菜单
Boost developer productivity with Gitai: An AI-powered Git automation tool that analyzes code changes and generates semantic Conventional Commits instantly. Supports Node.js, Python, Java, Go, PHP, and more. Compatible with OpenAI, Anthropic, and Groq.
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。
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。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill gitai-automation命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | gitai-automation |
| display_name | Gitai - Automated Conventional Commits in Git with AI |
| description | Boost developer productivity with Gitai: An AI-powered Git automation tool that analyzes code changes and generates semantic Conventional Commits instantly. Supports Node.js, Python, Java, Go, PHP, and more. Compatible with OpenAI, Anthropic, and Groq. |
| author | leandrosilvaferreira |
| version | 1.0.0 |
| tags | ["git","automation","ai","commit","conventional-commits","workflow","productivity","dev-tools","openai","anthropic","groq","llm"] |
| allowed-tools | Run Command, Read File, Write File |
| priority | HIGH |
Transform your development workflow with intelligent, automated commit management.
Gitai analyzes your code changes to generate precise, descriptive commit messages following the Conventional Commits standard. It eliminates the friction of writing commit messages, ensuring a clean, semantic, and professional git history automatically.
Key capabilities:
This skill requires the @notyped/gitai CLI tool to be installed and configured on the system BEFORE the agent can operate.
The AGENT MUST NOT attempt to install this package or configure it.
CHECK if gitai is available:
command -v gitai
IF MISSING, STOP immediately and inform the user:
"The
gitaiCLI tool is not installed. Please install it globally (e.g.,npm install -g @notyped/gitai) and configure it before using this skill."
CHECK if ~/.gitai exists.
IF MISSING, STOP immediately and inform the user:
"The
gitaitool is installed but not configured. Please rungitaiin your terminal to complete the setup."
ONLY PROCEED if both checks pass.
Based on gitai --help:
gitai [options] [projectPath] [baseMessage]
Arguments:
projectPath: The path to the project (default: ".").baseMessage: The base commit message (Optional).Options:
-p, --push: Whether to push after committing (default: false).-V, --version: Output the version number.-h, --help: Display help for command.| Command | Action Description |
|---|---|
gitai . '' | Analyzes current folder, Generates message and commits |
gitai . '' --push | Analyzes current folder, Generates message, commits, AND pushes to remote |
gitai ./frontend 'ui update' | Analyzes only the ./frontend directory, Generates message and commits |
Check which version of Gitai is currently active:
gitai --version
gitai hangs waiting for input, it means ~/.gitai is missing or invalid. create the file manually as described in Step 2.node -v).API_KEY in ~/.gitai.MIT
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.