Add CONTRIBUTING.md and fix persona list in getting started guide

- Create contribution guide with bug reporting, PR guidelines, and
  code of conduct focused on therapeutic safety
- Fix incomplete persona list to show all 5 styles: warm & supportive,
  warm 4o-style, direct & challenging, coach, grounded & real

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

CONTRIBUTING.md

@@ -0,0 +1,48 @@
+# Contributing to AI Therapy Kit
+
+Thank you for your interest in contributing! This project helps people access emotional support through AI, so we take contributions seriously.
+
+## Reporting Bugs
+
+1. Check existing [issues](https://github.com/ataglianetti/ai-therapy-kit/issues) to avoid duplicates
+2. Create a new issue with:
+   - Clear description of the problem
+   - Steps to reproduce
+   - Expected vs actual behavior
+   - Your setup (OS, Claude Code version)
+
+## Suggesting Features
+
+Open an issue with the "feature request" label. Include:
+- What problem does this solve?
+- Who would benefit?
+- Any implementation ideas?
+
+## Pull Requests
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/your-feature`)
+3. Make your changes
+4. Test thoroughly
+5. Submit a PR with a clear description
+
+### What We're Looking For
+
+- Additional therapeutic modalities (must have clinical grounding)
+- Improved crisis detection and safety protocols
+- Local LLM integration guides
+- Translations
+- Documentation improvements
+
+## Code of Conduct
+
+This project deals with mental health and emotional wellbeing. Please:
+
+- **Prioritize safety** — Changes to crisis detection or safety protocols require extra scrutiny
+- **Respect privacy** — Never suggest changes that would transmit user data
+- **Be evidence-based** — Therapeutic approaches should have clinical support
+- **Be kind** — Users of this project may be vulnerable; keep that in mind
+
+## Questions?
+
+Open an issue or reach out to the maintainer.