A Safe Space for Practicing Difficult Conversations
", unsafe_allow_html=True) # Welcome text and instructions if not st.session_state.setup_complete: st.markdown(""" ## Practice Hard Conversations—Safely. Welcome to a therapeutic roleplay simulator built for emotionally charged moments. This tool helps you rehearse boundary-setting and difficult conversations by simulating realistic relational dynamics—tailored to your attachment style. You'll choose: - A scenario (e.g., "Ask my mom not to comment on my body") - A tone of response (e.g., supportive, guilt-tripping, dismissive) - Your attachment style (e.g., anxious, avoidant, disorganized) - And your goal (e.g., "I want to stay calm and not backtrack") The AI will take on the role of a realistic human responder—not to therapize you, but to mirror the relational pressure you might encounter in real life. Then, you'll get a reflection summary to help you track your emotional patterns and practice courage. ### 🧠 Not sure what your attachment style is? You can take this [free quiz from Sarah Peyton](https://www.yourresonantself.com/attachment-assessment) to learn more. Or you can just pick the one that vibes when you read it: - **Anxious** – "I often worry if I've upset people or said too much." - **Avoidant** – "I'd rather handle things alone than depend on others." - **Disorganized** – "I want closeness, but I also feel overwhelmed or mistrusting." - **Secure** – "I can handle conflict and connection without losing myself." """) # Sidebar with setup form with st.sidebar: st.markdown(""" ### Welcome! 👋 Hi, I'm Jocelyn Skillman, LMHC — a clinical therapist, relational design ethicist, and creator of experimental tools that explore how AI can support (not replace) human care. Each tool in this collection is thoughtfully designed to: - Extend therapeutic support between sessions - Model emotional safety and relational depth - Help clients and clinicians rehearse courage, regulation, and repair - Stay grounded in trauma-informed, developmentally sensitive frameworks I use Claude (by Anthropic) as the primary language model for these tools, chosen for its relational tone, contextual nuance, and responsiveness to emotionally complex prompts. As a practicing therapist, I imagine these resources being especially helpful to clinicians like myself — companions in the work of tending to others with insight, warmth, and care. #### Connect With Me 🌐 [jocelynskillman.com](http://www.jocelynskillman.com) 📬 [Substack: Relational Code](https://jocelynskillmanlmhc.substack.com/) --- """) st.markdown("### 🎯 Simulation Setup") with st.form("simulation_setup"): attachment_style = st.selectbox( "Your Attachment Style", ["Anxious", "Avoidant", "Disorganized", "Secure"], help="Select your attachment style for this practice session" ) scenario = st.text_area( "Scenario Description", placeholder="Example: I want to tell my dad I can't call every night anymore.", help="Describe the conversation you want to practice" ) tone = st.text_input( "Desired Tone for AI Response", placeholder="Example: guilt-tripping, dismissive, supportive", help="How should the AI character respond?" ) practice_goal = st.text_area( "Your Practice Goal", placeholder="Example: staying grounded and not over-explaining", help="What would you like to work on in this conversation?" ) submit_setup = st.form_submit_button("Start Simulation") if submit_setup and scenario and tone and practice_goal: # Create system message with simulation parameters system_message = f"""Attachment Style: {attachment_style} Scenario: {scenario} Tone: {tone} Goal: {practice_goal} Remember to stay in character unless the client says 'pause', 'reflect', or 'debrief'. Keep responses under 3 lines unless asked to elaborate.""" # Reset messages and add system message st.session_state.messages = [{"role": "assistant", "content": "Simulation ready. You can begin the conversation whenever you're ready."}] st.session_state.setup_complete = True st.rerun() # Display simulation status if not st.session_state.setup_complete: st.info("👈 Please complete the simulation setup in the sidebar to begin.") else: # Display chat history for message in st.session_state.messages: with st.chat_message(message["role"]): st.markdown(message["content"]) # User input field if user_prompt := st.chat_input("Type your message here... (or type 'debrief' to end simulation)"): # Add user message to chat history st.session_state.messages.append({"role": "user", "content": user_prompt}) # Display user message with st.chat_message("user"): st.markdown(user_prompt) # Get Claude's response with st.spinner("..."): response = anthropic.messages.create( model="claude-3-opus-20240229", max_tokens=1024, messages=[ {"role": m["role"], "content": m["content"]} for m in st.session_state.messages ] ) assistant_response = response.content[0].text # Add assistant response to chat history st.session_state.messages.append( {"role": "assistant", "content": assistant_response} ) # Display assistant response with st.chat_message("assistant"): st.markdown(assistant_response) # Footer st.markdown("---") st.markdown("by Jocelyn Skillman LMHC - to learn more check out: jocelynskillmanlmhc.substack.com
", unsafe_allow_html=True)