Aircury AI Framework
npx skills add https://github.com/aircury/ai-framework --skill airsyncCLI를 사용하여 이 스킬을 설치하고 작업 공간에서 SKILL.md 워크플로 사용을 시작하세요.
The Aircury AI Framework is a meta-framework for AI-assisted software engineering. It defines how AI agents should think, plan, and deliver code across all Aircury projects while separating a shared workflow constitution from installable capabilities.
It installs project rules, agent entrypoints, living specification folders, optional engineering standards, and curated skills. The canonical source of truth for behavior is always specs/features/, whether a task uses plan-build, OpenSpec, Spec Kit, or a direct implementation flow.
Aircury gives agents enough structure to work consistently without forcing every change through a heavy process:
plan-build for clear day-to-day changes.specs/features/.Run the installer from any project directory (or your home directory for a global setup):
bunx @aircury/ai-framework
# or
npx @aircury/ai-framework
The TUI asks for:
Local to configure the current project, Global to configure your machine.If files already exist, the installer asks whether to skip or overwrite them. Skills are installed through the skills ecosystem with npx or bunx, so they can be updated later.
| Scope | Outputs |
|---|---|
| Local | FRAMEWORK.md, AGENTS.md, .aircury/framework.config.json, starter specs/ folders, optional tool files, selected skills, and a .gitignore entry for specs/changes/. |
| Global | Selected skills for the chosen global agent integrations. |
| Document | Purpose |
|---|---|
docs/concepts.md |
Conceptual model: why the framework exists, workflow routing, capabilities, and canonical specs. |
docs/implementation.md |
Installer flow, generated files, capabilities, skill installation, and conflict handling. |
docs/playbook.md |
Workflow selection guide, examples, and operating rules for installed projects. |
docs/contribution.md |
How to contribute modules, templates, skills, and installer wiring. |