flow-elaboration-to-construction
Orchestrate Elaboration→Construction phase transition with iteration planning, team scaling, and full-scale development kickoff
What this skill does
# Elaboration → Construction Phase Transition Flow
**You are the Core Orchestrator** for the critical Elaboration→Construction 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**: Elaboration (architecture proven, risks retired)
**To**: Construction (full-scale iterative development)
**Key Milestone**: Construction Phase Entry
**Success Criteria**:
- Architecture baselined and stable
- First 2 iterations planned with ready backlog
- Development process tailored and team trained
- CI/CD pipeline operational
- Iteration 0 (infrastructure) complete
**Expected Duration**: 1-2 weeks setup, 15-20 minutes orchestration
## Natural Language Triggers
Users may say:
- "Transition to Construction"
- "Start Construction phase"
- "Begin building"
- "Move to Construction"
- "Scale up for Construction"
- "Start full development"
You recognize these as requests for this orchestration flow.
## Parameter Handling
### --guidance Parameter
**Purpose**: User provides upfront direction to tailor orchestration priorities
**Examples**:
```
--guidance "Team scaling from 5 to 20 developers, need extensive onboarding"
--guidance "Fast track, minimal documentation, focus on delivery"
--guidance "Offshore team joining, need extra process documentation"
--guidance "Complex integrations, need thorough environment setup"
```
**How to Apply**:
- Parse guidance for keywords: scaling, timeline, team, infrastructure
- Adjust agent assignments (add environment-engineer for complex setup)
- Modify artifact depth (comprehensive vs minimal documentation)
- Influence priority ordering (infrastructure vs process focus)
### --interactive Parameter
**Purpose**: You ask 5-8 strategic questions to understand project context
**Questions to Ask** (if --interactive):
```
I'll ask 6 strategic questions to tailor the Construction transition to your needs:
Q1: What's your team scaling plan?
(e.g., 5→20 developers, gradual vs immediate, onshore/offshore mix)
Q2: What are your infrastructure priorities?
(Help me focus Iteration 0 on critical infrastructure needs)
Q3: What's your iteration cadence preference?
(1 week, 2 weeks, 3 weeks - affects planning depth)
Q4: How mature is your CI/CD pipeline?
(Determines infrastructure setup focus)
Q5: What's your biggest concern for Construction?
(e.g., quality, velocity, team coordination, technical debt)
Q6: Do you need specialized environments?
(e.g., compliance environments, performance testing, security scanning)
Based on your answers, I'll adjust:
- Agent assignments (infrastructure vs process focus)
- Iteration planning depth (detailed vs high-level)
- Onboarding materials (comprehensive vs minimal)
- Environment setup complexity
```
**Synthesize Guidance**: Combine answers into structured guidance string for execution
## Artifacts to Generate
**Primary Deliverables**:
- **ABM Validation Report**: Elaboration exit criteria → `.aiwg/reports/abm-validation-report.md`
- **Iteration 0 Completion Report**: Infrastructure readiness → `.aiwg/reports/iteration-0-completion.md`
- **Development Process Guide**: Tailored process → `.aiwg/planning/development-process-guide.md`
- **Iteration Plan - Sprint 1**: First iteration → `.aiwg/planning/iteration-plan-001.md`
- **Iteration Plan - Sprint 2**: Second iteration → `.aiwg/planning/iteration-plan-002.md`
- **Team Onboarding Guide**: New member guide → `.aiwg/team/onboarding-guide.md`
- **Architecture Stability Report**: Change tracking → `.aiwg/reports/architecture-stability-report.md`
- **Construction Readiness Report**: Final go/no-go → `.aiwg/reports/construction-readiness-report.md`
**Supporting Artifacts**:
- Environment setup scripts
- CI/CD pipeline configurations
- Team RACI matrix updates
- Dual-track workflow setup
## Multi-Agent Orchestration Workflow
### Step 1: Validate Architecture Baseline Milestone (ABM)
**Purpose**: Verify Elaboration phase complete before starting Construction
**Your Actions**:
1. **Check for Required Elaboration Artifacts**:
```
Read and verify presence of:
- .aiwg/architecture/software-architecture-doc.md
- .aiwg/architecture/adr/*.md
- .aiwg/requirements/supplemental-specification.md
- .aiwg/testing/master-test-plan.md
- .aiwg/risks/risk-list.md (≥70% retired)
- .aiwg/requirements/realizations/DES-UCR-*.md (behavioral specs — Layer 3)
- .aiwg/architecture/method-contracts/DES-MIC-*.md (interface contracts)
```
2. **Launch ABM Validation Agent**:
```
Task(
subagent_type="project-manager",
description="Validate Architecture Baseline Milestone criteria",
prompt="""
Read gate criteria from: $AIWG_ROOT/agentic/code/frameworks/sdlc-complete/flows/gate-criteria-by-phase.md
Validate ABM criteria:
- Software Architecture Document BASELINED
- Executable architecture baseline OPERATIONAL
- All P0/P1 architectural risks RETIRED/MITIGATED
- ≥70% of all risks retired or mitigated
- Requirements baseline ESTABLISHED (≥10 use cases)
- Behavioral specifications COMPLETE (Layer 3):
- ≥80% of architecturally significant UCs have realizations
- State machine specs for stateful entities
- Decision tables for complex branching logic
- Method-level interface contracts for key components
- Pseudo-code specifications COMPLETE for first iteration scope (Layer 4):
- Algorithm specs for non-trivial logic
- Error handling trees for critical paths
- Data structure definitions with invariants
- Spec-to-UC traceability chain validated
- Master Test Plan APPROVED
- Development Case tailored
- Test environments OPERATIONAL
Generate ABM Validation Report:
- Status: PASS | FAIL
- Criteria checklist with evidence
- Behavioral spec coverage: X/Y use cases with realizations
- Pseudo-code spec coverage: X/Y methods with specs
- Decision: GO to Construction | NO-GO
- Gaps (if NO-GO): List missing artifacts and specs
Save to: .aiwg/reports/abm-validation-report.md
"""
)
```
3. **Decision Point**:
- If ABM PASS → Continue to Step 2
- If ABM FAIL → Report gaps, recommend extending Elaboration
- Escalate to user for executive decision if criteria partially met
**Communicate Progress**:
```
✓ Initialized ABM validation
⏳ Validating Elaboration exit criteria...
✓ ABM Validation complete: [PASS | FAIL]
```
### Step 2: Execute Iteration 0 (Infrastructure Setup)
**Purpose**: Scale infrastructure for full Construction team
**Your Actions**:
1. **Launch Infrastructure Setup Agents** (parallel):
```
# Agent 1: DevOps Engineer
Task(
subagent_type="devops-engineer",
description="Setup CI/CD pipeline and environments",
prompt="""
Setup Construction infrastructure:
CI/CD Pipeline:
- Build automation (compile, package, containerize)
- Test automation (unit, integration, E2E)
- Deployment automation (dev, test, staging)
- Quality gates (coverage, security scans)
Environments:
- Development: Per-developer or shared
- Test: Shared integration environment
- Staging: Production-like validation
- Production: Provisioned (not deployed)
Document setup in: .aiwg/working/construction/infrastructure/ci-cd-setup.md
"""
)
# Agent 2: Build Engineer
Task(
subagent_type="build-engineer",
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.