Update vision-management skill for manifesto vs vision distinction

Restructured skill to clearly distinguish:
- Manifesto: Organization-level (architecture repo)
- Vision: Product-level (product repos)

Key additions:
- Architecture table showing all three levels with commands
- Manifesto section with structure, when to update, creation steps
- Vision section clarified as product-level extending manifesto
- Relationship diagram showing inheritance model
- Example of persona inheritance (org → product)
- Continuous improvement loop including retro → encoding flow
- Quick reference table for common questions

Closes #43

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

skills/vision-management/SKILL.md

@@ -1,123 +1,175 @@
 ---
 name: vision-management
-description: Create, maintain, and evolve a product vision. Use when initializing a vision, updating goals, aligning work with vision, or connecting learnings to vision refinement.
+description: Create, maintain, and evolve organization manifesto and product visions. Use when working with manifesto.md, vision.md, milestones, or aligning work with organizational direction.
 ---
 
 # Vision Management
 
-How to create, maintain, and evolve a product vision for continuous improvement.
+How to create, maintain, and evolve organizational direction at two levels: manifesto (organization) and vision (product).
 
 ## Architecture
 
-The vision system has two layers:
+| Level | Document | Purpose | Command | Location |
+|-------|----------|---------|---------|----------|
+| **Organization** | `manifesto.md` | Identity, shared personas, beliefs, principles | `/manifesto` | Architecture repo |
+| **Product** | `vision.md` | Product-specific personas, jobs, solution | `/vision` | Product repos |
+| **Goals** | Gitea milestones | Measurable progress toward vision | `/vision goals` | Per repo |
 
-| Layer | Purpose | Location |
+Product vision inherits from and extends the organization manifesto.
-|-------|---------|----------|
-| **vision.md** | North star philosophy (why, principles, non-goals) | File in repo root |
-| **Milestones** | Goals with progress tracking | Gitea milestones |
 
-- **vision.md** is stable - updated rarely when direction changes
+---
-- **Milestones** are actionable - created/closed as goals evolve
-- **Issues** are assigned to milestones to track progress
 
-## Vision Document Structure
+## Manifesto (Organization Level)
 
-The vision.md file should contain the stable "why" and "who" - not progress tracking:
+The manifesto defines who we are as an organization. It lives in the architecture repo and applies across all products.
+
+### Manifesto Structure
+
+```markdown
+# Manifesto
+
+## Who We Are
+Organization identity - what makes us unique.
+
+## Who We Serve
+Shared personas across all products.
+- **Persona Name**: Description, context, constraints
+
+## What They're Trying to Achieve
+Jobs to be done at the organization level.
+- "Help me [outcome] without [pain]"
+
+## What We Believe
+Core beliefs that guide how we work.
+### [Belief Category]
+- Belief point
+- Belief point
+
+## Guiding Principles
+Decision-making rules that apply everywhere.
+1. **Principle**: Explanation
+
+## Non-Goals
+What the organization explicitly does NOT do.
+- **Non-goal**: Why
+```
+
+### When to Update Manifesto
+
+- **Rarely** - this is foundational identity
+- When core beliefs change
+- When adding/removing personas served
+- When adding non-goals based on learnings
+
+### Creating a Manifesto
+
+1. Define organization identity (Who We Are)
+2. Identify shared personas (2-4 max)
+3. Articulate organization-level jobs to be done
+4. Document core beliefs (especially about AI/development)
+5. Establish guiding principles
+6. Define non-goals
+
+---
+
+## Vision (Product Level)
+
+The vision defines what a specific product does. It lives in each product repo and extends the manifesto.
+
+### Vision Structure
 
 ```markdown
 # Vision
 
-## Who We Serve (Personas)
+## Who This Product Serves
-The people we're building for and what characterizes them.
+Product-specific personas (may extend org personas).
+- **Persona Name**: Product-specific context
 
-- **Persona Name**: Brief description of who they are, their context, constraints
+## What They're Trying to Achieve
-
+Product-specific jobs to be done.
-## What They're Trying to Achieve (Jobs to Be Done)
+- "Help me [outcome] without [pain]"
-The outcomes our personas are trying to accomplish - in their words.
-
-- "Help me [achieve outcome] without [pain point]"
-- "Help me [do thing] so I can [benefit]"
 
 ## The Problem
-Current pain points that prevent our personas from achieving their jobs.
+Pain points this product addresses.
 
 ## The Solution
-How this product addresses the jobs to be done.
+How this product solves those problems.
 
-## Guiding Principles
+## Product Principles
-Core beliefs that guide decisions.
+Product-specific principles (beyond org principles).
 
 ## Non-Goals
-What we're explicitly NOT doing (and why).
+What this product explicitly does NOT do.
 ```
 
-Do NOT include goals, progress, or focus in vision.md - that's what milestones are for.
+### When to Update Vision
 
-## Defining Personas
+- When product direction shifts
+- When adding/changing personas served by this product
+- When discovering new non-goals
+- After major learnings from retros
 
-Good personas are:
+### Creating a Product Vision
-- **Specific**: Not "developers" but "solo developers shipping MVPs"
-- **Characterized**: Include constraints, context, priorities
-- **Limited**: 2-4 personas max, or you're building for everyone (no one)
 
-| Bad | Good |
+1. Reference the organization manifesto
-|-----|------|
+2. Define product-specific personas (can extend org personas)
-| "Users" | "Solo developer shipping side projects on evenings/weekends" |
+3. Identify product-specific jobs to be done
-| "Developers" | "Small team lead coordinating 2-5 engineers" |
+4. Articulate the problem this product solves
-| "Companies" | "Early-stage startup with no dedicated DevOps" |
+5. Define the solution approach
+6. Set product-specific principles (if any)
+7. Document product non-goals
+8. Create initial milestones
 
-## Defining Jobs to Be Done
+---
 
-Jobs should be:
+## Relationship: Manifesto → Vision
-- **Outcome-focused**: What they want to achieve, not what they do
-- **In their voice**: How they'd describe it, not technical jargon
-- **Pain-aware**: Include what's hard about it today
 
-Format: "Help me [outcome] without [pain]" or "Help me [action] so I can [benefit]"
+```
+Manifesto (org)          Vision (product)
+├── Shared Personas  →   Product Personas (more specific)
+├── Org Jobs         →   Product Jobs (subset/extension)
+├── Beliefs          →   (inherited, not duplicated)
+├── Principles       →   Product Principles (additional)
+└── Non-Goals        →   Product Non-Goals (additional)
+```
 
-| Bad | Good |
+### Inheritance Model
-|-----|------|
-| "Git integration" | "Help me commit and push without remembering git commands" |
-| "Issue tracking" | "Help me know what to work on next without checking 5 tools" |
-| "Code review" | "Help me catch bugs before they ship without slowing down" |
 
-## Creating a Vision
+- **Personas**: Product personas can be more specific versions of org personas
+- **Jobs**: Product jobs should trace back to org-level jobs
+- **Beliefs**: Inherited from manifesto, not duplicated in vision
+- **Principles**: Product can add specific principles; org principles apply automatically
+- **Non-Goals**: Product adds its own; org non-goals apply automatically
 
-When no vision exists:
+### Example
 
-1. **Define personas**: Who are we building for? (2-4 specific personas)
+**Manifesto** (organization):
-2. **Identify jobs to be done**: What are they trying to achieve?
+```markdown
-3. **Articulate the problem**: What pain points prevent them from achieving their jobs?
+## Who We Serve
-4. **Define the solution**: How does the product address these jobs?
+- **Solo Developer**: Individual shipping side projects, time-constrained
-5. **Set guiding principles**: What beliefs guide decisions?
+```
-6. **Document non-goals**: What are you explicitly NOT doing?
-7. **Create initial milestones**: 3-5 measurable goals tied to personas/jobs
 
-### Good Goals (Milestones)
+**Vision** (product - e.g., CLI tool):
+```markdown
+## Who This Product Serves
+- **Solo Developer (CLI user)**: Uses terminal daily, prefers keyboard over GUI
+```
+
+The product persona extends the org persona with product-specific context.
+
+---
+
+## Milestones (Goals)
+
+Milestones are product-level goals that track progress toward the vision.
+
+### Good Milestones
 
 - Specific and measurable
 - Tied to a persona and job to be done
 - Outcome-focused (not activity-focused)
-- Have clear success criteria in the description
+- Include success criteria in description
 
-| Bad | Good |
-|-----|------|
-| "Improve performance" | "Page load under 2 seconds" |
-| "Better UX" | "User can complete checkout in under 60 seconds" |
-| "More features" | "Support 3 export formats (CSV, JSON, PDF)" |
-
-### Tying Milestones to Personas
-
-Each milestone should clearly serve a persona's job to be done:
-
-```
-Milestone: "Automate routine git workflows"
-For: Solo developer
-Job: "Help me commit and push without remembering git commands"
-Success: /commit, /pr commands handle 80% of git workflows
-```
-
-Include persona context in milestone descriptions:
 ```bash
 tea milestones create --title "Automate routine git workflows" \
   --description "For: Solo developer
@@ -125,35 +177,14 @@ Job: Ship without context switching to git commands
 Success: /commit and /pr commands handle 80% of workflows"
 ```
 
-## Managing Goals with Milestones
+### Milestone-to-Vision Alignment
 
-```bash
+Every milestone should trace to:
-# List milestones with progress
+- A persona (from vision or manifesto)
-tea milestones
+- A job to be done (from vision)
-tea milestones -f title,items_open,items_closed,state
+- A measurable outcome
 
-# Create a new goal
+---
-tea milestones create --title "Automate repetitive workflows" \
-  --description "Success: 80% of routine tasks handled by slash commands"
-
-# View issues in a milestone
-tea milestones issues "Automate repetitive workflows"
-
-# Close a completed goal
-tea milestones close "Automate repetitive workflows"
-```
-
-### Assigning Issues to Milestones
-
-When creating issues, assign them to the relevant milestone:
-
-```bash
-tea issues create --title "Add /commit command" \
-  --description "..." \
-  --milestone "Automate repetitive workflows"
-```
-
-Progress is automatically tracked through open/closed issue counts.
 
 ## Aligning Issues with Vision
 
@@ -161,50 +192,49 @@ When creating or reviewing issues:
 
 1. **Check persona alignment**: Which persona does this serve?
 2. **Check job alignment**: Which job to be done does this enable?
-3. **Check goal alignment**: Does this issue support a milestone?
+3. **Check milestone alignment**: Does this issue support a goal?
 4. **Assign to milestone**: Link the issue to the relevant goal
-5. **Prioritize by focus**: Issues in priority milestones get worked first
-6. **Flag misalignment**: Issues without clear persona/milestone need justification
 
 Every issue should trace back to: "This helps [persona] achieve [job] by [outcome]."
 
 ### Identifying Gaps
 
-Compare vision to current work:
-
 - **Underserved personas**: Which personas have few milestones/issues?
 - **Unaddressed jobs**: Which jobs to be done have no work toward them?
 - **Empty milestones**: Which milestones have no issues?
-- **Stalled milestones**: Which milestones have no recent progress?
+- **Orphan issues**: Issues without a milestone need justification
-- **Orphan issues**: Are there issues without a milestone?
 
-## Connecting Retros to Vision
+---
-
-After a retrospective:
-
-1. **Review learnings**: Any that affect the vision or goals?
-2. **Milestone changes**: Should any goals be added, closed, or modified?
-3. **Non-goal additions**: Did we learn something to add to vision.md?
-4. **Progress check**: Did completed work close any milestones?
-
-### Retro-to-Vision Questions
-
-- "Did this work reveal a new goal we should add as a milestone?"
-- "Did we learn something that should become a non-goal in vision.md?"
-- "Should we close or modify any milestones based on what we learned?"
-- "Are any milestones ready to close?"
 
 ## Continuous Improvement Loop
 
 ```
-Vision → Milestones → Issues → Work → Retro → (Vision/Milestones updated)
+Manifesto → Vision → Milestones → Issues → Work → Retro → (updates)
+                                                    ↓
+                                          Architecture repo issues
+                                                    ↓
+                                          Encoded into learnings +
+                                          skills/commands/agents
 ```
 
-1. **Vision** defines why and principles (stable)
+1. **Manifesto** defines organizational identity (very stable)
-2. **Milestones** define measurable goals
+2. **Vision** defines product direction (stable)
-3. **Issues** are work items toward those goals
+3. **Milestones** define measurable goals (evolve)
-4. **Work** implements the issues
+4. **Issues** are work items toward goals
-5. **Retros** capture learnings
+5. **Work** implements the issues
-6. **Updates** refine vision and create/close milestones
+6. **Retros** create issues on architecture repo
+7. **Encoding** turns insights into learnings and system improvements
 
-The vision is stable. The milestones evolve as you learn and achieve goals.
+---
+
+## Quick Reference
+
+| Question | Answer |
+|----------|--------|
+| Where do shared personas live? | `manifesto.md` in architecture repo |
+| Where do product personas live? | `vision.md` in product repo |
+| Where do beliefs live? | `manifesto.md` only (inherited) |
+| Where do goals live? | Gitea milestones (per repo) |
+| What command for org vision? | `/manifesto` |
+| What command for product vision? | `/vision` |
+| What repo for learnings? | Architecture repo |