aios-core
Version:
Synkra AIOS: AI-Orchestrated System for Full Stack Development - Core Framework
588 lines (526 loc) • 19.4 kB
YAML
template:
id: design-story-template-v1
name: Design/Research Story Document
version: 1.0
description: Template for design, research, architecture, and documentation planning stories
use_cases:
- UX design and user research
- Architecture planning and design
- Documentation planning and strategy
- Research and analysis work
- Non-development planning tasks
output:
format: markdown
filename: docs/stories/{{epic_num}}.{{story_num}}.{{story_title_short}}.md
title: "Story {{epic_num}}.{{story_num}}: {{story_title_short}}"
workflow:
mode: interactive
elicitation: advanced-elicitation
story_type: design
agent_config:
primary_agents:
- ux-design-expert
- architect
- analyst
editable_sections:
- Status
- Story
- Objective
- Scope
- CodeRabbit Integration
- Tasks Breakdown
- Testing & Validation
- Acceptance Criteria
- Deliverables
- Dev Notes
- Change Log
sections:
- id: header
title: Story Header
type: metadata
instruction: Define story metadata including ID, epic, wave, status, priority, owner, dates
template: |
# Story {{epic_num}}.{{story_num}}: {{story_title}}
**Story ID:** STORY-{{epic_num}}.{{story_num}}
**Epic:** Epic {{epic_num}} - {{epic_title}}
**Wave:** Wave {{wave_num}} ({{wave_name}})
**Status:** {{status_emoji}} {{status}}
**Priority:** {{priority_emoji}} {{priority}}
**Owner:** {{owner_agents}}
**Created:** {{creation_date}}
**Duration:** {{duration}}
**Investment:** ${{investment}}
elicit: true
owner: po
editors: [po, sm]
- id: story
title: Story
type: template-text
template: |
**As a** {{role}},
**I want** {{action}},
**so that** {{benefit}}
instruction: Define the user story using the standard format with role, action, and benefit
elicit: true
owner: po
editors: [po]
- id: objective
title: Objective
type: free-text
instruction: |
Provide a clear, concise statement of what this story aims to achieve.
Focus on the "what" and "why" of the design/research work.
example: |
Define complete personas for all 13 AIOS agents with names, roles, archetypes,
colors, and icons to establish the foundation for the agent identity system.
elicit: true
owner: po
editors: [po, ux-design-expert, architect]
- id: scope
title: Scope
type: free-text
instruction: |
Define the boundaries of this story:
- What is included in this story
- What is explicitly excluded
- Dependencies on other stories
- Deliverables that will be used by downstream stories
example: |
Create comprehensive persona definitions that will be used by:
- Story 6.1.2 (Agent File Updates)
- Story 6.1.3 (@docs Agent Creation)
- Story 6.1.4 (Configuration System)
elicit: true
owner: po
editors: [po, ux-design-expert, architect]
- id: coderabbit-integration
title: 🤖 CodeRabbit Integration
instruction: |
Define quality gates and specialized agent assignments for design/research work.
Even though this is not code, quality standards still apply.
elicit: true
owner: po
editors: [po, sm]
sections:
- id: story-type-analysis
title: Story Type Analysis
instruction: |
Categorize the design/research story:
- Documentation/Design: Writing, planning, specifications
- Research/Analysis: User research, competitive analysis, technical research
- Architecture: System design, patterns, technical planning
- UX Design: User experience, interface design, accessibility
- Strategy: Product strategy, roadmap planning
template: |
**Primary Type**: {{story_type}}
**Secondary Type(s)**: {{story_type_secondary}}
**Complexity**: {{complexity_level}}
elicit: true
owner: po
editors: [po]
- id: specialized-agents
title: Specialized Agent Assignment
instruction: |
List which specialized agents should be involved:
**Design/Research Stories**:
- @ux-design-expert: UX design, user research, accessibility
- @architect: Architecture design, technical planning, patterns
- @analyst: Research, competitive analysis, data analysis
- @po: Requirements validation, acceptance criteria
- @qa: Quality review of deliverables
**Supporting Agents**:
- @pm: Strategy alignment, roadmap planning
- @sm: Process facilitation, sprint planning
template: |
**Primary Agents**:
- {{primary_agent_1}}
- {{primary_agent_2}}
**Supporting Agents**:
- {{supporting_agent_1}}
- {{supporting_agent_2}}
elicit: true
owner: po
editors: [po, sm]
- id: quality-gates
title: Quality Gate Tasks
instruction: |
Define validation checkpoints for design/research work:
**Pre-Completion Review** (Primary Agent):
- Validate deliverables meet acceptance criteria
- Check completeness and consistency
- Cultural sensitivity review (if applicable)
**Documentation Review** (Architect/Analyst):
- Ensure technical accuracy
- Validate against source documents
- Check format and structure
**Handoff Validation** (PO):
- Verify downstream stories can use deliverables
- Confirm no blocking issues
- Validate acceptance criteria coverage
template: |
- [ ] Pre-Completion Review (@{{primary_agent}}): Validate deliverables before marking complete
- [ ] Documentation Review (@architect or @analyst): Ensure technical accuracy
- [ ] Handoff Validation (@po): Verify downstream story readiness
elicit: true
owner: po
editors: [po, sm]
- id: focus-areas
title: Quality Focus Areas
instruction: |
Specific quality criteria based on story type:
**Documentation/Design Stories**:
- Clarity and completeness
- Consistency across all deliverables
- Proper structure and formatting
**Research Stories**:
- Source verification and citations
- Data accuracy and validation
- Methodology documentation
**Architecture Stories**:
- Technical accuracy
- Alignment with existing patterns
- Scalability and maintainability considerations
**UX Design Stories**:
- Accessibility compliance (WCAG 2.1 AA)
- User-centered design principles
- Consistency with design system
template: |
**Primary Focus**:
- {{focus_area_1}}
- {{focus_area_2}}
**Secondary Focus**:
- {{focus_area_3}}
- {{focus_area_4}}
elicit: true
owner: po
editors: [po]
- id: tasks-breakdown
title: Tasks Breakdown
type: structured-list
instruction: |
Break down the story into time-boxed phases and tasks.
For design/research work, structure by research phases, design iterations, or deliverable creation.
Format:
### Phase N: Phase Name (X hours)
**Task N.M: Task Name** (X hours)
- Bullet point details
- Expected outputs
example: |
### Day 1: Research & Design (8 hours)
**Task 1.1: User Research** (3 hours)
- Conduct 5 user interviews
- Analyze pain points and needs
- Document research findings
**Task 1.2: Design Exploration** (3 hours)
- Create 3 design concepts
- Review with stakeholders
- Select preferred direction
**Task 1.3: Detailed Design** (2 hours)
- Create high-fidelity mockups
- Document design decisions
- Prepare for handoff
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, architect, analyst, po]
- id: testing-validation
title: Testing & Validation
type: structured-text
instruction: |
Define how the deliverables will be validated and tested.
Include validation steps, success criteria, and iteration criteria.
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, architect, qa]
sections:
- id: validation-steps
title: Validation Steps
instruction: |
Define specific validation checkpoints by phase:
- What will be validated
- Who will validate it
- Success criteria for each validation
template: |
**Phase 1 Validation (After Research):**
- [ ] **Research Quality Check:** Verify research methodology and data accuracy
- [ ] **Stakeholder Review:** Present findings to 3+ stakeholders for feedback
- [ ] **Documentation Check:** Ensure all research is properly documented
**Phase 2 Validation (After Design/Deliverables):**
- [ ] **Quality Review:** Validate deliverables meet acceptance criteria
- [ ] **Consistency Check:** Verify consistency across all outputs
- [ ] **Handoff Validation:** Confirm downstream teams can use deliverables
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, qa]
- id: success-criteria
title: Success Criteria
instruction: |
Define measurable success criteria for validation:
- Quality metrics (e.g., 4.5/5 stars from reviews)
- Completeness metrics (e.g., 100% of deliverables complete)
- Usability metrics (e.g., downstream teams need zero clarifications)
template: |
- **Quality:** {{quality_metric}}
- **Completeness:** {{completeness_metric}}
- **Usability:** {{usability_metric}}
- **Accuracy:** {{accuracy_metric}}
elicit: true
owner: qa
editors: [qa, po]
- id: iteration-criteria
title: Review & Iteration Criteria
instruction: |
Define what constitutes minor vs. major changes vs. complete redo:
**Minor Changes:** Quick fixes (30 min - 1 hour)
**Major Changes:** Significant rework (2-4 hours)
**Complete Redo:** Fundamental approach rejected (escalate to PO)
template: |
**Minor Changes ({{minor_time_estimate}}):**
- {{minor_change_example_1}}
- {{minor_change_example_2}}
**Major Changes ({{major_time_estimate}}):**
- {{major_change_example_1}}
- {{major_change_example_2}}
**Complete Redo (Escalate to PO):**
- {{redo_trigger_1}}
- {{redo_trigger_2}}
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, po]
- id: acceptance-criteria
title: Acceptance Criteria
type: categorized-list
instruction: |
Copy and expand acceptance criteria from the parent epic.
Categorize into Must Have, Should Have, and Nice to Have.
elicit: true
owner: po
editors: [po]
sections:
- id: must-have
title: Must Have
instruction: Critical requirements that must be met for story completion
type: checklist
elicit: true
- id: should-have
title: Should Have
instruction: Important requirements that significantly improve quality
type: checklist
elicit: true
- id: nice-to-have
title: Nice to Have
instruction: Optional enhancements that add value but aren't required
type: checklist
elicit: true
- id: dependencies
title: Dependencies
type: structured-list
instruction: |
Document dependencies and blocking relationships:
- Prerequisites: What must be complete before this story starts
- Dependent Stories: What stories are blocked by this story
- External Dependencies: Third-party tools, stakeholder input, etc.
template: |
### Prerequisites (Blocking)
- **Story X.Y:** Brief description of why this blocks
- **External:** Tool/stakeholder needed
### Dependent Stories (This Blocks)
- **Story X.Y:** What they need from this story
- **Epic X:** How this epic depends on these deliverables
elicit: true
owner: po
editors: [po, sm]
- id: deliverables
title: Deliverables
type: structured-list
instruction: |
List all deliverables with clear specifications:
- File locations and formats
- Content requirements
- Examples of expected output
- How deliverables will be used by downstream stories
example: |
### 1. Persona Definitions Document
**Location:** `docs/agents/persona-definitions.md`
**Contents:**
- Complete persona for each agent
- Name, role, archetype, color, icon
- Communication style and traits
- Design rationale
### 2. YAML Export
**Location:** `docs/agents/persona-definitions.yaml`
**Format:**
```yaml
agents:
- id: dev
name: Dex
role: Builder
archetype: Aquarius
```
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, architect]
- id: investment-breakdown
title: Investment Breakdown
type: structured-text
instruction: |
Break down the time and cost investment:
- Research phase hours and cost
- Design phase hours and cost
- Documentation phase hours and cost
- Total investment
template: |
- **Research & Analysis:** {{research_hours}} hours @ ${{hourly_rate}}/hr = ${{research_cost}}
- **Design & Creation:** {{design_hours}} hours @ ${{hourly_rate}}/hr = ${{design_cost}}
- **Documentation:** {{doc_hours}} hours @ ${{hourly_rate}}/hr = ${{doc_cost}}
- **Total:** ${{total_cost}} ({{duration}} @ ${{daily_rate}}/day story rate)
elicit: true
owner: po
editors: [po, pm]
- id: success-metrics
title: Success Metrics
type: bullet-list
instruction: |
Define measurable success metrics for the story:
- Quality metrics (ratings, approvals)
- Adoption metrics (usage by downstream stories)
- Performance metrics (time saved, efficiency gained)
- User satisfaction metrics
example: |
- **Quality:** 5/5 stars from team review
- **Cultural Sensitivity:** 100% approval from diverse reviewers
- **Usability:** Deliverables used by downstream stories without rework
- **Accessibility:** Passes WCAG AA standards
elicit: true
owner: po
editors: [po, qa]
- id: risks-mitigation
title: Risks & Mitigation
type: structured-list
instruction: |
Identify risks specific to design/research work and mitigation strategies.
For each risk, document:
- Risk description
- Likelihood (Low/Medium/High)
- Impact (Low/Medium/High)
- Mitigation strategy
template: |
### Risk 1: {{risk_title}}
- **Likelihood:** {{likelihood}}
- **Impact:** {{impact}}
- **Mitigation:** {{mitigation_strategy}}
elicit: true
owner: po
editors: [po, pm]
- id: dev-notes
title: Dev Notes
instruction: |
Provide contextual information for implementers:
- Design principles and rationale
- Source files and references
- Research findings summary
- Important constraints or considerations
elicit: true
owner: ux-design-expert
editors: [ux-design-expert, architect]
sections:
- id: design-principles
title: Design Principles Applied
instruction: Document key design principles guiding this work
elicit: true
- id: source-references
title: Source Files & References
instruction: |
List all source documents and references:
- Primary source documents (epics, PRDs, decisions)
- Current files to reference or modify
- Research sources and citations
- External tools or resources needed
elicit: true
- id: related-documents
title: Related Documents
type: link-list
instruction: Link to related epics, decisions, and reference materials
template: |
- **Epic:** [Epic {{epic_num}} - {{epic_title}}](../epics/epic-{{epic_num}}-{{epic_slug}}.md)
- **Decision:** [Decision #{{decision_num}} - {{decision_title}}](../one-pagers/DECISION-{{decision_num}}-{{decision_slug}}.md)
- **Research:** {{research_references}}
elicit: true
owner: po
editors: [po]
- id: change-log
title: Change Log
type: table
columns: [Date, Version, Description, Author]
instruction: Track changes made to this story document
owner: po
editors: [po, ux-design-expert, architect, qa]
- id: dev-agent-record
title: Dev Agent Record
instruction: This section is populated by the implementing agent during execution
owner: implementing-agent
editors: [ux-design-expert, architect, analyst]
sections:
- id: agent-model
title: Agent Model Used
template: "{{agent_model_name_version}}"
instruction: Record the specific AI agent model and version used
owner: implementing-agent
editors: [implementing-agent]
- id: debug-log-references
title: Debug Log References
instruction: Reference any debug logs or traces generated during work
owner: implementing-agent
editors: [implementing-agent]
- id: completion-notes
title: Completion Notes
instruction: Notes about completion, issues encountered, decisions made
owner: implementing-agent
editors: [implementing-agent]
- id: file-list
title: File List
instruction: List all files created, modified, or referenced during story execution
owner: implementing-agent
editors: [implementing-agent]
- id: qa-results
title: QA Results
instruction: Results from QA review of the completed story deliverables
owner: qa
editors: [qa]
template: |
### Quality Review Summary
**Reviewer:** @qa ({{qa_agent_name}})
**Review Date:** {{review_date}}
**Overall Score:** {{score}}/10
### Deliverables Validation
- [ ] All deliverables present and complete
- [ ] Quality meets acceptance criteria
- [ ] Downstream stories can use deliverables
- [ ] Documentation is clear and accurate
### Issues Found
{{issues_list}}
### Recommendations
{{recommendations}}
### Approval Status
{{approval_status}}
metadata:
template_type: design-story
compatible_agents:
- ux-design-expert
- architect
- analyst
- po
- qa
incompatible_agents:
- dev
- github-devops
story_types:
- design
- research
- architecture
- documentation
- planning
version_history:
- version: 1.0
date: 2025-01-14
author: "@po (Pax)"
changes: "Initial design story template based on Story 6.1.1 hybrid approach"