Stats
Actions
Tags
From rtl-agent-team
Generates design documents from spec through microarchitecture (Phase 1→3) with research, block architecture, reference model, and BFM, stopping before RTL for human review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rtl-agent-team:rat-p1p3-spec-uarch [spec-file or project-description][spec-file or project-description]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<Purpose>
<Use_When>
<Do_Not_Use_When>
None — this pipeline starts from Phase 1.
Task(subagent_type="rtl-agent-team:spec-to-uarch-orchestrator", prompt="Execute Phase 1→3 spec-to-uarch pipeline. User input: $ARGUMENTS")
Do not perform any work directly. The orchestrator agent manages phase sequencing, 3-round iterative reviews, quality gates, ADR recording, and state management.
npx claudepluginhub babyworm/rtl-agent-team --plugin rtl-agent-teamDefines phase gate rules, cascading quality protocol, handoff checklists, and ADR requirements for a Phase 1→3 specification-to-microarchitecture pipeline. Pure reference — no orchestration.
Creates comprehensive RTL implementation plans for hardware designs like DMA controllers, UARTs, and memory subsystems, covering blocks, interfaces, clocks, FSMs, and pipelines.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.