I see you added the mckinsey-consultant skill!
This is a McKinsey-style problem-solving tool.

Would you like me to introduce the working method?
Or directly tell me what business problem you want to analyze?

I see you added the mckinsey-consultant skill!
This is a McKinsey-style problem-solving tool.

Would you like me to introduce the working method?
Or directly tell me what business problem you want to analyze?

I see you added the mckinsey-consultant skill! This is a very powerful consulting framework system.

Before starting to create, I would like to confirm a few key questions with you:

1. **What business problem do you want to solve?** 
   - Market entry strategy?
   - Business growth opportunities?
   ...
2. **Expected deliverable format:**
   ...

Phase 1: Problem Decomposition (20-30 minutes)
  STEP 1: Define Problem Boundaries
  STEP 2: Issue Tree (MECE Decomposition)
  STEP 3: Hypotheses (Hypothesis-Driven)

Phase 2: Solution Design (30-40 minutes)
  STEP 4: Determine Argumentation Method
  STEP 5: Design Dummy Pages → Output Dummy.md

Phase 3: Page-by-Page Generation (40-60 minutes)
  STEP 6-7: Page-by-Page Loop (Search→Excel→PPT→Self-Check→Pause)
  STEP 8: Optional Word Generation
  STEP 9: Iterative Optimization

"Analyze [business problem] with mckinsey-consultant"
"Analyze growth opportunities in China's XX market"

[Upload ProjectName_DummyPages_Date.md]
[Optional: Upload completed PPT and Excel]

"This is a previous project, please continue from page X"

undefined

**No additional files needed** - Basic conversation is sufficient

---

undefined

**Execution Process**:
1. Decompose the problem based on the framework in methodology.md
2. Perform 5-10 rapid web_searches
3. Record complete URLs (prepare for STEP 5)
4. Form hypothesis tree

**Output**:
```markdown

---

undefined

**Execution Process**:
1. Select layout types from layouts.md for each hypothesis
2. Apply design specifications from design-specs.md
3. Clarify data requirements and sources for each page
4. **⭐ Annotate page dependencies** (New)

**Dependency Types**:
- ✅ Independent: No dependencies, can be generated directly
- ⏩ Depends on previous pages: Requires data from previous pages
- ⏪ Depends on subsequent pages or hypothesis tree: Requires completion of subsequent pages, or can use specific documents from previous steps (e.g., Hypothesis Tree), such as executive summary and table of contents


**⭐ Output**: `ProjectName_DummyPages_Date.md`

**Dummy.md Structure**:
```markdown

Generate in new conversation:
1. Ask if the user has the Issue Tree
2. Provide options: Upload/Describe/Work on other pages first

If Page 3 is not completed:
1. Inform the user of the dependency
2. Provide options: Complete Page 3 first or perform temporary search

**⚠️ Critical**: Dummy.md must be complete to support cross-conversation continuation

---

undefined

**Page-by-Page Loop Process**:

**⭐ Dependency Check Examples**:

**Scenario 1: Independent Page**

**Scenario 2: Forward Dependency, Satisfied**

**Scenario 3: Forward Dependency, Not Satisfied**

**Scenario 4: Requires Documents**

**Scenario 5: Backward Dependency**

   ✓ Excel data complete
   ✓ Source URL recorded
6. Inform the user: "Page X completed, self-check passed. Continue?"
7. Wait for confirmation
8. Clear search results context for this page
9. Proceed to next page

undefined

**Breakpoint Continuation Support**:

**Scenario 1: Pause in Same Conversation**

**Scenario 2: Cross-Continuation ⭐**

---

undefined

**Principle**: Do not offer by default to save context

---

undefined

**Optimization Focus**:
- Color contrast (dark blue background → white text)
- Information density (50-70 characters per square inch)
- Element occlusion/text overflow

---

Loading: Full SKILL.md (1130 lines) + all references
Result: Context consumed quickly, difficult to generate 10-15 pages

Initial Loading: Core SKILL.md (~300 lines)

STEP 1: No additional loading needed
STEP 2-3: Temporarily load methodology.md → Release after use
STEP 4-5: Temporarily load layouts.md + design-specs.md → Release after use
STEP 6-7: Temporarily load excel-data-spec.md → Release after use
        + Page-by-page processing (only 5 search results at a time)
STEP 8: Load delivery-summary.md on demand
STEP 9: Load troubleshooting.md on demand

Result: Context consumption reduced by 70%+, can stably generate 20-25 pages

User: "Analyze China's new energy vehicle market with mckinsey-consultant"

Claude:
[Loading: None, core SKILL.md is sufficient]
STEP 1: Define problem boundaries...
[First time entering STEP 2]
file_read(methodology.md)
STEP 2-3: Build Issue Tree...
[Release methodology.md after use]
[First time entering STEP 4-5]
file_read(layouts.md)
file_read(design-specs.md)
STEP 4-5: Design Dummy Pages...
[Output Dummy.md]
[Release layouts.md, design-specs.md after use]
[First time entering STEP 6]
file_read(excel-data-spec.md)
STEP 6-7: Generate page by page...
  Page 1: Search→Excel→PPT→Self-Check→Pause
  [Clear context for Page 1]
  Page 2: Search→Excel→PPT→Self-Check→Pause
  [Clear context for Page 2]
  ...

[New Conversation]
User: [Upload Dummy.md]
      "Please continue from Page 10"

Claude:
file_read(Dummy.md)  # Read complete project specifications
[Identify current phase is STEP 6-7]
file_read(excel-data-spec.md)  # Load on demand
Review design requirements for Page 10 in Dummy
Start Page 10: Search→Excel→PPT→Self-Check→Pause