rat-auto-design

name	rat-auto-design
description	Full 6-phase RTL pipeline from spec to verified design (P1 research through P6 design note). Triggers: 'design a chip', 'full pipeline', 'autopilot'.
user-invocable	true
argument-hint	[spec-file or project-description]
allowed-tools	Bash, Read, Write, Edit, Task, Grep, Glob, AskUserQuestion, Skill, TeamCreate, TeamDelete, Agent, SendMessage, TaskCreate, TaskList, TaskUpdate

Execute the full RTL design pipeline from specification to verified silicon. In team mode (default), the skill directly sequences phases using phase-specific team skills for parallel execution. In sequential mode (--no-team), delegates to autopilot-orchestrator.

<Use_When>

• Starting a complete RTL design from a specification document
• User says "design a chip", "full pipeline", "RTL design", "autopilot"
• Need end-to-end flow: Research → Architecture → μArch → RTL → Verify → Design Note </Use_When>

<Do_Not_Use_When>

• Only need a specific phase (use the phase-specific skill instead)
• Only need design space exploration (use rat-dse)
• Only need design documents without RTL (use rat-p1p3-spec-uarch) </Do_Not_Use_When>

Prerequisites

None — this is the full pipeline entry point. Setup is handled automatically.

Execution

# Parse mode
TEAM_MODE = "--no-team" not in ARGUMENTS

if TEAM_MODE:
    # ═══ TEAM MODE: Skill sequences phases directly ═══

    # State management
    Write(".rat/state/rat-auto-design-state.json",
      { "schema_version": "3.0", "status": "running",
        "current_phase": 1, "execution_mode": "team",
        "phases": { "1": {"status":"pending"}, "2": {"status":"pending"},
                    "3": {"status":"pending"}, "4": {"status":"pending"},
                    "5": {"status":"pending"}, "6": {"status":"pending"} } })

    # Phase 1: Research (team)
    Skill(skill="rtl-agent-team:rtl-p1-research-team", args="$ARGUMENTS")
    # Gate check + state update

    # Phase 2: Architecture + RefC (team)
    Skill(skill="rtl-agent-team:rtl-p2-arch-team", args="Phase 1 complete")
    # Gate check + state update

    # Phase 3: uArch + BFM (team)
    Skill(skill="rtl-agent-team:rtl-p3-uarch-team", args="Phase 2 complete")
    # Gate check + state update

    
    Skill(skill=, args=)
    

    
    Skill(skill=, args=)
    

    
    Bash()
    Task(subagent_type=,
         prompt=)

    
    
    
    Bash()
    
    Bash()

:
    
    Task(subagent_type=,
         prompt=)

Team mode uses native teams within each phase for parallel execution (Orchestrator as Teammate pattern). Each phase team skill handles its own TeamCreate/TeamDelete lifecycle with a coordinator teammate + 3-5 workers. Sequential mode delegates everything to the autopilot-orchestrator.

Output

• Design artifacts: docs/phase-1-research/ through docs/phase-5-verify/
• Phase 6 design note and review verdicts: reviews/phase-6-review/ (Phase 6 is the design review + documentation phase; its outputs live under reviews/, not docs/)
• rtl/*/*.sv — lint-clean, unit-tested RTL modules
• sim/ — testbenches, regression results, and coverage data
• reviews/ — per-phase review reports with final compliance verdict