socrates-ai-openclaw 0.1.1

OpenClaw framework integration for Socrates AI - Socratic method discovery skill

Socratic OpenClaw Skill - Modern Architecture

Socratic method discovery skill for OpenClaw using modern modular architecture

This is the modernized replacement for the deprecated socrates-ai-openclaw package. It uses the latest socratic-core library instead of the monolithic socrates-ai package.

Features

🎓 Socratic Discovery - Claude-guided questioning for project discovery 📚 RAG Knowledge Base - Vector embeddings with ChromaDB for context-aware responses 📊 Specification Generation - Auto-generate requirements, architecture, and project specs 💾 Session Persistence - Resume discoveries anytime 🔄 Multi-turn Conversations - Natural dialogue flow with context tracking ⚡ Production Ready - Built on battle-tested socratic-core library

Installation

pip install socratic-openclaw-skill

Quick Start

from socratic_openclaw_skill import SocraticDiscoverySkill

# Initialize the skill
skill = SocraticDiscoverySkill()

# Start a discovery session
result = await skill.start_discovery("AI-powered SaaS application")
print(result["question"])
# Output: "What problem does this solve for your target users?"

# Respond to the question
result = await skill.respond(result["session_id"], "Helps teams manage projects efficiently")
print(result["question"])

# Generate a specification
result = await skill.generate(result["session_id"])
print(result["spec"])

With OpenClaw

# Install OpenClaw
pip install openclaw

# Socratic discovery is automatically available
# Users can start a discovery session in their preferred channel

In OpenClaw chat:

User: "Help me plan a new project"
OpenClaw: "I'll guide you through Socratic discovery. Question 1: What problem does this solve?"
User: "Tracks team time efficiently"
OpenClaw: "Question 2: Who are your target users?"
... (continues for 5-8 turns)
User: "Generate a spec"
OpenClaw: "Here's your project specification..."

Architecture

User Input (OpenClaw)
↓
SocraticDiscoverySkill (Modern)
↓
├─ SessionManager (track sessions)
├─ QuestionEngine (generate questions)
├─ ResponseProcessor (handle answers)
├─ SpecGenerator (create specs)
└─ StorageHandler (persist data)
↓
socratic-core Library (Foundation)
↓
├─ SocratesConfig
├─ EventEmitter
├─ Exception hierarchy
└─ Logging infrastructure
↓
Claude API (LLM)
ChromaDB (RAG)

Configuration

Environment Variables

# Required
export ANTHROPIC_API_KEY="sk-ant-..."

# Optional
export SOCRATIC_MODEL="claude-opus-4-5"
export SOCRATIC_TEMPERATURE="0.7"
export SOCRATIC_WORKSPACE_ROOT="~/.openclaw/workspace"

Programmatic Configuration

from socratic_openclaw_skill import SocraticDiscoverySkill
from pathlib import Path

skill = SocraticDiscoverySkill(
    workspace_root=Path.home() / ".openclaw" / "workspace",
    model="claude-opus-4-5",
    temperature=0.7
)

API Reference

SocraticDiscoverySkill

start_discovery(topic: str) -> Dict

Start a new Socratic discovery session.

Parameters:

• topic (str): The project or concept to discover

Returns:

{
    "status": "started",
    "session_id": "discover_1234567890_abc",
    "topic": "AI-powered expense tracker",
    "question": "What problem does this solve?",
    "progress": {"step": 1}
}

respond(session_id: str, response: str) -> Dict

Record user response and get next question.

Parameters:

• session_id (str): Session ID from start_discovery
• response (str): User's response to previous question

Returns:

{
    "status": "question_asked",
    "session_id": "discover_...",
    "question": "Who is your target user?",
    "progress": {"questions_asked": 2, "responses_recorded": 1}
}

generate(session_id: str) -> Dict

Generate project specification from discovery.

Parameters:

• session_id (str): Session ID from start_discovery

Returns:

{
    "status": "spec_generated",
    "session_id": "discover_...",
    "spec": "# Project Name\n\n## Overview\n...",
    "saved_to": "~/.openclaw/workspace/projects/project-name/PROJECT.md",
    "artifacts": ["PROJECT.md", "REQUIREMENTS.md", "ARCHITECTURE.md"]
}

Migration from socrates-ai-openclaw

The old socrates-ai-openclaw package is deprecated and broken. Use this package instead:

Before (Broken):

# ❌ BROKEN - depends on non-existent socrates-ai>=1.3.0
pip install socrates-ai-openclaw

Now (Works):

# ✅ WORKS - uses modern modular architecture
pip install socratic-openclaw-skill

Code Changes

# Old (broken)
from socrates_openclaw import SocraticDiscoverySkill

# New (works)
from socratic_openclaw_skill import SocraticDiscoverySkill

Storage

Projects are stored in your workspace directory:

~/.openclaw/workspace/
├── projects/
│   ├── project-name-1/
│   │   ├── PROJECT.md
│   │   ├── REQUIREMENTS.md
│   │   ├── ARCHITECTURE.md
│   │   └── .session-*.json
│   └── project-name-2/
├── .socrates-vectors/     (ChromaDB embeddings)
├── .socrates-kb/          (Knowledge base)
└── .socratic-sessions.json (Session tracking)

All data is stored locally - no cloud upload.

Troubleshooting

API Key Issues

# Error: Anthropic key not found
# Solution:
export ANTHROPIC_API_KEY="sk-ant-..."

# Or in code:
import os
os.environ["ANTHROPIC_API_KEY"] = "your-key"

Missing Dependencies

# If you get import errors:
pip install socratic-openclaw-skill[dev]

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Write tests
4. Submit a pull request

See CONTRIBUTING.md for details.

Support

• GitHub Issues: Report bugs
• Documentation: Full docs
• Email: [e-mail]

License

MIT License - see LICENSE file

Acknowledgments

Built with:

• socratic-core - Foundation library
• Anthropic Claude - LLM
• ChromaDB - Vector storage
• OpenClaw - AI assistant platform

---

Made with ❤️ for the Socrates and OpenClaw communities