product-playbook 1.0.0

package/i18n/en/references/rules-end-of-flow.md

@@ -0,0 +1,150 @@
+# 🏁 End-of-Flow Rules
+
+> Loaded when all steps are completed.
+
+## ⛔ End Condition Check
+
+Before producing the final integrated output, the following must be verified:
+
+1. Confirm that all steps in the progress indicator are marked ✅
+2. If any steps were skipped (at the user's explicit request), mark them as "⚠️ Skipped" in the final output
+3. If any steps are marked ⬜ (not executed), do not proceed to the final output
+4. **Security quick check**: If the user will be entering the development phase (generating a dev handoff package), include a security reminder in the final output, and when generating the dev handoff package, automatically read `references/08-security-checklist.md` to produce the corresponding security architecture section
+
+Violations of this rule include: Independently deciding that "the remaining steps are not important" and skipping them, marking incomplete steps as completed, or combining multiple steps into a single output.
+
+## 🔍 Decision Consistency Check
+
+Before generating the final integrated output, scan ALL completed steps and verify cross-step consistency:
+
+### Checks by Mode
+
+**🚀 Quick Mode** (3 steps — check 2 cross-references):
+1. JTBD ↔ PR-FAQ: Does the PR-FAQ address the same problem as the JTBD statement?
+2. PR-FAQ ↔ North Star: Does the North Star measure the outcome the PR-FAQ promises?
+
+**📦 Full Mode** (20 steps — check all 7):
+1. Target User — same persona referenced across JTBD, Positioning, PR-FAQ, and North Star?
+2. Core Problem / JTBD — PR-FAQ addresses the same problem? MVP solves it?
+3. Positioning — reflected in PR-FAQ headline and solution direction?
+4. Solution Direction — selected solution matches MVP scope?
+5. MVP Scope — consistent with PR-FAQ promises? "Not Doing" items respected?
+6. North Star Metric — measures JTBD outcome? Achievable with MVP scope?
+7. Pre-mortem Risks — still relevant given final solution and MVP?
+
+**🔄 Revision Mode** (12 steps — check 4):
+1. Existing JTBD ↔ Pain Points ↔ Positioning: consistent after re-evaluation?
+2. PR-FAQ ↔ MVP Scope: revision scope matches what PR-FAQ describes?
+3. North Star ↔ Before/After: metric comparison is logical?
+4. Pre-mortem Risks: still relevant for the revised product?
+
+**⚡ Build Mode** (7 steps — check 4):
+1. Problem Statement ↔ PR-FAQ: same problem addressed?
+2. Solution Direction ↔ MVP Scope: selected solution matches MVP?
+3. North Star ↔ MVP: metric achievable with MVP scope?
+4. Pre-mortem Risks: still relevant for final solution?
+
+**🔧 Feature Extension Mode** (4 steps — check 3):
+1. Problem ↔ Selected Solution: solution directly addresses the stated problem?
+2. Solution ↔ Execution Scope: scope correctly implements the selected solution?
+3. Risk Assessment: identified risks still relevant for the execution scope?
+
+**✏️ Custom Mode** — only check cross-references between steps the user actually executed. Skip checks for steps that were not part of the custom selection.
+
+### Execution
+1. List each core decision as a one-liner (e.g., "Target User: Early-stage startup founders")
+2. Check for contradictions or outdated references between steps
+3. If inconsistencies are found:
+   - Display: "⚠️ Consistency check found [N] issue(s) before final output:"
+   - List each issue with the affected steps
+   - Ask user: "Should I fix these before generating the final output, or proceed as-is?"
+4. If all consistent:
+   - Display: "✅ Decision consistency check passed — all steps aligned."
+   - Proceed to final output
+
+### Why This Matters
+During iterative planning, users may modify upstream decisions (e.g., change JTBD) while some downstream steps retain outdated content. This check catches those gaps before the final document is produced, preventing inconsistent deliverables.
+
+## 📦 Product Context Auto-Extraction
+
+After all steps are completed and while producing the final integrated output, read `references/rules-context.md` Section 8 to perform context extraction:
+
+1. **Check whether `.product-context.md` exists**
+   - Does not exist → Create a new file
+   - Exists → Update per the rules (Identity/Core Strategy overwrite, Decision History append, Architecture merge, Insights merge and deduplicate)
+
+2. **Extract content** (according to the flow type mapping in `rules-context.md` Section 8 table)
+
+3. **Inform the user**: After the final output, display:
+   "✅ Product context has been updated in `.product-context.md` — it will be automatically loaded in your next planning session."
+
+4. **Version control reminder** (first creation only):
+   "⚠️ We recommend adding `.product-context.md` to `.gitignore` — this file may contain sensitive product strategy information."
+
+## Best Entry Point Analysis (Full Mode only)
+
+```
+[Persona Pain Points] → [JTBD Statement] → [OST Opportunity] → [HMW Question]
+    → [Positioning (April Dunford)] → [PR-FAQ Validation] → [Solution Selected]
+        → [Aha Moment] → [North Star Metric] → [PMF Level Assessment]
+```
+
+Analysis points: Most worthwhile problem to solve / Core JTBD / Product positioning / PMF level and next milestone / First action step / Pre-mortem risk alerts
+
+## Final Output by Mode
+
+| Mode | Final Integrated Output |
+|------|------------------------|
+| 🔧 Feature Extension Mode | Feature development spec: Problem → Selected solution → Impact scope → Execution scope → Risks |
+| 🚀 Quick Mode | One-page direction summary: Problem → Solution → Success Definition |
+| 📦 Full Mode | Best Entry Point Analysis + Product Spec Summary |
+| 🔄 Revision Mode | Revision product spec summary: Before/after comparison + What to change/What not to change + Success metrics |
+| ✏️ Custom Mode | Product Spec Summary (unexecuted fields marked "Not Executed") |
+| ⚡ Build Mode | Engineer-oriented execution summary |
+
+### Output Language Override
+
+Users can request outputs in a different language than the planning session:
+- "Generate the PR-FAQ in Japanese"
+- "Output the report in Spanish"
+- "Write the PRD in Chinese"
+
+When a language override is requested:
+1. Generate the output content in the requested language
+2. Keep framework names in English (JTBD, PR-FAQ, North Star, etc.)
+3. Return to the planning session's original language after output generation
+4. Note: This only affects the output document language, not the reference files or planning flow
+
+## Extended Output Prompt
+
+After completing the final integrated output, proactively ask:
+
+```
+"The planning content has been fully integrated! Would you like me to generate any of the following documents?
+
+□ Updated [document type] (incremental update based on your uploaded source document) ← only show this option when a source document was uploaded
+□ PDF document (professional layout with bookmark navigation, suitable for formal sharing)
+□ HTML planning report (interactive, suitable for online sharing)
+□ Word document (suitable for collaborative editing)
+□ PRD engineer delivery package (includes flowchart, DB schema, UI wireframe)
+□ Presentation PPTX (suitable for meeting reports, recommend polishing with Keynote / PowerPoint after export)
+□ Dev handoff package (CLAUDE.md + TASKS.md + TICKETS.md + technical architecture — ready to start development in Claude Code)
+□ All of the above
+
+You can also say 'No thanks' to finish, or specify a particular document.
+You can also use /export [pdf|docx|pptx|html|md] to export at any time."
+```
+
+**Option display rules**:
+- Source document uploaded → "Updated [document type]" listed first with "(recommended)" label
+- Target audience is engineers → PRD and dev handoff package listed first
+- Target audience is executives/leadership → PDF and presentation listed first
+- Target audience is cross-functional → PDF, HTML report, and presentation all listed
+- Quick Mode → Only ask if PDF or presentation is needed
+- Target audience is yourself → Dev handoff package listed first
+
+**Export trigger rules**:
+- User selects PDF / Word / Presentation PPTX → Load `rules-export-document.md`
+- First time triggering document export → Load `rules-document-tools.md` first to check and install necessary tools
+- User selects HTML planning report → Load `06-html-report.md` (existing rules)
+- User selects "All of the above" → Execute each format export in sequence

package/i18n/en/references/rules-export-document.md

@@ -0,0 +1,346 @@
+# Multi-Format Document Export Rules
+
+> Loaded when the user triggers `/export [format]` or selects an export format after the flow ends.
+> On first use, load `rules-document-tools.md` first to confirm tools are installed.
+
+## Supported Export Formats
+
+| Format | Command | Conversion Path | Tools |
+|--------|---------|----------------|-------|
+| PDF | `/export pdf` | HTML+CSS → Playwright → pikepdf bookmarks | Playwright MCP + pikepdf |
+| DOCX | `/export docx` | MD → Pandoc | pandoc + reference.docx |
+| PPTX | `/export pptx` | MD → Pandoc | pandoc |
+| HTML | `/export html` | Existing `06-html-report.md` rules | Built-in |
+| Markdown | `/export md` | Direct output | Built-in |
+
+---
+
+## PDF Export (Core Flow)
+
+### Path Selection
+
+PDF export has two paths, automatically selected based on source content:
+
+| Source | Path | Reason |
+|--------|------|--------|
+| Planning output direct export (PRD / incremental update / spec) | **Path A: setContent** | No external JS dependencies, all resources can be inlined |
+| HTML planning report to PDF (with Mermaid diagrams / CDN fonts) | **Path B: HTTP Server** | Needs to load external JS (mermaid.js) and CDN fonts |
+
+### Path A: Standalone Document → PDF (setContent)
+
+Applicable to: PRD, feature extension incremental updates, specs, any content without external JS.
+
+**Step 1: Generate HTML Content**
+
+Claude reads `references/templates/prd-style.css` and generates a complete HTML document:
+
+```html
+<!DOCTYPE html>
+<html lang="zh-TW">
+<head>
+<meta charset="UTF-8">
+<style>
+/* Read the full contents of prd-style.css and inline here */
+</style>
+</head>
+<body>
+
+<!-- Cover page -->
+<div class="cover-page">
+  <h1>[Document Title]</h1>
+  <div class="subtitle">[Subtitle or one-line description]</div>
+  <div class="version-badge">[Version Number]</div>
+  <div class="meta-info">
+    <strong>PM</strong> [PM Name]<br>
+    <strong>Date</strong> [ISO Date]<br>
+    <strong>Status</strong> [Status]
+  </div>
+</div>
+
+<!-- Legend (only for incremental update documents) -->
+<div class="diff-legend">
+  <div class="diff-legend-item"><div class="diff-legend-swatch swatch-new"></div> New in this version</div>
+  <div class="diff-legend-item"><div class="diff-legend-swatch swatch-upd"></div> Modified in this version</div>
+  <div class="diff-legend-item"><div class="diff-legend-swatch swatch-unchanged"></div> Unchanged</div>
+</div>
+
+<!-- Table of Contents page -->
+<div class="toc-page">
+  <h2>Table of Contents</h2>
+  <ul class="toc">
+    <!-- Claude auto-generates TOC items based on h2 headings -->
+    <li>
+      <span class="toc-title">[Section Name]</span>
+      <span class="toc-dots"></span>
+      <span class="toc-page-num">[Page Number]</span>
+    </li>
+  </ul>
+</div>
+
+<!-- Body content -->
+[Body HTML]
+
+<!-- Footer -->
+<div class="doc-footer">
+  [Document Code] [Version] ｜ [Date] ｜ Generated by Product Playbook
+</div>
+
+</body>
+</html>
+```
+
+**Important**:
+- CSS must be fully inlined (no external links)
+- Fonts use system fonts: `"PingFang TC", "Noto Sans TC", system-ui` (Playwright will automatically embed in PDF)
+- No `<script>` tags or external resource references
+- TOC page numbers are estimates (may need fine-tuning after PDF generation)
+
+**Step 2: Playwright Renders PDF**
+
+Save the HTML content to `/tmp/export-{timestamp}.html`, then call Playwright MCP:
+
+```javascript
+// mcp__plugin_playwright_playwright__browser_run_code
+async (page) => {
+  const fs = require('fs');
+  const html = fs.readFileSync('/tmp/export-{timestamp}.html', 'utf8');
+  await page.setContent(html, { waitUntil: 'networkidle' });
+  await page.pdf({
+    path: '{output_path}',
+    format: 'A4',
+    margin: { top: '1.8cm', bottom: '1.8cm', left: '2cm', right: '2cm' },
+    printBackground: true,
+    displayHeaderFooter: true,
+    headerTemplate: '<div></div>',
+    footerTemplate: '<div style="font-size:8pt;color:#999;text-align:center;width:100%;">p.<span class="pageNumber"></span> / <span class="totalPages"></span></div>'
+  });
+  return 'PDF generated';
+}
+```
+
+> Note: If the HTML content is too large (>500KB), setContent may time out. In that case, switch to Path B (HTTP Server).
+
+**Step 3: pikepdf Bookmark Injection**
+
+```python
+import pikepdf, re
+
+pdf = pikepdf.open('{output_path}')
+
+# Extract h2 headings from HTML as bookmarks
+# Claude should record the estimated page number for each h2 when generating HTML
+bookmarks = [
+    # (title, page index 0-based)
+    ("Revision History", 2),
+    ("User Story", 4),
+    ("Development Architecture", 6),
+    # ... generated based on actual content
+]
+
+with pdf.open_outline() as outline:
+    for title, page_idx in bookmarks:
+        page_idx = min(page_idx, len(pdf.pages) - 1)
+        outline.root.append(
+            pikepdf.OutlineItem(title, page_idx)
+        )
+
+# Set PDF metadata
+with pdf.open_metadata() as meta:
+    meta['dc:title'] = '[Document Title]'
+    meta['dc:creator'] = ['[PM Name]']
+    meta['pdf:Producer'] = 'Product Playbook + Playwright'
+
+pdf.save('{output_path}')
+```
+
+**Step 4: Notify User**
+
+```
+✅ PDF exported to: {output_path}
+  📄 {page_count} pages ｜ {file_size}
+  📑 Includes bookmark navigation ({bookmark_count} sections)
+```
+
+### Path B: HTML Report → PDF (HTTP Server)
+
+Applicable to: HTML reports with Mermaid diagrams, CDN fonts, interactive elements.
+
+**Step 1: HTML Report Already Generated**
+
+The HTML report is generated by `06-html-report.md` rules and saved as `/tmp/report-{timestamp}.html`.
+
+**Step 2: Start HTTP Server**
+
+```bash
+cd /tmp && python3 -m http.server 18899 &
+echo $!  # Record PID
+```
+
+**Step 3: Playwright Rendering**
+
+```javascript
+// mcp__plugin_playwright_playwright__browser_run_code
+async (page) => {
+  await page.goto('http://localhost:18899/report-{timestamp}.html', {
+    waitUntil: 'networkidle',
+    timeout: 30000
+  });
+  // Wait for Mermaid chart rendering to complete
+  await page.waitForTimeout(3000);
+  // Expand all accordion (<details>) elements
+  await page.evaluate(() => {
+    document.querySelectorAll('details').forEach(d => d.open = true);
+  });
+  await page.pdf({
+    path: '{output_path}',
+    format: 'A4',
+    margin: { top: '1.8cm', bottom: '1.8cm', left: '2cm', right: '2cm' },
+    printBackground: true,
+    displayHeaderFooter: true,
+    headerTemplate: '<div></div>',
+    footerTemplate: '<div style="font-size:8pt;color:#999;text-align:center;width:100%;">p.<span class="pageNumber"></span> / <span class="totalPages"></span></div>'
+  });
+  return 'PDF generated';
+}
+```
+
+**Step 4: Shut Down HTTP Server + pikepdf Bookmarks**
+
+```bash
+kill {SERVER_PID}
+```
+
+Then perform the same pikepdf bookmark injection step as Path A.
+
+### Playwright MCP Unavailable Fallback
+
+If Playwright MCP is not connected, use Node.js directly:
+
+```bash
+node -e "
+const { chromium } = require('playwright');
+const fs = require('fs');
+(async () => {
+  const browser = await chromium.launch({ headless: true });
+  const page = await browser.newPage();
+  const html = fs.readFileSync('/tmp/export-{timestamp}.html', 'utf8');
+  await page.setContent(html, { waitUntil: 'networkidle' });
+  await page.pdf({
+    path: '${OUTPUT_PATH}',
+    format: 'A4',
+    printBackground: true,
+    margin: { top: '1.8cm', bottom: '1.8cm', left: '2cm', right: '2cm' }
+  });
+  await browser.close();
+  console.log('PDF generated');
+})();
+"
+```
+
+---
+
+## DOCX Export
+
+### Step 1: Generate Markdown
+
+Claude organizes the planning output into clean Markdown format and saves it as `/tmp/export-{timestamp}.md`.
+
+### Step 2: Pandoc Conversion
+
+```bash
+pandoc /tmp/export-{timestamp}.md \
+  -o "{output_path}" \
+  --from markdown \
+  --to docx \
+  --reference-doc="~/.claude/skills/product-playbook/references/templates/reference.docx" \
+  --toc \
+  --toc-depth=2
+```
+
+If no reference.docx template is available, omit the `--reference-doc` parameter (uses Pandoc default styles).
+
+### Step 3: Notify User
+
+```
+✅ Word document exported to: {output_path}
+  📄 Includes table of contents ｜ {file_size}
+```
+
+---
+
+## PPTX Export
+
+```bash
+pandoc /tmp/export-{timestamp}.md \
+  -o "{output_path}" \
+  --from markdown \
+  --to pptx \
+  --slide-level=2
+```
+
+> Tip: Pandoc PPTX quality is limited. It's recommended to use the PPTX as an outline, then polish it with PowerPoint/Keynote.
+
+---
+
+## Special Handling for Incremental Update Documents
+
+When exporting Feature Extension or Revision mode incremental update documents:
+
+### Diff Visual Marking Rules
+
+1. **Paragraphs marked `[NEW]`**:
+   - Use `<span class="new">NEW</span>` marker
+   - Table rows get `class="new-row"`
+   - Paragraphs get `class="diff-added"`
+
+2. **Paragraphs marked `[UPDATED]`**:
+   - Use `<span class="upd">UPDATED</span>` marker
+   - Table rows get `class="upd-row"`
+   - If original content exists, original content gets `class="diff-removed"`, new content gets `class="diff-added"`
+
+3. **Unchanged paragraphs**: Display normally, no special markers
+
+4. **Legend at document start**:
+```html
+<div class="diff-legend">
+  <div class="diff-legend-item">
+    <div class="diff-legend-swatch swatch-new"></div> New in this version
+  </div>
+  <div class="diff-legend-item">
+    <div class="diff-legend-swatch swatch-upd"></div> Modified in this version
+  </div>
+  <div class="diff-legend-item">
+    <div class="diff-legend-swatch swatch-unchanged"></div> No marker = Unchanged
+  </div>
+</div>
+```
+
+---
+
+## Output Path Rules
+
+Default output to `~/Downloads/`, filename format:
+
+```
+[Document Code] [Document Title] [Version].{ext}
+
+Examples:
+[D-221] Virtual Account v1.0.14 Full Merged Version.pdf
+Product Planning Report - UPASS Virtual Account.docx
+```
+
+If the user specifies a path, use the user-specified path.
+
+---
+
+## Quality Checklist
+
+Before export, Claude self-checks:
+
+- [ ] No residual Markdown syntax in HTML (`**`, `##`, `|---|`)
+- [ ] All table row and column counts match the original content
+- [ ] `[NEW]` / `[UPDATED]` markers correctly mapped to corresponding CSS classes
+- [ ] Cover page information (title, version, PM, date) is correct
+- [ ] TOC items match the body h2 headings
+- [ ] CSS is fully inlined (Path A) or CDN is accessible (Path B)
+- [ ] Bookmark count matches h2 heading count

package/i18n/en/references/rules-file-integration.md

@@ -0,0 +1,65 @@
+# 📎 File Integration Guide
+
+> Loaded when the user uploads supplementary materials.
+
+## Directly Supported File Types
+
+| File Type | Common Scenarios | Integration Method |
+|-----------|-----------------|-------------------|
+| **Images** | Competitor screenshots, whiteboard photos, hand-drawn journey maps, app interface screenshots, data report screenshots | Recognize content and integrate into the corresponding step |
+| **PDF** | Market reports, internal documents, user research reports, legacy PRDs | Load `rules-import-document.md` for three-layer parsing (pymupdf direct extraction → Claude Vision semantic parsing → Tesseract fallback). On first use, load `rules-document-tools.md` to check tools. |
+| **CSV / Excel** | User behavior data, retention data, NPS survey results, sales data | Analyze data and use for quantitative assessment |
+| **Text files** | Interview transcripts, existing requirements documents, meeting notes | Extract Persona clues, pain points, JTBD evidence |
+| **DOCX** | Existing PRDs, product spec documents, user research reports | Load `rules-import-document.md`, use Pandoc to convert to Markdown then integrate. On first use, load `rules-document-tools.md` to check tools. |
+| **PPTX** | Existing presentations, product intro slides | Load `rules-import-document.md`, use Pandoc to convert to Markdown then integrate. |
+
+## Not Directly Supported but Guidance Available
+
+| File Type | Guidance |
+|-----------|----------|
+| **Video** | Ask the user to describe key scenes, or provide a transcript/subtitle file |
+| **Figma / Sketch** | Ask the user to take screenshots and upload them |
+| **Protobuf / Swagger** | Ask the user to export as JSON or text format |
+
+## File → Step Auto-Mapping Table
+
+| Uploaded Content | Auto-Mapped Step | Integration Action |
+|-----------------|-----------------|-------------------|
+| Competitor app / website screenshots | Positioning | Identify as "competitive alternatives," analyze differentiation |
+| Whiteboard hand-drawn flowchart | Journey Map / OST | Recognize the flow and convert into a structured table |
+| User interview transcript | Persona + JTBD | Extract pain points, current workarounds, emotional reactions, Job statements |
+| User behavior data (CSV) | Opportunity Assessment + North Star + PMF | Replace assumption-based scores with real data |
+| NPS / satisfaction survey | PMF + Sean Ellis Score | Directly calculate the Score; determine PMF level |
+| Existing PRD / requirements document | Revision Mode S1 + MVP | Extract existing feature list and decision history |
+| Market report PDF | Opportunity Assessment + Strategy | Extract market size, trends, competitive landscape |
+| Sales data | Business Model + GTM | Analyze revenue structure, customer distribution, channel effectiveness |
+| App interface screenshots | Aha Moment + Journey | Analyze the current experience path |
+
+## Integration Rules
+
+1. **Proactive identification**: First explain "I see you uploaded [file type]. I will integrate the [key information] from it into [step name]."
+2. **Do not overwrite existing output**: Mark the uploaded content as "supplementary material," update the output, and trigger the change propagation rules
+3. **Mark the source**: Annotate in the output which content came from the uploaded file (e.g., "✦ From the uploaded user research report")
+4. **Data takes priority**: When real data conflicts with previous assumptions, defer to the real data
+5. **Cross-step impact**: A single file may affect multiple steps — list all affected steps at once
+
+## 📎 Source Document Identification & Incremental Update
+
+When a user uploads a file during **Feature Extension** or **Revision Mode**, determine if it is a "source document" (a document that should be incrementally updated with the new planning output):
+
+### Identification Criteria
+- File type: PRD, product spec, architecture doc, requirements doc, design doc
+- User explicitly says: "this is our current PRD", "update this document", "build on this spec", etc.
+- Uploaded during S1 (context collection) of Feature Extension or Revision Mode
+
+### When a Source Document Is Identified
+1. Mark it: "📎 Source document detected — final output will be an incremental update based on this file"
+2. Parse the document structure (section headings, formatting conventions, naming patterns)
+3. Record the document's format and style for consistent output
+4. During S1, use the document to pre-fill existing system context (tech stack, modules, features)
+
+### Incremental Output Rules (applied at Final Output stage)
+- New content inserted into the appropriate sections, marked with `[NEW]`
+- Modified content marked with `[UPDATED]`, original content preserved as comment
+- Sections unrelated to the new feature remain untouched
+- The output document maintains the original file's format, style, and naming conventions

package/i18n/en/references/rules-full.md

@@ -0,0 +1,66 @@
+# 📦 Full Mode Step Sequence (20 Steps + Final Output)
+
+> This file is the authoritative step definition for Full Mode. Loaded by the SKILL.md core dispatcher.
+
+## Step Sequence
+
+```
+Phase 0: Prerequisites
+  S1.  Opportunity Assessment + DHM → Read references/00-opportunity-check.md
+  S2.  Strategy Blocks + Rumelt Strategy Kernel → Read references/01-strategy.md
+
+Phase 1: Discovery
+  S3.  Persona Table → Read references/02a-persona.md
+  S4.  Persona Cards → Read references/02a-persona.md
+  S5.  JTBD Analysis → Read references/02b-jtbd.md
+  S6.  Opportunity Solution Tree (OST) → Read references/02c-ost-journey.md
+  S7.  User Journey Map → Read references/02c-ost-journey.md
+
+Phase 2: Define
+  S8.  Pain Points Summary Table → Read references/03-define.md
+  S9.  April Dunford Positioning → Read references/03-define.md
+  S10. HMW Reframing → Read references/03-define.md
+  S11. Opportunity Assessment Table → Read references/03-define.md
+
+Phase 3: Develop
+  S12. PR-FAQ → Read references/04a-prfaq.md
+  S13. Parallel Prototypes → Read references/04b-solutions.md
+  S14. Pre-mortem → Read references/04b-solutions.md
+  S15. GEM + RICE Prioritization → Read references/04b-solutions.md
+  S16. User Story → Read references/04b-solutions.md
+  S17. MVP + Not Doing List → Read references/04c-mvp.md
+
+Phase 4: Deliver
+  S18. North Star + Three-Layer Signals + Aha Moment → Read references/05a-northstar-aha.md
+  S19. PMF Level Assessment + GTM Strategy + Business Model → Read references/05b-pmf-gtm.md
+  S20. Hypothesis Validation Plan → Read references/05c-validation-spec.md
+────
+Final Output → Product Spec Summary (references/05c-validation-spec.md → 4.6) + Best Entry Point Analysis
+```
+
+> In Full Mode, section 4.1 Empowered Teams is added before S18 when the target audience is executives or cross-functional teams; otherwise it is skipped.
+
+## Reference Loading Instructions
+
+When entering each step, only read the corresponding reference file (do not preload all files):
+
+| Step | Reference File |
+|------|---------------|
+| S1 | `references/00-opportunity-check.md` |
+| S2 | `references/01-strategy.md` |
+| S3-S4 | `references/02a-persona.md` |
+| S5 | `references/02b-jtbd.md` |
+| S6-S7 | `references/02c-ost-journey.md` |
+| S8-S11 | `references/03-define.md` |
+| S12 | `references/04a-prfaq.md` |
+| S13-S16 | `references/04b-solutions.md` |
+| S17 | `references/04c-mvp.md` |
+| S18 | `references/05a-northstar-aha.md` |
+| S19 | `references/05b-pmf-gtm.md` |
+| S20 + Final Output | `references/05c-validation-spec.md` |
+
+## Final Output Format
+
+**Best Entry Point Analysis** (full logic chain) + **Product Spec Summary**
+
+After completion, follow `references/rules-end-of-flow.md` to execute the end-of-flow rules.