diff --git a/skills/design-thinking/empathize.md b/skills/design-thinking/empathize.md
new file mode 100644
index 0000000..bdb2561
--- /dev/null
+++ b/skills/design-thinking/empathize.md
@@ -0,0 +1,152 @@
+# Skill: Design Thinking - Empathize
+
+## Description
+Deeply understand users through research, interviews, and observation to identify real pain points and needs.
+
+## Input
+- **context**: Product/feature context (required)
+- **target_users**: User segments to research (required)
+- **research_type**: interview|observation|survey|analytics (optional, default: interview)
+- **existing_data**: Current user feedback/analytics (optional)
+
+## Research Techniques
+
+### 1. User Interviews
+**Framework: TEDW**
+- **Tell** me about the last time you...
+- **Explain** your workflow for...
+- **Describe** the biggest challenge with...
+- **Walk** me through how you currently...
+
+**Best Practices:**
+- 5-7 users per segment minimum
+- Open-ended questions only
+- Listen 80%, talk 20%
+- Ask "why" 5 times (5 Whys technique)
+- Record exact quotes for later synthesis
+
+### 2. Pain Point Identification
+**Severity Matrix:**
+- **Critical**: Blocks core workflow, happens daily
+- **High**: Major frustration, weekly occurrence
+- **Medium**: Annoying but workaround exists
+- **Low**: Minor inconvenience, rare
+
+**Indicators:**
+- User workarounds/hacks
+- Manual data entry
+- Switching between tools
+- Waiting/delays
+- Errors/mistakes
+- Emotional language ("frustrating", "annoying")
+
+### 3. Empathy Mapping Template
+
+```
+SAYS (verbatim quotes)
+"I waste 2 hours every week on..."
+"Its so frustrating when..."
+
+THINKS (unspoken concerns)
+- Worried about making mistakes
+- Unsure if doing it right
+- Feels inefficient
+
+DOES (observed behaviors)
+- Opens 5 tabs to complete one task
+- Double-checks every entry
+- Asks colleagues for help
+
+FEELS (emotions)
+- Frustrated with repetitive work
+- Anxious about errors
+- Overwhelmed by complexity
+
+PAIN POINTS
+- [Critical pain identified]
+- [High priority pain]
+
+GAINS (what success looks like)
+- Completes task in <5 minutes
+- Confident in accuracy
+- No context switching
+```
+
+### 4. Observation Techniques
+**Contextual Inquiry:**
+- Shadow users in their environment
+- Note workarounds and hacks
+- Identify unstated needs
+- Look for patterns across users
+
+**What to Observe:**
+- Where do they slow down?
+- When do they switch tools?
+- What causes confusion/errors?
+- What do they complain about?
+
+## Output Format
+```json
+{
+  "status": "success",
+  "research_summary": {
+    "users_interviewed": 7,
+    "segments": ["power_users", "occasional_users"],
+    "methods": ["interview", "observation"]
+  },
+  "user_personas": [
+    {
+      "name": "Sarah - Marketing Manager",
+      "context": "Creates 10+ campaigns/month",
+      "goals": ["Speed", "Consistency", "Analytics"],
+      "frustrations": ["Manual data entry", "Lost context"],
+      "quote": "I spend more time copying data than creating campaigns"
+    }
+  ],
+  "pain_points": [
+    {
+      "description": "Manual campaign setup takes 2+ hours",
+      "severity": "critical",
+      "frequency": "daily",
+      "users_affected": 6,
+      "evidence": ["Quote 1", "Quote 2"],
+      "current_workaround": "Excel templates + copy-paste"
+    }
+  ],
+  "empathy_insights": [
+    "Users prioritize speed over features",
+    "Fear of making mistakes drives behavior",
+    "Existing tools lack integration"
+  ],
+  "key_quotes": [
+    "I waste 2 hours every week on manual setup",
+    "Im never confident I did it right"
+  ],
+  "next_step": "Define problem with /dt define"
+}
+```
+
+## Quality Gates
+- [ ] At least 5 users per segment
+- [ ] Mix of qualitative + quantitative data
+- [ ] Clear pain points with severity ratings
+- [ ] Verbatim user quotes captured
+- [ ] Patterns identified across users
+- [ ] Jobs-to-be-done understood
+
+## Token Budget
+- Max input: 800 tokens
+- Max output: 2000 tokens
+
+## Model
+- Recommended: sonnet (deep analysis)
+
+## Philosophy
+> "People dont want a quarter-inch drill. They want a quarter-inch hole."
+> Focus on the underlying need, not the stated solution.
+
+**Keep it simple:**
+- Real users, real problems
+- Evidence over assumptions
+- Quality over quantity of feedback
+- Deep understanding over surface-level