flow-construction-to-transition

What this skill does

<!-- AIWG-SKILL-CALLOUT -->
> **Skill access pattern (post-kernel-pivot, 2026.5+)**
>
> Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via:
>
> ```bash
> aiwg discover "<capability>"
> aiwg show skill <name>
> ```
>
> Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).


# Construction → Transition Phase Transition Flow

**You are the Core Orchestrator** for the critical Construction→Transition phase transition.

## Your Role

**You orchestrate multi-agent workflows. You do NOT execute bash scripts.**

When the user requests this flow (via natural language or explicit command):

1. **Interpret the request** and confirm understanding
2. **Read this template** as your orchestration guide
3. **Extract agent assignments** and workflow steps
4. **Launch agents via Task tool** in correct sequence
5. **Synthesize results** and finalize artifacts
6. **Report completion** with summary

## Phase Transition Overview

**From**: Construction (feature-complete, tested, deployment-ready)
**To**: Transition (production deployed, users trained, support operational)

**Key Milestone**: Product Release Milestone (PRM)

**Success Criteria**:
- Production deployment successful and stable
- Users trained and actively using system
- Support and operations teams operational
- Hypercare period completed without critical issues
- Business value validated

**Expected Duration**: 2-4 weeks (typical), 20-30 minutes orchestration

## Natural Language Triggers

Users may say:
- "Transition to production"
- "Start Transition phase"
- "Prepare for deployment"
- "Move to Transition"
- "Ready to deploy"
- "Deploy to production"
- "Begin production rollout"
- "Start hypercare period"

You recognize these as requests for this orchestration flow.

## Parameter Handling

### --guidance Parameter

**Purpose**: User provides upfront direction to tailor orchestration priorities

**Examples**:
```
--guidance "High-risk deployment, need extensive validation and rollback plans"
--guidance "Limited support team, extra training and documentation needed"
--guidance "Performance critical, validate SLAs thoroughly before cutover"
--guidance "Phased rollout required, start with pilot users only"
```

**How to Apply**:
- Parse guidance for keywords: rollback, training, performance, phased, pilot
- Adjust agent assignments (add reliability-engineer for performance focus)
- Modify deployment strategy (phased vs. big-bang based on risk tolerance)
- Influence validation depth (comprehensive vs. streamlined based on risk)

### --interactive Parameter

**Purpose**: You ask 6-8 strategic questions to understand deployment context

**Questions to Ask** (if --interactive):

```
I'll ask 8 strategic questions to tailor the Transition to your needs:

Q1: What deployment strategy do you prefer?
    (e.g., big-bang, phased/canary, blue-green, feature toggles)

Q2: How critical is zero-downtime deployment?
    (Helps me plan cutover strategy and rollback procedures)

Q3: What's your support team's readiness level?
    (Determines training depth and handover timeline)

Q4: What are your rollback criteria?
    (Define when to pull back vs. fix forward)

Q5: How long should the hypercare period be?
    (7 days minimum, 14 days standard, 30 days for critical systems)

Q6: Are there specific compliance requirements for production?
    (e.g., SOC2 audit trails, HIPAA logging, PCI-DSS controls)

Q7: What's your user adoption strategy?
    (All at once, pilot group first, gradual onboarding)

Q8: What business metrics define success?
    (KPIs to validate during hypercare and PRM review)

Based on your answers, I'll adjust:
- Deployment strategy and validation depth
- Support training intensity
- Hypercare monitoring focus
- Success criteria thresholds
```

**Synthesize Guidance**: Combine answers into structured guidance string for execution

## Artifacts to Generate

**Primary Deliverables**:
- **Production Deployment Report**: Deployment execution and validation → `.aiwg/deployment/production-deployment-report.md`
- **User Training Report**: Training delivery and UAT results → `.aiwg/deployment/user-training-report.md`
- **Support Handover Report**: Support team readiness → `.aiwg/deployment/support-handover-report.md`
- **Operations Handover Report**: Ops team readiness → `.aiwg/deployment/operations-handover-report.md`
- **Hypercare Daily Reports**: Production monitoring → `.aiwg/reports/hypercare-day-*.md`
- **PRM Report**: Milestone readiness assessment → `.aiwg/reports/prm-report.md`

**Supporting Artifacts**:
- Infrastructure Readiness Report
- Operational Runbooks
- Support Knowledge Base
- Complete audit trails

## Multi-Agent Orchestration Workflow

### Step 1: Validate Construction Exit Criteria (OCM)

**Purpose**: Verify Operational Capability Milestone achieved before starting Transition

**Your Actions**:

1. **Check for Required Construction Artifacts**:
   ```
   Read and verify presence of:
   - .aiwg/deployment/deployment-plan.md
   - .aiwg/deployment/release-notes.md
   - .aiwg/deployment/support-runbook.md
   - .aiwg/testing/test-evaluation-summary.md
   - .aiwg/deployment/bill-of-materials.md
   ```

2. **Launch Gate Check Agent**:
   ```
   Task(
       subagent_type="project-manager",
       description="Validate Construction gate (OCM) criteria",
       prompt="""
       Read gate criteria from: $AIWG_ROOT/agentic/code/frameworks/sdlc-complete/flows/gate-criteria-by-phase.md

       Validate OCM criteria:
       - All planned features IMPLEMENTED (100% Must Have, ≥80% Should Have)
       - All acceptance tests PASSING (≥98% pass rate)
       - Test coverage targets MET (unit ≥80%, integration ≥70%, e2e ≥50%)
       - Zero P0 (Show Stopper) defects open
       - Zero P1 (High) defects open OR all have approved waivers
       - Performance tests PASSING (response time, throughput, concurrency)
       - Security tests PASSING (no High/Critical vulnerabilities)
       - CI/CD pipeline OPERATIONAL
       - Deployment plan COMPLETE and APPROVED
       - Operational Readiness Review (ORR) PASSED

       Generate OCM Validation Report:
       - Status: PASS | FAIL
       - Criteria checklist with results
       - Decision: GO to Transition | NO-GO
       - Gaps (if NO-GO): List missing artifacts

       Save to: .aiwg/reports/ocm-validation-report.md
       """
   )
   ```

3. **Decision Point**:
   - If OCM PASS → Continue to Step 2
   - If OCM FAIL → Report gaps to user, recommend `flow-elaboration-to-construction` to complete Construction
   - Escalate to user for executive decision if criteria partially met

**Communicate Progress**:
```
✓ Initialized OCM validation
⏳ Validating Construction exit criteria...
✓ OCM Validation complete: [PASS | FAIL]
```

### Step 2: Prepare Production Environment

**Purpose**: Ensure production infrastructure is provisioned, configured, and validated

**Your Actions**:

1. **Read Infrastructure Context**:
   ```
   Read:
   - .aiwg/deployment/infrastructure-definition.md
   - .aiwg/deployment/deployment-environment.md
   - .aiwg/architecture/software-architecture-doc.md (deployment view)
   ```

2. **Launch Infrastructure Validation Agents** (parallel):
   ```
   # Agent 1: DevOps Engineer
   Task(
       subagent_type="devops-engineer",
       description="Validate production infrastructure readiness",
       prompt="""
       Read infrastructure definition and deployment environment docs

       Validate production environment:
       - Infrastructure provisioned (compute, storage, network)
       - Capacity validated (expected load + 20% buffer)
       - High availability configured (redundancy, failover)
       - Scalability tested (autoscaling operational)