diff --git a/skills/design-thinking/loop.md b/skills/design-thinking/loop.md
new file mode 100644
index 0000000..cd3d8aa
--- /dev/null
+++ b/skills/design-thinking/loop.md
@@ -0,0 +1,267 @@
+# Skill: Design Thinking - Loop
+
+## Description
+Connect all phases of design thinking into a continuous improvement cycle, with clear decision points for iteration vs shipping.
+
+## Input
+- **phase_results**: Results from empathize, define, ideate, prototype, test phases (required)
+- **iteration_number**: Which iteration is this (optional, default: 1)
+- **time_constraint**: Timeline for shipping (optional)
+- **quality_bar**: Minimum quality requirements (optional)
+
+## The Continuous Loop
+
+### Full Cycle Flow
+```
+EMPATHIZE → DEFINE → IDEATE → PROTOTYPE → TEST
+     ↑                                      ↓
+     └──────────── LOOP BACK ───────────────┘
+
+Decision Points:
+1. After TEST: Ship, Iterate, or Pivot?
+2. If Iterate: Which phase to revisit?
+3. If Pivot: Back to Empathize or Define?
+```
+
+### Loop Decision Framework
+
+**Decision Matrix:**
+```
+Test Results → Next Action
+
+SHIP:
+- Success rate: >80%
+- User satisfaction: >4/5
+- No critical issues
+- Meets business goals
+→ Action: Deploy to production
+
+ITERATE (Minor):
+- Success rate: 60-80%
+- 2-3 moderate issues
+- Core concept works
+- Quick fixes available
+→ Action: PROTOTYPE → TEST
+
+ITERATE (Major):
+- Success rate: 40-60%
+- Multiple issues
+- Concept solid but execution off
+- Need design changes
+→ Action: IDEATE → PROTOTYPE → TEST
+
+PIVOT:
+- Success rate: <40%
+- Wrong problem solved
+- Users prefer current solution
+- Fundamental assumption wrong
+→ Action: EMPATHIZE or DEFINE
+```
+
+### When to Loop Back to Each Phase
+
+**Back to EMPATHIZE if:**
+- Users dont have the problem you thought
+- Your solution solves wrong pain point
+- Missing key user segment
+- Assumptions about users proven wrong
+
+**Back to DEFINE if:**
+- Problem statement too broad/narrow
+- Wrong success metrics
+- HMW question leads to wrong solutions
+- Persona doesnt match real users
+
+**Back to IDEATE if:**
+- Solution works but not optimal
+- Better ideas emerged during testing
+- Technical constraints changed
+- Simpler approach possible
+
+**Back to PROTOTYPE if:**
+- Concept good, execution poor
+- Usability issues in UI/UX
+- Need higher/lower fidelity
+- Technical implementation issues
+
+**Rerun TEST if:**
+- Fixed critical issues
+- Changed user segment
+- Need more data
+- A/B test needed
+
+## Iteration Velocity
+
+### Fast Iteration Cycles
+```
+Week 1:
+- Mon: Empathize (existing data)
+- Tue: Define + Ideate
+- Wed: Prototype (lo-fi)
+- Thu: Test (3-5 users)
+- Fri: Loop decision
+
+Week 2:
+- Mon-Tue: Iterate prototype
+- Wed: Test again
+- Thu: Ship or continue
+```
+
+### Quality vs Speed Trade-offs
+```
+Speed Priority:
+- Lo-fi prototypes
+- 3-user tests
+- Ship at 70% quality
+- Fix in production
+
+Quality Priority:
+- Hi-fi prototypes
+- 10+ user tests
+- Ship at 95% quality
+- Polish before launch
+
+Balanced:
+- Med-fi prototypes
+- 5-user tests
+- Ship at 80% quality
+- Plan iteration post-launch
+```
+
+## Metrics That Matter
+
+### Leading Indicators (Predict Success)
+```
+Empathize:
+- Users interviewed per segment
+- Pain points validated by 3+ users
+- Quote-to-insight ratio
+
+Define:
+- HMW clarity score (1-5)
+- Stakeholder alignment (%)
+- Success metric specificity
+
+Ideate:
+- Ideas per session
+- Effort/Impact scoring
+- Idea diversity
+
+Prototype:
+- Build time vs plan
+- Component reuse rate
+- Fidelity appropriate for stage
+
+Test:
+- User completion rate
+- Time on task vs target
+- SUS score
+```
+
+### Lagging Indicators (Measure Impact)
+```
+Post-Launch:
+- User adoption rate
+- Feature usage frequency
+- Support tickets (fewer = better)
+- User satisfaction (NPS)
+- Business metrics (revenue, retention)
+```
+
+## Output Format
+```json
+{
+  "status": "success",
+  "iteration": 2,
+  "cycle_summary": {
+    "empathize": "5 users interviewed, 3 critical pains identified",
+    "define": "HMW: Reduce setup time from 2hr to 5min",
+    "ideate": "8 ideas generated, selected template-based approach",
+    "prototype": "Med-fi prototype, 6hrs build time",
+    "test": "80% success rate, SUS score 72"
+  },
+  "decision": {
+    "verdict": "iterate_minor",
+    "confidence": "high",
+    "reasoning": "Core flow works but 2 UX issues need fixing"
+  },
+  "loop_back_to": "prototype",
+  "changes_needed": [
+    "Add template preview on hover",
+    "Improve success confirmation message"
+  ],
+  "estimated_effort": "4 hours",
+  "next_test_plan": {
+    "users": 3,
+    "focus": "Template selection UX",
+    "success_criteria": "90% success rate on template task"
+  },
+  "ship_criteria": {
+    "must_have": [
+      "90% task completion",
+      "SUS score > 75",
+      "Zero critical issues"
+    ],
+    "nice_to_have": [
+      "Template customization",
+      "Saved templates"
+    ]
+  },
+  "timeline": {
+    "this_iteration": "3 days",
+    "total_so_far": "10 days",
+    "target_ship": "14 days"
+  }
+}
+```
+
+## Quality Gates
+- [ ] Clear decision made (ship/iterate/pivot)
+- [ ] Loop target phase identified
+- [ ] Specific changes documented
+- [ ] Success criteria for next iteration defined
+- [ ] Timeline realistic
+- [ ] Learning captured for future iterations
+
+## Token Budget
+- Max input: 1500 tokens
+- Max output: 2000 tokens
+
+## Model
+- Recommended: sonnet (strategic reasoning)
+
+## Philosophy
+> "Done is better than perfect. But learning is better than done."
+> Ship fast, learn faster, improve continuously.
+
+**Keep it simple:**
+- Small iterations beat big leaps
+- Test assumptions early
+- Fail fast, learn faster
+- Perfect is the enemy of shipped
+- User feedback > internal opinions
+
+## Pivot vs Persevere
+
+**Persevere if:**
+- Core metrics trending up
+- Users like the direction
+- Issues are tactical, not strategic
+- Learning compounds each iteration
+
+**Pivot if:**
+- 3+ iterations with no improvement
+- Users consistently reject solution
+- Wrong problem being solved
+- Better opportunity identified
+
+## Continuous Improvement Post-Launch
+```
+Post-Ship Loop:
+1. Monitor usage analytics
+2. Collect user feedback
+3. Identify new pain points
+4. Prioritize improvements
+5. Small iterations weekly
+6. Major updates monthly
+```