brainstorming
Structured design dialogue that validates ideas before implementation begins.
Create Business Requirements Documents (BRD) following SDD methodology - Layer 1 artifact defining business needs and objectives
Full skill instructions
Create Business Requirements Documents (BRD) - Layer 1 artifact in the SDD workflow that defines high-level business needs, strategic objectives, and success criteria.
Layer: 1 (Entry point - no upstream dependencies)
Downstream Artifacts: PRD (Layer 2), EARS (Layer 3), BDD (Layer 4), ADR (Layer 5)
Before creating this document, you MUST:
List existing upstream artifacts:
ls docs/BRD/ docs/PRD/ docs/EARS/ docs/BDD/ docs/ADR/ docs/SYS/ docs/REQ/ 2>/dev/null
Reference only existing documents in traceability tags
Use null only when upstream artifact type genuinely doesn't exist
NEVER use placeholders like BRD-XXX or TBD
Do NOT create missing upstream artifacts - skip functionality instead
Before creating a BRD, read:
.claude/skills/doc-flow/SHARED_CONTENT.mdai_dev_flow/BRD/BRD-TEMPLATE.mdai_dev_flow/BRD/BRD_CREATION_RULES.mdai_dev_flow/BRD/BRD_VALIDATION_RULES.mdai_dev_flow/PLATFORM_VS_FEATURE_BRD.mdFor New Projects: Use project-init skill first to initialize project structure.
Before creating ANY BRD section, confirm:
ai_dev_flow/ID_NAMING_STANDARDS.md - Element Type Codes tableBRD.{DOC_NUM}.{ELEM_TYPE}.{SEQ} (4 segments, dots)Common Element Types:
| Code | Type | Example |
|---|---|---|
| 01 | Functional Requirement | BRD.02.01.01 |
| 06 | Acceptance Criteria | BRD.02.06.01 |
| 23 | Business Objective | BRD.02.23.01 |
| 32 | Architecture Topic | BRD.02.32.01 |
⚠️ Removed Patterns: Do NOT use
AC-XXX,FR-XXX,BC-XXX,BO-XXXformats.
Use doc-brd when:
CRITICAL DECISION: Before creating a BRD, determine if it's a Platform BRD or Feature BRD.
Does this BRD define infrastructure, technology stack, or cross-cutting concerns?
Does this BRD describe a specific user-facing workflow or feature?
Will other BRDs depend on or reference this BRD's architectural decisions?
Does this BRD establish patterns, standards, or capabilities used across multiple features?
Does this BRD implement functionality on top of existing platform capabilities?
Platform BRD Path:
1. Create Platform BRD (populate sections 3.6 and 3.7)
2. Create ADRs for critical technology decisions (identified in BRD sections 3.6/3.7)
3. Create PRD referencing Platform BRD and ADRs
4. Create additional ADRs for implementation details
5. Continue to SPEC
Feature BRD Path:
1. Create Feature BRD (reference Platform BRD in sections 3.6 and 3.7)
2. Create PRD for feature
3. Create ADRs for implementation decisions (if needed)
4. Continue to SPEC
Platform BRD:
Feature BRD:
Reference: ai_dev_flow/PLATFORM_VS_FEATURE_BRD.md for detailed guidance
Primary Template:
BRD-TEMPLATE.md - Comprehensive business requirements (general purpose)
ai_dev_flow/BRD/BRD-TEMPLATE.mdNote: Use the comprehensive template for all BRD documents. For simpler requirements, complete only the essential sections and mark others as "N/A - Not applicable for this scope".
Note: Technical QA standards, testing strategy, and defect management are documented in PRD-TEMPLATE.md Section 21 (product level).
Two Structure Options:
| Structure | Format | Use When |
|---|---|---|
| Monolithic (Flat) | docs/BRD/BRD-NN_{slug}.md | Single-file documents <25KB, MVP templates |
| Section-Based (Nested) | docs/BRD/BRD-NN_{slug}/BRD-NN.S_{section}.md | Documents >25KB, complex multi-section |
Monolithic Structure (Flat) - for MVP/small documents:
docs/BRD/BRD-NN_{slug}.md (directly in BRD directory, no nested folder)# BRD-NN: Document Title (no .S suffix)ai_dev_flow/BRD/BRD-MVP-TEMPLATE.md or simplified BRD-TEMPLATE.mdSection-Based Structure (Nested) - for large/complex documents:
docs/BRD/BRD-NN_{slug}/BRD-NN.S_{section}.mdBRD-NN_{slug}/ where slug MUST match the index file slug# BRD-NN.S: Section Title (includes .S suffix)ai_dev_flow/BRD/BRD-SECTION-0-TEMPLATE.mdai_dev_flow/BRD/BRD-SECTION-TEMPLATE.mdai_dev_flow/ID_NAMING_STANDARDS.md (Section-Based File Splitting)Document Control (MANDATORY - First section before all numbered sections):
Core Sections:
Platform BRD Additional Sections:
ALWAYS START WITH STRATEGY: Read relevant {project_root}/strategy/ documents FIRST
Reading Order:
{project_root}/strategy/README.md - Performance targets, strategy goals{project_root}/strategy/strategy_overview.md - Strategic framework{project_root}/strategy/core_algorithm.md - Primary algorithm specifications{project_root}/strategy/risk_management.md - Risk management policies{project_root}/strategy/selection_criteria/ - Entry criteriaEvery BRD MUST cite specific strategy document sections in Traceability section.
Purpose: Identify architectural topics requiring decisions with cost-focused, alternatives-based analysis.
Every BRD MUST include Section 7.2: "Architecture Decision Requirements" addressing all 7 mandatory ADR topic categories.
| # | Category | Element ID | Description | When N/A |
|---|---|---|---|---|
| 1 | Infrastructure | BRD.NN.32.01 | Compute, deployment, scaling | Pure data/analytics project |
| 2 | Data Architecture | BRD.NN.32.02 | Database, storage, caching | No persistent data needed |
| 3 | Integration | BRD.NN.32.03 | APIs, messaging, external systems | Standalone system |
| 4 | Security | BRD.NN.32.04 | Auth, encryption, access control | Internal tool, no sensitive data |
| 5 | Observability | BRD.NN.32.05 | Monitoring, logging, alerting | MVP/prototype only |
| 6 | AI/ML | BRD.NN.32.06 | Model serving, training, MLOps | No AI/ML components |
| 7 | Technology Selection | BRD.NN.32.07 | Languages, frameworks, platforms | Using existing stack |
Element Type Code: 32 = Architecture Topic
| Field | Description | Required For |
|---|---|---|
| Status | Selected, Pending, or N/A | All topics |
| Business Driver | WHY this decision matters to business | Selected/Pending |
| Business Constraints | Non-negotiable business rules | Selected/Pending |
| Alternatives Overview | MANDATORY table with cost estimates | Selected |
| Cloud Provider Comparison | MANDATORY GCP/Azure/AWS comparison | Selected |
| Recommended Selection | Selected option with rationale | Selected |
| PRD Requirements | What PRD must elaborate | All topics |
**Alternatives Overview**:
| Option | Function | Est. Monthly Cost | Selection Rationale |
|--------|----------|-------------------|---------------------|
| Serverless | Event-driven compute | $200-$800 | Selected - cost-effective |
| Kubernetes | Container orchestration | $500-$2,000 | Rejected - over-engineered |
| VM-based | Traditional VMs | $400-$1,500 | Rejected - manual scaling |
**Cloud Provider Comparison**:
| Criterion | GCP | Azure | AWS |
|-----------|-----|-------|-----|
| **Service Name** | Cloud Run | Container Apps | Fargate |
| **Est. Monthly Cost** | $300 | $350 | $400 |
| **Key Strength** | Auto-scaling | AD integration | Ecosystem |
| **Key Limitation** | Fewer features | Higher cost | Complex pricing |
| **Fit for This Project** | High | Medium | Medium |
### BRD.01.32.01: Infrastructure
**Status**: Selected
**Business Driver**: Customer onboarding workflow requires scalable compute for variable registration volumes.
**Business Constraints**:
- Must support auto-scaling for peak periods (10x baseline)
- Maximum infrastructure cost: $5,000/month
- 99.9% availability during business hours
**Alternatives Overview**:
| Option | Function | Est. Monthly Cost | Selection Rationale |
|--------|----------|-------------------|---------------------|
| Serverless (Cloud Functions) | Event-driven compute | $200-$800 | Selected - cost-effective for variable load |
| Kubernetes (GKE/EKS) | Container orchestration | $500-$2,000 | Rejected - over-engineered for this scale |
| VM-based (Compute Engine) | Traditional VMs | $400-$1,500 | Rejected - manual scaling overhead |
**Cloud Provider Comparison**:
| Criterion | GCP | Azure | AWS |
|-----------|-----|-------|-----|
| **Service Name** | Cloud Run | Container Apps | Lambda + Fargate |
| **Est. Monthly Cost** | $300 | $350 | $400 |
| **Key Strength** | Simple container deployment | Azure AD integration | Largest ecosystem |
| **Key Limitation** | Fewer enterprise features | Higher baseline cost | Complex pricing |
| **Fit for This Project** | High | Medium | Medium |
**Recommended Selection**: GCP Cloud Run - serverless containers with optimal cost-to-scale ratio.
**PRD Requirements**: Evaluate cold start impact on latency. Specify concurrency limits and scaling policies.
N/A Example:
### BRD.01.32.06: AI/ML Architecture
**Status**: N/A - No AI/ML components in project scope
**Reason**: This feature uses standard rule-based validation. No machine learning, AI agents, or predictive analytics required.
**PRD Requirements**: None for current scope. Flag for Phase 2 evaluation if ML-based fraud detection needed.
Pending Example:
### BRD.01.32.05: Observability
**Status**: Pending - Awaiting infrastructure finalization
**Business Driver**: System monitoring required for SLA compliance.
**Business Constraints**:
- Real-time alerting for system failures
- Minimum 30-day log retention
**Alternatives Overview**: [Placeholder - To be completed after infrastructure selection]
**PRD Requirements**: Complete observability analysis after infrastructure finalization.
BRD Section 7.2 → PRD Section 18 → ADR
(WHAT & WHY & HOW MUCH) (HOW to evaluate) (Final decision)
─────────────────────────────────────────────────────────────────────────
Business drivers Technical details Implementation decision
Business constraints Deep-dive analysis Trade-off analysis
Cost estimates Evaluation criteria Selected approach
Do NOT write: "See ADR-033" or "Reference ADR-045" (ADRs don't exist yet)
Reference: See ai_dev_flow/BRD/BRD_CREATION_RULES.md Section 9 for complete guidelines
CRITICAL: Document Control MUST be the first section at the very top of the BRD (before all numbered sections).
Correct Structure:
# BRD-01: Project Name
## Document Control
[All metadata fields here]
## 1. Executive Summary
[Content here]
Layer 1 (BRD): No upstream tags required (entry point)
Tag Count: 0 tags
Format: BRD has no @ tags since it's Layer 1 (top of hierarchy)
Downstream artifacts will tag BRD (using unified format):
@brd: BRD.01.01.30 (TYPE.NN.TT.SS format)@brd: BRD.01.01.30The SDD framework uses two distinct notation systems for cross-references:
| Notation | Format | Artifacts | Purpose |
|---|---|---|---|
| Dash | TYPE-NN | ADR, SPEC, CTR | Technical artifacts - references to files/documents |
| Dot | TYPE.NN.TT.SS | BRD, PRD, EARS, BDD, SYS, REQ, IMPL, TASKS | Hierarchical artifacts - references to elements inside documents |
Key Distinction:
@adr: ADR-033 → Points to the document ADR-033_risk_limit_enforcement.md@brd: BRD.17.01.01 → Points to element 01.01 inside document BRD-017.mdFor hierarchical requirements (BRD, PRD, EARS, BDD, SYS, REQ):
TYPE.NN.TT.SS (dot separator, 4-segment unified format)TYPE-NN:NNN (colon separator - DEPRECATED)TYPE.NN.TT (3-segment format - DEPRECATED)Examples:
@brd: BRD.17.01.01 ✅@brd: BRD.017.001 ❌ (old 3-segment format)Upstream Sources (what drives BRD creation):
{project_root}/strategy/)Downstream Artifacts (what BRD drives):
Same-Type Document Relationships (conditional):
@related-brd: BRD-NN - BRDs sharing business domain context@depends-brd: BRD-NN - BRD that must be implemented first (e.g., platform BRD before feature BRD)Use questionnaire above to determine Platform vs Feature BRD.
Read relevant {project_root}/strategy/ sections to understand business logic.
Choose appropriate template (comprehensive, simplified, or domain-specific).
Check docs/BRD/ for next available ID number (e.g., BRD-01, BRD-02).
ID Numbering Convention: Start with 2 digits and expand only as needed.
Folder structure (DEFAULT - nested folder per document with descriptive slug):
docs/BRD/BRD-NN_{slug}/ (folder slug MUST match index file slug)docs/BRD/BRD-NN_{slug}/BRD-NN.0_{section_type}.md (shortened, PREFERRED)docs/BRD/BRD-NN_{slug}/BRD-NN.S_{section_type}.md (shortened, PREFERRED)Example (Shortened Pattern - PREFERRED):
docs/BRD/BRD-01_platform_architecture/
├── BRD-01.0_index.md
├── BRD-01.1_executive_summary.md
├── BRD-01.2_business_context.md
└── BRD-01.3_requirements.md
Note: Folder contains descriptive slug, so filenames can omit it. Full pattern (BRD-01.0_platform_architecture_index.md) also accepted for backward compatibility.
OPTIONAL (for small documents <25KB): docs/BRD/BRD-NN_{slug}.md (monolithic)
Complete all required metadata fields and initialize Document Revision History table.
Fill all 18 required sections following template structure.
Platform BRD: Populate sections 3.6 and 3.7 with technology details Feature BRD: Mark sections 3.6 and 3.7 as "N/A - See Platform BRD-NN"
List topics needing architectural decisions (do NOT reference specific ADR numbers).
In Traceability section, link to specific {project_root}/strategy/ sections.
MANDATORY: Create or update docs/BRD/BRD-00_TRACEABILITY_MATRIX.md
ai_dev_flow/BRD/BRD-00_TRACEABILITY_MATRIX-TEMPLATE.mdRun validation scripts:
# BRD structure validation
./ai_dev_flow/scripts/validate_brd_template.sh docs/BRD/BRD-01_*.md
# Link integrity
./ai_dev_flow/scripts/validate_links.py --path docs/BRD/
Commit BRD file and traceability matrix together.
BRD-Specific Validation:
./ai_dev_flow/scripts/validate_brd_template.sh docs/BRD/BRD-01_platform.md
Quality Gates Validation:
./scripts/validate_quality_gates.sh docs/BRD/BRD-01_platform.md
All diagrams MUST use Mermaid syntax. Text-based diagrams (ASCII art, box drawings) are prohibited.
See: ai_dev_flow/DIAGRAM_STANDARDS.md and mermaid-gen skill.
{project_root}/strategy/ sectionsCRITICAL: Execute this validation loop IMMEDIATELY after document creation. Do NOT proceed to next document until validation passes.
LOOP:
1. Run BRD template validation script
2. IF errors found: Fix issues
3. IF warnings found: Review and address
4. IF unfixable issues: Log for manual review, continue
5. IF clean: Mark VALIDATED, proceed
# BRD structure validation (primary)
./ai_dev_flow/scripts/validate_brd_template.sh docs/BRD/BRD-NN_slug.md
# Link integrity validation
./ai_dev_flow/scripts/validate_links.py --path docs/BRD/
# Quality gates validation
./scripts/validate_quality_gates.sh docs/BRD/BRD-NN_slug.md
| This Layer | Required Upstream Tags | Count |
|---|---|---|
| BRD (Layer 1) | None (entry point) | 0 tags |
| Issue | Fix Action |
|---|---|
| Invalid tag format | Correct to TYPE.NN.TT.SS (4-segment) or TYPE-NN format |
| Broken link | Recalculate path from current location |
| Missing traceability section | Insert from template |
| Code | Description | Severity |
|---|---|---|
| XDOC-006 | Tag format invalid | ERROR |
| XDOC-008 | Broken internal link | ERROR |
| XDOC-009 | Missing traceability section | ERROR |
Blocking: YES - Cannot proceed to next document until Phase 1 validation passes with 0 errors.
After creating BRD, use:
doc-prd - Create Product Requirements Document (Layer 2)
The PRD will:
@brd: BRD.NN.01.SS tags (unified 4-segment format)For supplementary documentation related to BRD artifacts:
BRD-REF-NNN_{slug}.mddoc-ref skillBRD-REF documents are EXEMPT from ready-scores and quality gates:
| Standard BRD | BRD-REF |
|---|---|
| PRD-Ready Score: ✅ Required (≥90%) | PRD-Ready Score: NOT APPLICABLE |
| Cumulative tags: Required | Cumulative tags: NOT REQUIRED |
| Quality gates: Full validation | Quality gates: EXEMPT |
| Format: Structured 18 sections | Format: Free format, business-oriented |
Purpose: BRD-REF documents are reference targets that other documents link to. They provide supporting information, context, or external references but do not define formal business requirements.
Reference: See ai_dev_flow/BRD/BRD_VALIDATION_RULES.md for validation details.
ai_dev_flow/SPEC_DRIVEN_DEVELOPMENT_GUIDE.mdai_dev_flow/PLATFORM_VS_FEATURE_BRD.mdai_dev_flow/BRD/BRD_CREATION_RULES.mdai_dev_flow/BRD/BRD_VALIDATION_RULES.mdai_dev_flow/BRD/README.md.claude/skills/doc-flow/SHARED_CONTENT.mdBRD Purpose: Define business needs and objectives
Layer: 1 (Entry point)
Tags Required: None (0 tags)
Key Decision: Platform vs Feature BRD
Critical Sections:
Next: doc-prd
Structured design dialogue that validates ideas before implementation begins.
Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.
Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.
Introduction to the obra skills system with mandatory skill invocation rules and best practices.
Execute a written implementation plan with critical review and task checkpoints.
Delegate independent tasks to specialized agents working concurrently with isolated context.
Isolated git worktrees with smart directory selection and safety verification.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Plan searchable and shareable content that drives traffic, builds authority, and generates leads.
README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.
Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.
Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.
The world's fastest calendar for remote work
Capture, organize, and utilize your knowledge effortlessly.
Instant Summaries of Audio & Video Interviews with AnySummary
Transform PDFs into engaging mind maps.
Chat with any PDF instantly
Create an optimal daily plan using your voice
A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.
AskYourPDF Pricing Plans: Tailored to Your Needs