vision
Parses and analyzes project vision to extract structured requirements. Use at project start to understand goals, scope, and constraints. Triggers on: analyze vision, parse project goals, understand requirements.
Best use case
vision is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Parses and analyzes project vision to extract structured requirements. Use at project start to understand goals, scope, and constraints. Triggers on: analyze vision, parse project goals, understand requirements.
Teams using 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/vision/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How vision Compares
| Feature / Agent | 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?
Parses and analyzes project vision to extract structured requirements. Use at project start to understand goals, scope, and constraints. Triggers on: analyze vision, parse project goals, understand requirements.
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
# Vision Analysis Skill Parse the project vision document and extract structured requirements for architecture and planning. ## Workspace Mode Note When running in workspace mode, all paths are relative to `.aha-loop/` directory: - Vision file: `.aha-loop/project.vision.md` - Analysis output: `.aha-loop/project.vision-analysis.md` The orchestrator will provide the actual paths in the prompt context. --- ## The Job 1. Read `project.vision.md` from the project root 2. Validate all required sections are present 3. Extract and structure the requirements 4. Identify project type and scale 5. Output analysis to guide architecture decisions 6. Save analysis to `project.vision-analysis.md` --- ## Input: project.vision.md The vision document should contain: ### Required Sections | Section | Purpose | |---------|---------| | **What** | One-sentence description of the project | | **Why** | Motivation and problem being solved | | **Target Users** | Who will use this product | | **Success Criteria** | Measurable definition of success | ### Optional Sections | Section | Purpose | |---------|---------| | **Constraints** | Technical, budget, or time limitations | | **Inspirations** | Reference products or desired style | | **Non-Goals** | What the project explicitly won't do | --- ## Analysis Process ### Step 1: Validate Vision Document Check that `project.vision.md` exists and contains required sections: ```markdown ## Validation Checklist - [ ] What section present and clear - [ ] Why section explains motivation - [ ] Target Users defined - [ ] Success Criteria are measurable ``` If sections are missing or unclear, document what's needed before proceeding. ### Step 2: Identify Project Type Classify the project: | Type | Characteristics | |------|-----------------| | **CLI Tool** | Command-line interface, no UI | | **Web App** | Browser-based, frontend + backend | | **API Service** | Backend only, REST/GraphQL | | **Library** | Reusable code package | | **Desktop App** | Native desktop application | | **Mobile App** | iOS/Android application | | **Full Stack** | Complete web application | | **Infrastructure** | DevOps, deployment tools | ### Step 3: Estimate Project Scale | Scale | Stories | Duration | Complexity | |-------|---------|----------|------------| | **Small** | 5-15 | Days | Single component | | **Medium** | 15-50 | Weeks | Multiple components | | **Large** | 50-200 | Months | Full system | | **Enterprise** | 200+ | Quarters | Multiple systems | ### Step 4: Extract Core Features From the vision, identify: 1. **Must-Have Features** - Critical for MVP 2. **Should-Have Features** - Important but not blocking 3. **Nice-to-Have Features** - Enhancements for later 4. **Out of Scope** - Explicitly excluded ### Step 5: Identify Technical Implications Based on features, note: - Data storage needs (database type, scale) - Authentication requirements - External integrations - Performance requirements - Security considerations - Deployment environment --- ## Output: project.vision-analysis.md ```markdown # Vision Analysis **Generated:** [timestamp] **Vision Version:** [hash or date of vision.md] ## Project Classification - **Type:** [Web App | API Service | CLI Tool | ...] - **Scale:** [Small | Medium | Large | Enterprise] - **Estimated Stories:** [range] ## Core Requirements ### Must-Have (MVP) 1. [Feature 1] 2. [Feature 2] 3. ... ### Should-Have (Post-MVP) 1. [Feature 1] 2. ... ### Nice-to-Have (Future) 1. [Feature 1] 2. ... ### Out of Scope - [Excluded item 1] - [Excluded item 2] ## Technical Implications ### Data & Storage - [Storage needs analysis] ### Authentication & Security - [Auth requirements] ### Integrations - [External system integrations] ### Performance - [Performance requirements] ### Deployment - [Deployment environment needs] ## Constraints Summary | Constraint | Impact | |------------|--------| | [Constraint 1] | [How it affects decisions] | ## Open Questions - [ ] [Question that needs clarification] - [ ] [Another question] ## Recommended Next Steps 1. Run Architect Skill to determine technology stack 2. Address any open questions before proceeding 3. ... ## Architecture Hints Based on this vision, consider: - [Hint about architecture approach] - [Hint about technology category] ``` --- ## Decision Points ### When Vision is Unclear If the vision document lacks detail: 1. **Do NOT guess** - Document what's missing 2. **List specific questions** - What exactly needs clarification 3. **Provide options** - Suggest possible interpretations 4. **Proceed cautiously** - Make conservative assumptions and note them ### When Scope is Too Large If estimated scale is "Large" or "Enterprise": 1. **Recommend phased approach** - Break into multiple major milestones 2. **Identify MVP subset** - What's the smallest useful version 3. **Flag risk** - Note that large projects need careful management ### When Constraints Conflict If constraints seem to conflict with goals: 1. **Document the conflict** - Be explicit about the tension 2. **Propose resolutions** - Suggest possible compromises 3. **Prioritize** - Recommend which constraint to relax --- ## Integration with Orchestrator After vision analysis: 1. Save `project.vision-analysis.md` to project root 2. Signal completion to orchestrator 3. Architect Skill uses this analysis as input --- ## Example Analysis **Input Vision:** ```markdown # Project Vision ## What A personal finance tracker that helps users manage their budget and track expenses. ## Why Existing apps are too complex. Users need a simple, focused tool. ## Target Users Individuals who want basic expense tracking without complexity. ## Success Criteria - Users can add expenses in under 5 seconds - Monthly reports generated automatically - Works offline ## Constraints - Must be a web app (PWA for offline) - No paid APIs (keep it free) - Single developer, limited time ``` **Output Analysis:** ```markdown # Vision Analysis ## Project Classification - **Type:** Web App (PWA) - **Scale:** Medium - **Estimated Stories:** 20-35 ## Core Requirements ### Must-Have (MVP) 1. Quick expense entry (< 5 seconds) 2. Expense categorization 3. Monthly report generation 4. Offline support (PWA) 5. Data persistence ### Should-Have (Post-MVP) 1. Budget setting and tracking 2. Expense trends visualization 3. Export functionality ### Nice-to-Have (Future) 1. Multiple currencies 2. Receipt photo capture 3. Bank import ### Out of Scope - Multi-user/sharing features - Investment tracking - Tax preparation ## Technical Implications ### Data & Storage - Local-first (IndexedDB for offline) - Optional cloud sync later ### Authentication & Security - Initially: None (local only) - Later: Simple auth for sync ### Performance - Critical: Fast expense entry - PWA service worker for offline ### Deployment - Static hosting (Netlify, Vercel) - No backend initially ## Constraints Summary | Constraint | Impact | |------------|--------| | PWA required | Must use service workers, IndexedDB | | No paid APIs | Use free/open solutions only | | Limited time | Focus on MVP, defer nice-to-haves | ## Recommended Next Steps 1. Run Architect Skill to select frontend framework 2. Design offline-first data architecture 3. Plan PWA implementation strategy ``` --- ## Checklist Before completing vision analysis: - [ ] All required vision sections validated - [ ] Project type identified - [ ] Scale estimated - [ ] Features categorized (must/should/nice/out) - [ ] Technical implications documented - [ ] Constraints analyzed - [ ] Open questions listed - [ ] Analysis saved to `project.vision-analysis.md`
Related Skills
vision-builder
Builds project visions through interactive guided conversation. Use when users have vague ideas needing structure. Triggers on: build vision, I have an idea, start new project, new idea.
skill-creator
Creates new Skills following Anthropic best practices. Use when discovering reusable workflows or repetitive patterns. Triggers on: create skill, new workflow, codify this process, standardize workflow.
roadmap
Creates and manages project roadmaps with milestones and PRD queues. Use after architecture is defined for project planning. Triggers on: create roadmap, plan milestones, organize prds.
research
Conducts deep technical research for Aha Loop stories. Use before implementing stories involving unfamiliar libraries or architectural decisions. Triggers on: research this, investigate, explore options, compare alternatives.
prd
Generates Product Requirements Documents (PRD) for new features. Use when planning features or starting projects. Triggers on: create prd, write prd, plan feature, requirements, spec out.
prd-converter
Converts PRDs to prd.json format for Aha Loop autonomous execution. Use when converting existing PRDs to JSON format. Triggers on: convert prd, create prd.json, aha-loop format.
plan-review
Reviews and adjusts PRD plans based on research findings. Use after completing research to evaluate story modifications. Triggers on: review plan, adjust stories, update prd based on research.
parallel-explore
Guides parallel exploration of multiple implementation approaches using git worktrees. Use when facing decisions with multiple valid paths. Triggers on: explore options, compare approaches, parallel exploration.
observability
Logs AI thoughts and decisions for human observability. Applies continuously throughout all tasks to maintain transparency.
god-member
Defines God Committee member behavior and responsibilities with oversight authority. Use when operating as a committee member. Triggers on: god committee, committee observation, council discussion.
god-intervention
Guides God Committee members through executing interventions. Use for repairs, rollbacks, and emergency actions. Triggers on: intervention, repair, rollback, emergency action.
god-consensus
Guides God Committee members through consensus-building for collective decisions. Use for proposals, voting, and disagreement resolution. Triggers on: consensus, voting, proposal, committee decision.