Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
Back to list

Readable Verilog Generator

Generates, annotates, reviews, repairs and validates synthesizable Verilog-2001 RTL behind a strict multi-gate quality pipeline.

Dev & CodingAdvanced24112AI score 9/10Last updated: Aug 25, 2026

What it does

  • Confirms the design contract (ports, clock/reset, pipeline, interface family, verification cases), then produces a Python semantic model before emitting synthesizable Verilog-2001 .v files.
  • Runs a formatter-backed quality gate with an eight-item matrix — compile / ast / readability / comment / naming / profile / testbench / toolchain — and publishes JSON + Markdown reports with VG rule IDs, locations and ordered repair steps.
  • Handles existing RTL: structural analysis, semantic equivalence comparison, log-driven diagnosis and minimal evidence-backed patches (conservative, semi_auto, auto_apply).
  • Emits a companion <module>_spec.md plus WaveDrom timing diagrams (JSON5 + SVG) for every module.
  • Prefers real external evidence (Vivado xsim, VCS+Verdi, iverilog) and explicitly forbids claiming an unrun check passed.

Who it's for

  • FPGA/ASIC digital design engineers who want consistent, reviewable RTL style.
  • Teams inheriting legacy Verilog that needs structural analysis and semantic comments.
  • Groups enforcing three-process FSMs, AXI-Stream/AXI4-Lite/AHB/APB templates and naming conventions.

Examples

  1. "Write a 4-stage pipelined FIR module with an AXI-Stream interface" → requirements → codegen plan → spec document → RTL plus timing diagrams.
  2. Hand it an existing uart_rx.v and ask for semantic comments only → the comment-only workflow proves token equivalence against an immutable normalized baseline.
  3. Run python -m scripts.python.validation.generated_deliverable_gate rtl/ --json report.json --markdown report.md before hand-off to see every violation and its fix order.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Eriemon/verilog-generator/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the SKILL.m folder from the GitHub repo Eriemon/verilog-generator into my ~/.claude/skills/readable-verilog-generator/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Eriemon/verilog-generator.git ~/.claude/skills/readable-verilog-generator

This is a third-party skill. Check the source repository before installing.

  1. Verify Python 3 and Git are installed (python --version, git --version).
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Clone the repo: git clone https://github.com/Eriemon/verilog-generator.git ~/.claude/skills/readable-verilog-generator
  4. Inspect the installers at the package root (install.sh, install.ps1, install.bat) and try a safe ./install.sh --dry-run first.
  5. For waveform SVG rendering, install Node.js/npm and run python -m scripts.python.toolchain.wavedrom_runtime check.
  6. For remote simulation or synthesis evidence, also install the erie-remote-ssh skill and configure .settings/verilog.remote.json in your remote workdir.
  7. Restart Claude Code and ask something like "generate a Verilog module for ..." to trigger the skill.
View source on GitHubLicense: Apache-2.0