Hacker News
The AI DevKit introduces a new way to extend AI agents with reusable skills via a simple CLI command. These skills, packaged as folders with a SKILL.md file, are distributed through skill registries and symlinked into projects for immediate use by AI coding agents.
AI 生成摘要
AI DevKit推出一種新方法，可透過簡單的CLI指令，利用可重複使用的技能來擴展AI代理。這些技能以包含SKILL.md檔案的資料夾形式打包，透過技能註冊中心分發，並以符號連結（symlink）方式連結到專案，供AI編碼代理即時使用。
Extend your AI agents with reusable, community-driven skills from skill registries.
Skills are packaged capabilities that extend what your AI agents can do. Think of them as "plugins" for your AI assistant—each skill teaches your agent a new competency, like frontend design patterns, database optimization, or security best practices.
Note: AI DevKit reads your project configuration from .ai-devkit.json. If this file doesn't exist when you run skill add, you'll be prompted to select which AI environments to configure. Skills require at least one skill-capable environment (Cursor, Claude Code, Codex, OpenCode, or Antigravity).
A skill is a folder containing a SKILL.md file and optional supporting resources (scripts, examples, templates). When you install a skill, it's symlinked into your project's skill directory, making it immediately available to your AI agent.
What's a symlink? A symlink (symbolic link) is like a shortcut—instead of copying files, it creates a reference to the original location. This means updates to the cached skill are automatically reflected in your project. On systems where symlinks aren't supported, files are copied instead.
Skills are distributed via Skill Registries—GitHub repositories that follow a standard structure. The AI DevKit maintains a curated list of registries, so you can easily discover and install skills from the community.
Get up and running in 30 seconds:
Once installed, simply ask your AI agent to use the skill's capabilities—it will automatically apply the techniques and patterns defined in the skill.
Skills are currently supported by the following AI coding agents:
When you install a skill, it's automatically added to all skill-capable environments configured in your project.
Once a skill is installed, your AI agent automatically has access to it. You don't need to do anything special—just ask!
When your AI agent starts a session, it reads the SKILL.md files from your project's skill directories. These files contain instructions that teach the agent new capabilities, patterns, or best practices.
Let's say you installed a frontend-design skill. You can now ask your agent:
"Use the frontend-design skill to create a responsive navigation component"
Or simply reference the concepts the skill teaches:
"Build a card component following modern design patterns"
The agent will apply the techniques, conventions, and examples defined in the skill's instructions.
Install a skill from a registry.
Syntax:
Parameters:
Example:
This command will:
Output:
List all skills installed in your project.
Syntax:
Example Output:
The list shows:
Remove a skill from your project.
Syntax:
Example:
Output:
The cached copy remains in ~/.ai-devkit/skills/ so you can quickly reinstall it in other projects without re-downloading.
AI DevKit uses a centralized registry file to map registry identifiers to their GitHub repositories. The registry is hosted at:
The registry is a simple JSON file:
Each registry repository should follow this structure:
Want to create your own skills? Here's what you need:
Every skill must have a SKILL.md file with YAML frontmatter:
To provide fast installation times, AI DevKit caches skill registries locally:
The registry identifier doesn't exist in the skill registry. Check available registries:
The skill doesn't exist in the specified registry. Explore the registry repository on GitHub to see available skills.
Your project doesn't have any skill-compatible environments. Run ai-devkit init and select an environment that supports skills (Cursor, Claude Code, Codex, OpenCode, or Antigravity).
The skill folder exists but doesn't contain a SKILL.md file, meaning it's not a valid skill. Contact the registry maintainer.
A CLI toolkit for AI-assisted software development with phase templates and structured workflows.
© 2026 AI DevKit. Released under the MIT License.