한국어 문서: README_kr.md
RTL Agent Team
A Claude Code plugin for automated RTL design and verification.
94 specialized AI agents + 93 skills automate the 6-Phase pipeline:
Research → Architecture → μArch → RTL → Verify → Design Note.
A Claude Code plugin for automated RTL design and verification.
Automates the 6-Phase design pipeline (Research → Architecture → μArch → RTL → Verify → Design Note) with 94 specialized AI agents + 93 skills + 12 reference documents.
Marketplace
This repository serves as the RTL Agent Marketplace, providing hardware design plugins.
| Plugin | Description | Version |
|---|
| rtl-agent-team | 94-agent RTL design pipeline (Research → Architecture → μArch → RTL → Verify → Design Note) | 0.9.0 |
| systemverilog-lsp | SystemVerilog/Verilog LSP (slang-server based — diagnostics, hover, go-to-definition, etc.) | 1.1.1 |
Additional plugins (domain knowledge packages, MCP servers, specialized skills, etc.) will be added to the Marketplace over time.
Quick Start
# 1. Register the Marketplace
/plugin marketplace add babyworm/rtl-agent-team
# 2. Install plugins
/plugin install rtl-agent-team
/plugin install systemverilog-lsp # (optional) SV LSP
# 3. Check environment
/rtl-agent-team:rat-setup
# 4. Full automation (or "Design an H.264 TQ subsystem")
/rtl-agent-team:rat-auto-design
If systemverilog-lsp is installed but slang-server is missing, the sub-plugin checks on SessionStart and prompts for local (~/.local/bin, recommended), global, or skip.
Installation
Install from Claude Code chat (recommended)
/plugin marketplace add babyworm/rtl-agent-team
/plugin install rtl-agent-team
Verify installation: /plugin
Install from CLI
claude plugin marketplace add babyworm/rtl-agent-team
claude plugin install rtl-agent-team
Local symlink for development
When developing with direct access to the plugin source:
git clone https://github.com/babyworm/rtl-agent-team.git
ln -s "$(pwd)/rtl-agent-team" ~/.claude/plugins/local/rtl-agent-team
Usage
Routing contract
- Route user intent to Action Skills first (for example,
/rtl-agent-team:rat-auto-design, /rtl-agent-team:rtl-p5-verify).
- Orchestrator agents are internal execution units and are spawned by Action Skills via
Task(...).
- Policy skills are loaded by orchestrators via
skills: [*-policy].
rtl-orchestrate is an internal routing reference skill (user-invocable: false), not a user slash command.
Full automation
/rtl-agent-team:rat-auto-design
Runs the entire 6-Phase pipeline automatically. You can also use natural language, e.g., "Design an H.264 TQ subsystem".
Autopilot escalation ladder
rat-auto-design gates use a per-gate retry ladder:
1..N: primary strategyN+1..2N: fallback strategy (scope split + agent composition switch)2N+1: last-chance alternative (one automatic attempt)- after last-chance fail: stop and ask user guidance
Dynamic fallback guidance is injected through state (orchestration_control.dynamic_prompt_text) and surfaced by Stop hooks.
Pipeline composition (split execution)
/rtl-agent-team:rat-dse # Phase 1→2: Deep algorithm + architecture exploration (DSE)
/rtl-agent-team:codec-rd-eval # BD-PSNR/BD-rate evaluation for algorithm comparison
/rtl-agent-team:codec-conformance-eval # Decoder conformance evaluation (JVET/JCTVC/3rd party)
/rtl-agent-team:rat-p1p3-spec-uarch # Phase 1→3: Spec → μArch design documents
/rtl-agent-team:rat-p4p5-impl-verify # Phase 4→5: μArch → RTL implementation + verification
Split the pipeline for human review between design and implementation:
rat-dse: Deep Design Space Exploration — compare multiple algorithms and architecture candidates with quantitative trade-offs. Can also transform an existing functional C model into an architectural reference model. Stops at Phase 2 for review.rat-p1p3-spec-uarch: Standard Phase 1→3 — produce design documents through μArch. Stops for review before RTL.rat-p4p5-impl-verify: Phase 4→5 — implement RTL and run full verification from approved μArch documents.
Resume interrupted pipeline
If rat-auto-design is interrupted, progress is saved automatically. Re-run the same command to resume from the last incomplete step — completed phases are skipped.
Project initialization
/rtl-agent-team:rat-init-project
Creates the project directory structure, deploys coding convention rules, and auto-installs EDA wrapper scripts (run_sim.sh, run_lint.sh, run_syn.sh, run_cdc.sh) into the project via a hook-driven bootstrap. Existing scripts are never overwritten (non-destructive policy).
For EDA tool verification and installation, run /rtl-agent-team:rat-setup (one-time per machine).
Individual skills