Best use case
openup-shared-vision is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create shared technical vision for team alignment
Teams using openup-shared-vision should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openup-shared-vision/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openup-shared-vision Compares
| Feature / Agent | openup-shared-vision | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create shared technical vision for team alignment
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Shared Vision This skill creates a shared technical vision document that ensures alignment between stakeholders and the development team on technical objectives, scope, and key decisions. ## When to Use Use this skill when: - Vision document exists but needs technical elaboration - Need to define IN/OUT scope clearly - Starting Elaboration phase and need technical alignment - Team members have different understanding of technical direction - Need to document key technical decisions and constraints ## When NOT to Use Do NOT use this skill when: - No vision document exists (use `/openup-create-vision` first) - In late Construction or Transition phases (should already exist) - Only need architecture details (use `/openup-create-architecture-notebook`) - Vision is already well-defined and understood ## Success Criteria After using this skill, verify: - [ ] Technical objectives are clearly documented - [ ] IN/OUT scope is well-defined - [ ] Technical assumptions and constraints are listed - [ ] Key technical decisions have rationale - [ ] Open questions are tracked for elaboration - [ ] Document is linked from main vision ## Process Summary 1. Read existing vision document 2. Extract technical context and objectives 3. Define IN/OUT scope 4. Document technical assumptions and constraints 5. Record key technical decisions 6. Identify open questions ## Detailed Steps ### 1. Read Existing Vision Read `docs/vision.md` to understand: - Project problem statement - Stakeholder needs - Business objectives - Current project status ### 2. Extract Technical Context From the vision and project status, identify: **Technical Objectives:** - What technical problems need to be solved? - What are the key quality attributes (performance, security, scalability)? - What technical success criteria exist? **If `$ARGUMENTS[technical_objectives]` is provided:** - Focus on those specific objectives - Add related technical objectives **Examples:** - "Achieve sub-second response times" - "Support 10,000 concurrent users" - "Ensure data encryption at rest and in transit" ### 3. Define IN/OUT Scope Create clear boundaries for what is included and excluded: **IN Scope:** What features and capabilities are definitely included? - Use `$ARGUMENTS[scope_focus]` as a starting point if provided - List specific features, capabilities, and technologies - Be specific about what "in scope" means **OUT Scope:** What is explicitly excluded to manage expectations? - Features that are explicitly NOT being built - Technologies that won't be used - Capabilities that are out of scope for this project ### 4. Document Technical Assumptions Record assumptions about the technical environment: | Assumption | Impact | Validated By | |------------|--------|--------------| | Example: PostgreSQL available | Low - affects data layer | DBA | | Example: Users on modern browsers | Medium - affects frontend | UX research | ### 5. Document Technical Constraints Record known constraints that limit options: | Constraint | Description | Mitigation | |------------|-------------|------------| | Example: Budget for cloud services | Must use cost-effective solutions | Serverless architecture | | Example: Legacy system integration | Must work with existing APIs | Adapter pattern | ### 6. Record Key Technical Decisions Document significant technical decisions with rationale: **Examples:** - Choice of programming language - Architectural style (microservices vs monolith) - Database selection - Deployment approach For each decision: - What was decided - Why (rationale) - Alternatives considered - Trade-offs accepted ### 7. Identify Open Questions List questions that need answers during elaboration: | Question | Impact | Target Phase | |----------|--------|--------------| | Example: How to handle offline mode? | High - affects architecture | Elaboration | | Example: Third-party API limits? | Medium - affects design | Elaboration | ### 8. Create Shared Vision Document Create `docs/shared-vision.md` using the shared vision template with: - Technical objectives table - IN/OUT scope sections - Assumptions and constraints tables - Key technical decisions - Open questions ### 9. Link from Main Vision Add a reference in `docs/vision.md`: ```markdown ## Technical Vision See [Shared Vision](shared-vision.md) for detailed technical objectives, scope, and decisions. ``` ## Output Returns a summary of: - Shared vision document created at `docs/shared-vision.md` - Technical objectives documented - IN/OUT scope defined - Key decisions recorded - Open questions identified ## Example Usage ``` /openup-shared-vision technical_objectives: "scalability, security" scope_focus: "user authentication" ``` ## Common Errors | Error | Cause | Solution | |-------|-------|----------| | Vision not found | docs/vision.md doesn't exist | Create vision first with /openup-create-vision | | Too vague | Objectives not specific enough | Add measurable criteria | | Missing OUT scope | Only IN scope defined | Always define both IN and OUT | | No rationale | Decisions without justification | Add why and alternatives considered | ## References - Shared Vision Template: `docs-eng-process/templates/shared-vision.md` - Vision Template: `docs-eng-process/templates/vision.md` - Architecture Notebook Template: `docs-eng-process/templates/architecture-notebook.md` ## See Also - [openup-create-vision](../create-vision/SKILL.md) - Create project vision first - [openup-create-architecture-notebook](../create-architecture-notebook/SKILL.md) - Create detailed architecture documentation - [openup-elaboration](../../openup-phases/elaboration/SKILL.md) - Elaboration phase activities
Related Skills
openup-transition
Initialize and manage Transition phase activities - deploy to users
openup-tdd-workflow
Guide Test-Driven Development cycle adapted for AI agents with a pragmatic approach
openup-sync-spec
Back-propagate pure refactors to stale artifacts; classify the diff, refuse behaviour-changes, propose targeted edits for approval (read-only by default)
openup-start-iteration
Begin a new OpenUP iteration with proper phase context and task selection
openup-retrospective
Generate iteration retrospective with feedback and action items
openup-request-input
Create an input request document for asynchronous stakeholder communication
openup-readiness
Compute the change-folder dependency DAG and print READY/BLOCKED/collision report for PM intake
openup-quick-task
Fast iteration mode for small changes - simplified workflow with minimal overhead
openup-plan-feature
Generate iteration plan and roadmap entry for a feature idea
openup-phase-review
Check phase completion criteria and prepare for phase review
openup-orchestrate
Run a full orchestrated iteration — PM decomposes the goal, delegates to specialist roles, collects outputs, and synthesizes results
openup-next
Run ONE OpenUP delivery cycle — read the derived board, claim the top READY lane, execute it, tick its progress, and exit through a legal exit. The sequential continue-loop.