🚀 Socket Launch Week Day 5:Introducing Repository Access Permissions and Custom Roles.Learn more
Sign In

digital-chip-design-agents

Package Overview
Dependencies
Maintainers
1
Versions
7
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

digital-chip-design-agents

Full digital chip design pipeline — 15 Claude Code plugins across 14 domains, from infrastructure setup through tape-out and firmware, with closed-loop verification↔RTL feedback.

latest
Source
npmnpm
Version
1.7.0
Version published
Maintainers
1
Created
Source

digital-chip-design-agents

Claude Code marketplace plugin — full digital chip design pipeline.
15 plugins · 16 skill files · 13 chip-design domains + infrastructure + pipeline orchestrator · closed-loop verification↔RTL feedback.

Validate

Quick Start

With Node.js (≥18), install everything with one command — no clone, no Python:

npx digital-chip-design-agents      # detects your AI agents and installs after a confirm

Then just describe your task in natural language:

Run the RTL design flow for my AXI DMA controller block
Analyse timing violations on this routed DEF and suggest ECOs
Build a UVM testbench for my FIFO block

Claude automatically loads the correct skill before executing.

For the install script, selective marketplace install, other AI assistants (Copilot / Gemini / OpenCode / Codex), and all flags, see docs/INSTALL.md.

Available Plugins

Plugin NameDomainInvoke When You Want To...
chip-design-architectureArchitecture EvaluationExplore microarch candidates, estimate PPA, assess risk
chip-design-rtlRTL Design (SystemVerilog)Write, lint, CDC-check, or synthesis-check RTL
chip-design-verificationFunctional Verification (UVM)Build testbench, write tests, close coverage, run regression
chip-design-formalFormal Verification (FPV/LEC)Prove properties, check equivalence, close formal gaps
chip-design-synthesisLogic SynthesisSet up SDC, run synthesis, verify netlist with LEC
chip-design-dftDesign for TestPlan DFT, insert scan, run ATPG, set up JTAG
chip-design-staStatic Timing AnalysisAnalyse timing, guide ECO closure, sign off timing
chip-design-hlsHigh-Level SynthesisConvert C/C++ to RTL, optimise directives, co-simulate
chip-design-pdPhysical DesignFull PD flow: floorplan → placement → CTS → routing → sign-off
chip-design-socSoC IP IntegrationQualify IPs, configure bus fabric, run chip-level sim
chip-design-compilerCompiler ToolchainBuild LLVM/GCC backend, assembler, linker, runtime for custom ISA
chip-design-firmwareEmbedded FirmwareBSP, HAL drivers, RTOS integration, firmware validation
chip-design-fpgaFPGA EmulationPort ASIC to FPGA, bring up hardware, validate SW on prototype
chip-design-infrastructureInfrastructure & MemoryDetect EDA tools, deploy wrappers, configure MCP servers, distil domain memory
chip-design-metaPipeline OrchestrationDrive closed-loop verification↔RTL feedback, manage fix_requests, enforce iteration cap

How It Works

Each plugin installs two things:

  • A Skill (plugins/<domain>/skills/<domain>/SKILL.md) — domain knowledge Claude reads before executing. Contains stage-by-stage rules, QoR metrics, common fixes, and output requirements.

  • An Orchestrator Agent (plugins/<domain>/agents/<domain>-orchestrator.md) — a subagent that manages the full multi-stage flow. It sequences stages, enforces pass/fail criteria, applies loop-back rules when a stage fails, and escalates clearly when human input is needed.

Skills are loaded autonomously by Claude when you describe a task. Orchestrators are invoked explicitly when you want to run a complete flow end-to-end.

Each orchestrator enforces a strict stage sequence with loop-back rules, and the 13 domains connect into a complete spec→tape-out pipeline. See docs/PIPELINE.md for the flow diagram and loop-back details, and docs/MASTER_INDEX.md for per-domain flow documentation.

Memory System

Each domain orchestrator reads from and writes to a two-tier persistent memory store under memory/:

  • memory/<domain>/knowledge.md — distilled summaries (failure patterns, tool flags, PDK quirks) read by every orchestrator at session start.
  • memory/<domain>/experiences.jsonl — append-only run records written after every signoff or escalation.

Distil accumulated records back into knowledge.md with the memory-keeper skill, and track QoR metrics across runs with tools/qor_trends.py. See memory/README.md for the full schema, distilling workflow, and QoR trend examples.

Repo Structure

digital-chip-design-agents/
├── .claude-plugin/marketplace.json   ← Marketplace registry (all 15 plugins)
├── plugins/                          ← One isolated directory per plugin (skill + orchestrator)
├── ides/                             ← IDE-specific config files (Copilot / Gemini / OpenCode / Codex)
├── memory/                           ← Persistent two-tier per-domain memory (see memory/README.md)
├── docs/                             ← Install guide, pipeline map, and per-domain flow docs
├── tools/qor_trends.py               ← QoR metric trending and regression detection
└── .github/workflows/                ← CI (validate.yml) and release (release.yml)

Contributing

See CONTRIBUTING.md. PRs welcome for:

  • Improved domain rules or QoR metrics in any SKILL.md
  • New loop-back rules in orchestrators
  • New skill domains (e.g., package/assembly, analog integration)

CI validates all files on every PR — the validate workflow must pass before merge.

License

MIT — see LICENSE.

Keywords

claude

FAQs

Package last updated on 20 Jun 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts