // Every 6 hours
prompt: `
1. Fetch top 30 HackerNews stories
2. Extract: title, points, comments, URL
3. Append to data/hn-trending.jsonl with timestamp
4. If any story mentions 'AI agents', save separately to data/hn-ai-agents.jsonl
`,
workspace: "./scraped-data"
}// 例行任务配置：
{
name: "Daily HackerNews trending",
schedule: "0 */6 * * *", // 每6小时一次
prompt: `
1. 获取HackerNews排名前30的故事
2. 提取：标题、点赞数、评论数、URL
3. 附加时间戳后写入data/hn-trending.jsonl
4. 如果任何故事提到'AI agents'，单独保存到data/hn-ai-agents.jsonl
`,
workspace: "./scraped-data"
}// Task prompt:
"Create a TypeScript function that:
- Takes an array of URLs
- Fetches each in parallel with retry logic
- Returns success/failure status for each
- Includes proper error handling and types
Save to src/utils/fetch-urls.ts with tests"
// Monitor live as agent:
// - Creates the implementation
// - Adds TypeScript types
// - Writes tests
// - Runs them to verify// 任务提示：
"Create a TypeScript function that:
- Takes an array of URLs
- Fetches each in parallel with retry logic
- Returns success/failure status for each
- Includes proper error handling and types
Save to src/utils/fetch-urls.ts with tests"
// 实时监控Agent执行：
// - 创建实现代码
// - 添加TypeScript类型定义
// - 编写测试用例
// - 运行测试验证// Multi-step task:
"1. Read all markdown files in content/drafts/
2. For each draft:
- Check grammar with language tool
- Generate 3 title alternatives
- Create social media preview text
- Move to content/ready/ when done
3. Create summary report in content/processing-report.md"// 多步骤任务：
"1. 读取content/drafts/中的所有markdown文件
2. 对每个草稿：
- 使用语言工具检查语法
- 生成3个备选标题
- 创建社交媒体预览文本
- 完成后移至content/ready/
3. 在content/processing-report.md中创建汇总报告"undefinedundefinedundefinedundefined// Minions creates Hermes sessions via API
// Each task = one persistent Hermes root session
// Sessions persist across Minions restarts
// Chat history stored in Hermes's database// Minions通过API创建Hermes会话
// 每个任务 = 一个持久化的Hermes根会话
// 会话在Minions重启后仍会保留
// 聊天历史存储在Hermes的数据库中// Task metadata (Minions SQLite):
{
id: "task_123",
title: "Research AI tools",
status: "in_progress",
hermesSessionId: "sess_abc", // Reference to Hermes
model: "claude-3-5-sonnet",
reasoningEffort: "medium"
}
// Chat transcript: stored in Hermes session database
// File outputs: in workspace directory// 任务元数据（Minions SQLite）：
{
id: "task_123",
title: "Research AI tools",
status: "in_progress",
hermesSessionId: "sess_abc", // 关联到Hermes的会话ID
model: "claude-3-5-sonnet",
reasoningEffort: "medium"
}
// 聊天记录：存储在Hermes会话数据库
// 文件输出：存储在工作区目录undefined// 文件会显示在Minions UI的文件浏览器中
// 按任务工作区目录组织
// 可直接从UI下载或查看~/.minions/
├── db.sqlite # Minions任务元数据
└── workspaces/
├── task_123/ # 单个任务的工作区
│ ├── output.json
│ └── report.md
└── task_456/
└── data.csv
Example workspace structure:
undefinedundefinedundefinedundefinedundefinedundefinedundefinedundefinedundefined// 通过UI操作：
// 1. 查看实时流输出
// 2. 检查Agent是否在等待输入
// 3. 通过聊天手动干预
// 4. 或取消并重启任务// Use the UI to:
// 1. View live streaming output
// 2. Check if agent is waiting for input
// 3. Manually intervene via chat
// 4. Or cancel and restart the task// 确保已设置LLM API密钥：
// export OPENAI_API_KEY=your_key
// 在设置页面检查完成度判断配置
// 验证API配额/速率限制// Ensure LLM API key is set:
// export OPENAI_API_KEY=your_key
// Check Settings page for completion judge configuration
// Verify API quota/rate limitsundefinedundefinedundefinedundefined// ✅ 推荐：具体、可衡量的结果
"Scrape product prices from 5 e-commerce sites,
save to products.json with timestamp,
compare to last week's data in products-history.json"
// ❌ 不推荐：模糊、无明确完成标准
"Research some products"// ✅ Good: Specific, measurable outcomes
"Scrape product prices from 5 e-commerce sites,
save to products.json with timestamp,
compare to last week's data in products-history.json"
// ❌ Bad: Vague, no clear completion criteria
"Research some products"undefinedundefinedundefinedundefined// 使用cron语法设置调度
"0 9 * * 1-5" # 工作日上午9点
"*/30 * * * *" # 每30分钟一次
"0 0 * * 0" # 每周日
// 加入错误恢复逻辑：
"If website is down, retry 3 times with 5-minute delays.
Log failures to errors.log"// Use cron syntax for schedules
"0 9 * * 1-5" // 9 AM weekdays
"*/30 * * * *" // Every 30 minutes
"0 0 * * 0" // Weekly on Sunday
// Build in error recovery:
"If website is down, retry 3 times with 5-minute delays.
Log failures to errors.log"// 在任务提示中明确完成条件：
"Task is ONLY complete when:
1. 所有50个URL已处理完成
2. results.json存在且为有效JSON
3. summary.md中的error_count为0
4. 所有输出文件已提交至git"// In task prompt, specify completion:
"Task is ONLY complete when:
1. All 50 URLs have been processed
2. results.json exists and is valid JSON
3. error_count in summary.md is 0
4. All output files are committed to git"// 创建依赖任务：
// 任务1："Scrape data, save to data/raw.json"
// 任务2："Read data/raw.json, analyze, create report.md"
// 任务3："Read report.md, generate executive summary"
// 在Kanban看板上监控所有任务
// 每个任务独立推进// Create dependent tasks:
// Task 1: "Scrape data, save to data/raw.json"
// Task 2: "Read data/raw.json, analyze, create report.md"
// Task 3: "Read report.md, generate executive summary"
// Monitor all on Kanban board
// Each progresses independently