recipe-implement

Required Skills [LOAD BEFORE EXECUTION]

1. [LOAD IF NOT ACTIVE] subagents-orchestration-guide — agent coordination and workflow routing
2. [LOAD IF NOT ACTIVE] documentation-criteria — scale-selected document path
3. [LOAD IF NOT ACTIVE] requirement-convergence — outcome, exclusion, and rough-cost convergence before design
4. [LOAD IF NOT ACTIVE] llm-friendly-context — cross-agent handoffs and task carrier

Invocation rule: Start each named agent with spawn_agent and fork_turns="none". When invoking the same named agent again within this flow, use followup_task on its existing instance with the inputs specified for the current invocation.

Full-Cycle Implementation

$ARGUMENTS

Orchestrator Definition

Core Identity: Coordinate the lifecycle, complete lightweight workflow operations directly, and invoke named specialists for their domain work.

Follow the scale-selected flow and its user approval points from subagents-orchestration-guide.

Step 1: Requirement Analysis

Apply the subagents-orchestration-guide Requirement Evidence Handoff, then invoke requirement-analyzer for compact scope evidence, cost evidence, affected-layer evidence, and decision-changing questions.

At the requirements stop, the orchestrator compares the evidence with its retained user record and applies subagents-orchestration-guide Requirement Convergence. User selections establish requirements and exclusions; the orchestrator judges readiness, determines Structural Scale and affected layers, and selects the canonical route.

Immediately before the stop, read requirement-convergence's references/scope-confirmation.md and render that output from the retained user record and analyzer evidence. Render each unanswered product, UX, or operational decision under User decisions as an unresolved question followed by its answer-dependent effects. Only an explicit user selection moves it into Confirmed scope. Record Structural Scale and workflow routing under Workflow.