IntentKit Development Assistant

Expert assistant for working with IntentKit, an autonomous agent framework that enables creation and management of AI agents with powerful skills.

What This Skill Does

This skill provides comprehensive guidance for developing, modifying, and maintaining the IntentKit framework. It understands the project architecture, follows coding standards, and helps with agent system development, skills creation, API implementation, and frontend work.

Architecture Knowledge

Package Structure (`intentkit/`)

The assistant understands the intentkit pip package structure:

Application Structure (`app/`)

Additional Directories

Technology Stack

Development Guidelines

Coding Standards

1. **Always use the latest package versions**

2. **Use English for all code comments**

3. **Use English for searches**

4. **Place imports at the beginning of files**

5. **Do not auto-commit unless explicitly requested**

6. **No need for dedicated documentation or example scripts after implementation**

Import Order (Avoid Circular Dependencies)

Packages must follow this dependency order (left can never import right):

```

utils → config → models → abstracts → clients → skills → core

```

Code Quality

Key Documentation References

Skills Development

When developing or modifying skills, refer to: `agent_docs/skill_development.md`

Operations Guide

For Git commits, pull requests, or releases, refer to: `agent_docs/ops_guide.md`

Frontend Development

For Next.js application work, refer to: `frontend/AGENTS.md`

Technology Documentation

Usage Examples

Example 1: Adding a New Skill

```

Create a new skill for fetching weather data from OpenWeatherMap API

```

The assistant will:

1. Read `agent_docs/skill_development.md`

2. Create skill in `intentkit/skills/` following LangChain BaseTool pattern

3. Add necessary configuration to `intentkit/config/`

4. Follow import order rules

5. Run linting and type checking

6. Create integration test in `tests/skills/`

Example 2: Modifying Agent Core

```

Add conversation memory persistence to the agent system

```

The assistant will:

1. Work in `intentkit/core/` with LangGraph

2. Update models in `intentkit/models/` (both Pydantic and SQLAlchemy)

3. Respect dependency order (models before core)

4. Ensure SQLAlchemy 2.0 API usage

5. Run pytest for core tests

Example 3: API Endpoint Development

```

Create a new FastAPI endpoint to list all agent skills

```

The assistant will:

1. Add endpoint to `app/` API server

2. Follow FastAPI best practices

3. Use proper Pydantic V2 models for request/response

4. Add tests in `tests/api/`

5. Run linting and tests

Important Constraints

Project Context

IntentKit is an open and fair framework for building AI agents equipped with powerful skills. The project emphasizes: