feat: add skills system for specialized agent workflows (#6)

Implement a skills framework that enables specialized workflows for
specific tasks (e.g., PDF processing, web page generation). Skills are
discovered from the skills/ directory and automatically mounted in
sandboxes with path mapping support.

- Add SkillsConfig for configuring skills path and container mount point
- Implement dynamic skill loading from SKILL.md files with YAML frontmatter
- Add path mapping in LocalSandbox to translate container paths to local paths
- Mount skills directory in AIO Docker sandbox containers
- Update lead agent prompt to dynamically inject available skills
- Add setup documentation and expand config.example.yaml

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
DanielWalnut
2026-01-16 14:44:51 +08:00
committed by GitHub
parent 5ef3cb57ee
commit cfa97f7a96
30 changed files with 2959 additions and 51 deletions

View File

@@ -2,6 +2,50 @@
> Originated from Open Source, give back to Open Source.
A LangGraph-based AI agent backend with sandbox execution capabilities.
## Quick Start
1. **Configure the application**:
```bash
# Copy example configuration
cp config.example.yaml config.yaml
# Set your API keys
export OPENAI_API_KEY="your-key-here"
# or edit config.yaml directly
```
2. **Install dependencies**:
```bash
cd backend
make install
```
3. **Run development server**:
```bash
make dev
```
## Project Structure
```
deer-flow/
├── config.example.yaml # Configuration template (copy to config.yaml)
├── backend/ # Backend application
│ ├── src/ # Source code
│ └── docs/ # Documentation
├── frontend/ # Frontend application
└── skills/ # Agent skills
├── public/ # Public skills
└── custom/ # Custom skills
```
## Documentation
- [Configuration Guide](backend/docs/CONFIGURATION.md) - Setup and configuration instructions
- [Architecture Overview](backend/CLAUDE.md) - Technical architecture details
## License
This project is open source and available under the [MIT License](./LICENSE).