Co-Pilot / 辅助式
更新于 a month ago

antigravity-kit

Vvudovn
2.9k
vudovn/antigravity-kit
80
Agent 评分

💡 摘要

反重力工具包提供AI代理模板,支持各种技能,实现无缝的任务执行和工作流程。

🎯 适合人群

软件开发人员项目经理质量保证工程师安全审计员科技初创公司

🤖 AI 吐槽:看起来很能打,但别让配置把人劝退。

安全分析中风险

风险:Medium。建议检查:是否执行 shell/命令行指令;是否发起外网请求(SSRF/数据外发);文件读写范围与路径穿越风险;依赖锁定与供应链风险。以最小权限运行,并在生产环境启用前审计代码与依赖。

Antigravity Kit

AI Agent templates with Skills, Agents, and Workflows

Quick Install

npx @vudovn/ag-kit init

Or install globally:

npm install -g @vudovn/ag-kit ag-kit init

This installs the .agent folder containing all templates into your project.

What's Included

| Component | Count | Description | | ------------- | ----- | ------------------------------------------------------------------ | | Agents | 20 | Specialist AI personas (frontend, backend, security, PM, QA, etc.) | | Skills | 36 | Domain-specific knowledge modules | | Workflows | 11 | Slash command procedures |

Usage

Using Agents

No need to mention agents explicitly! The system automatically detects and applies the right specialist(s):

You: "Add JWT authentication"
AI: 🤖 Applying @security-auditor + @backend-specialist...

You: "Fix the dark mode button"
AI: 🤖 Using @frontend-specialist...

You: "Login returns 500 error"
AI: 🤖 Using @debugger for systematic analysis...

How it works:

  • Analyzes your request silently

  • Detects domain(s) automatically (frontend, backend, security, etc.)

  • Selects the best specialist(s)

  • Informs you which expertise is being applied

  • You get specialist-level responses without needing to know the system architecture

Benefits:

  • ✅ Zero learning curve - just describe what you need
  • ✅ Always get expert responses
  • ✅ Transparent - shows which agent is being used
  • ✅ Can still override by mentioning agent explicitly

Using Workflows

Invoke workflows with slash commands:

| Command | Description | | ---------------- | ------------------------------------- | | /brainstorm | Explore options before implementation | | /create | Create new features or apps | | /debug | Systematic debugging | | /deploy | Deploy application | | /enhance | Improve existing code | | /orchestrate | Multi-agent coordination | | /plan | Create task breakdown | | /preview | Preview changes locally | | /status | Check project status | | /test | Generate and run tests | | /ui-ux-pro-max | Design with 50 styles |

Example:

/brainstorm authentication system
/create landing page with hero section
/debug why login fails

Using Skills

Skills are loaded automatically based on task context. The AI reads skill descriptions and applies relevant knowledge.

CLI Tool

| Command | Description | | --------------- | ----------------------------------------- | | ag-kit init | Install .agent folder into your project | | ag-kit update | Update to the latest version | | ag-kit status | Check installation status |

Options

ag-kit init --force # Overwrite existing .agent folder ag-kit init --path ./myapp # Install in specific directory ag-kit init --branch dev # Use specific branch ag-kit init --quiet # Suppress output (for CI/CD) ag-kit init --dry-run # Preview actions without executing

Documentation

Buy me coffee

License

MIT © Vudovn

五维分析
清晰度8/10
创新性7/10
实用性9/10
完整性8/10
可维护性8/10
优缺点分析

优点

  • 零学习曲线
  • 专家响应
  • 透明的代理使用
  • 自动技能应用

缺点

  • 定制化有限
  • 依赖AI准确性
  • 潜在学习限制
  • 需要互联网连接

相关技能

ccmp

A
toolCo-Pilot / 辅助式
86/ 100

“看起来很能打,但别让配置把人劝退。”

claude-mods

A
toolCo-Pilot / 辅助式
86/ 100

“看起来很能打,但别让配置把人劝退。”

agentic-qe

A
toolCo-Pilot / 辅助式
86/ 100

“看起来很能打,但别让配置把人劝退。”

免责声明:本内容来源于 GitHub 开源项目,仅供展示和评分分析使用。

版权归原作者所有 vudovn.