/recipe-fullstack-implement

name: recipe-fullstack-implement
description: Orchestrate full-cycle implementation across backend and frontend layers
disable-model-invocation: true

**Explicit User Instruction**: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.

Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

**Context**: Full-cycle fullstack implementation management (Requirements Analysis → Design (backend + frontend) → Planning → Implementation → Quality Assurance)

Orchestrator Definition

**Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)

**Local authority gate**: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

**Review Resolution Gate [MANDATORY]**: Resolve every actionable deliverable-review finding through subagents-orchestration-guide `Review Resolution` before correction or progression. Before the first finding disposition, read `references/review-resolution.md` from the loaded subagents-orchestration-guide skill.

Required Reference

**MANDATORY**: Read `references/monorepo-flow.md` from subagents-orchestration-guide skill BEFORE proceeding. Follow the Fullstack Flow defined there instead of the standard single-layer flow.

Execution Protocol

1. **Invoke named specialists for deliverable production** — pass deliverable paths between them and validate their results (see subagents-orchestration-guide "Orchestrator Execution Boundary") 2. **Follow monorepo-flow.md** for the design phase (multiple Design Docs, design-sync, vertical slicing) 3. **Follow subagents-orchestration-guide skill** for all other orchestration rules (stop points, structured responses, escalation) 4. **Enter autonomous mode** only after "batch approval for entire implementation phase"

At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.

Execution Decision Flow

1. Current Situation Assessment

Instruction Content: $ARGUMENTS

Assess the current situation:

| Situation Pattern | Decision Criteria | Next Action | |------------------|------------------|-------------| | New Requirements | No existing work, new feature/fix request | Start with requirement-analyzer | | Flow Continuation | Existing docs/tasks present, continuation directive | Identify next step in monorepo-flow.md | | Quality Errors | Error detection, test failures, build errors | Execute quality-fixer (layer-appropriate) | | Ambiguous | Intent unclear, multiple interpretations possible | Confirm with user |

2. Progress Verification for Continuation

When continuing existing flow, verify:

• Latest artifacts (PRD/ADR/Design Docs/Work Plan/Tasks)
• Current phase position (Requirements/Design/Planning/Implementation/QA)
• Identify next step in monorepo-flow.md

3. Design through Planning Phase

Execute Skill: external-resource-context before running the external resource hearing in monorepo-flow.md.

**Follow monorepo-flow.md** for the current Large or Medium design-through-planning flow. Its Large table and Medium step range define the required steps, agent invocations, and stop points.

Key points to enforce as the orchestrator runs the flow:

• Create separate Design Docs per layer (see monorepo-flow.md "Layer Context in Design Doc Creation")
• Frontend Design Doc references an applicable approved UI Spec and reuses applicable ui-analyzer output produced earlier in the flow
• Execute document-reviewer once per Design Doc (separate invocations)
• Run design-sync for cross-layer consistency verification
• Pass all Design Docs to work-planner (subagent_type: "dev-workflows:work-planner") with vertical slicing instruction
• Pass the Work Plan to document-reviewer (`doc_type: WorkPlan`) and request batch approval only after the review passes

4. Bind the Applicable Flow

After Structural Scale is determined, follow only that scale's applicable path. Treat each applicable design, review, approval, planning, implementation, verification, cleanup, and reporting phase as a gate. Advance only when the current phase's stated evidence or approval exists; skip only branches whose stated condition is false.

After requirement-analyzer [Stop]

Execute Skill: requirement-convergence before running the hearing protocol.

Build and judge the convergence record from the user's retained wording, using requirement-analyzer `scopeEvidence` and `costEvidence` as supporting facts, then run the requirement-convergence hearing protocol. After the requirements are confirmed, apply the subagents-orchestration-guide Small evidence gate before assigning the final Structural Scale; when the gate is unresolved, invoke codebase-analyzer before routing.

When user responds to questions:

• Update the orchestrator-owned convergence record from the answer, then update the Structural Scale judgment through the Small evidence gate.
• Re-execute requirement-analyzer only when the answer changes the repository analysis target or scope evidence.
• Repeat the hearing until every convergence field is `ready` or `weak-but-explicit`, then proceed with the resulting Scale.

Subagents Orchestration Guide Compliance Execution

**Pre-execution Checklist (MANDATORY)**:

• [ ] Read monorepo-flow.md reference
• [ ] Confirmed relevant flow steps
• [ ] Identified current progress position
• [ ] Clarified next step
• [ ] Recognized stopping points
• [ ] one complete-scope codebase-analyzer result included before Design Doc creation
• [ ] code-verifier included before document-reviewer for each Design Doc
• [ ] **Environment check**: Can I execute per-task