chip-impl-rtl-coding

chip-impl-rtl-coding is a skill for Claude Code from zhaixin244-wq/fnw. It costs 72 tokens per session (1,775 once invoked), scanned A, original, MIT.

A workflow for writing RTL, the hardware description code used to build chip circuits, for individual chip submodules. It covers data paths, control logic, reusable building blocks, and module connections based on a fixed architecture.

In plain words
What is it for?
Use it to implement data processing paths, control state machines, reusable circuit blocks, and interfaces in Verilog files. It is intended for chip submodule development after the architecture has been finalized.
Why use it?
It turns an approved microarchitecture and port list into organized submodule code while keeping implementation aligned with the design plan. It also provides standard patterns for resets, state machines, and valid/ready handshakes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to implement data processing paths, control state machines, reusable circuit blocks, and interfaces in Verilog files. It is intended for chip submodule development after the architecture has been finalized.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhaixin244-wq/fnw/chip-impl-rtl-coding
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zhaixin244-wq/fnw --skill chip-impl-rtl-coding
Clone the repo
git clone --depth 1 https://github.com/zhaixin244-wq/fnw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for chip-impl-rtl-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding/github.svg)](https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding)
Your own site
<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chip-impl-rtl-coding

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-rtl-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01775
Opus 5 $0.00036 $0.00888
Sonnet 5 $0.00014 $0.00355
Haiku 4.5 $0.00007 $0.00178

Measured 9d ago against content hash 864638157c8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chip-impl-rtl-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/chip-impl-rtl-coding/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTL 代码实现 Skill

任务

逐子模块实现 RTL 代码:数据通路 → 控制逻辑/FSM → CBB 集成 → 接口逻辑。

输入

  • microarch_doc: 微架构文档
  • port_list: 端口列表(来自 module_structure)
  • submodule_list: 子模块列表
  • cbb_docs: CBB 文档
  • coding_style: 编码规范

执行步骤(每个子模块)

  1. 数据通路:从微架构 §5.1 逐阶段编码
  2. 控制逻辑 + FSM:从微架构 §5.3 两段式状态机
  3. CBB 集成:从 RAG 检索结果实例化,标注 // CBB Ref
  4. 接口逻辑:valid/ready 握手、背压、异常处理
  5. 保存到 {module}_work/ds/rtl/{submodule}.v

模板化 always 块骨架

编码时直接复用以下模板,减少 LLM 推理开销,提升代码一致性。{...} 为占位符。

复位模板(异步复位同步释放)

// Ref: Arch-Sec-{X.Y} — {信号功能描述}
always @(posedge clk or negedge rst_n) begin
    if (!rst_n) begin
        {signal}_r <= {reset_value};
    end else begin
        {signal}_r <= {signal}_nxt;
    end
end

FSM 两段式模板

// FSM 段1:时序逻辑存状态
// Ref: Arch-Sec-{X.Y} — {状态机功能描述}
always @(posedge clk or negedge rst_n) begin
    if (!rst_n) state_cur <= S_IDLE;
    else state_cur <= state_nxt;
end

// FSM 段2:组合逻辑算次态
always @(*) begin
    state_nxt = S_IDLE;  // 默认值(防 latch)
    case (state_cur)
        S_IDLE: if ({condition}) state_nxt = S_WORK;
        S_WORK: state_nxt = {done} ? S_IDLE : S_WORK;
        default: state_nxt = S_IDLE;  // 非法状态回收
    endcase
end

握手模板(Valid-Ready)

// Valid-Ready 握手模板
// Ref: Arch-Sec-{X.Y} — {接口功能描述}
always @(posedge clk or negedge rst_n) begin
    if (!rst_n) valid_r <= 1'b0;
    else if (valid_r && ready) valid_r <= next_valid;  // 握手后更新
    else if (!valid_r) valid_r <= next_valid;           // 无数据时可更新
end

assign ready = !downstream_backpressure;  // ready 仅依赖下游

组合逻辑模板(防 latch)

always @(*) begin
    // 默认值(必须)
    {output1} = {default1};
    {output2} = {default2};
    case ({selector})
        {VAL_A}: begin
            {output1} = {value_a1};
            {output2} = {value_a2};
        end
        {VAL_B}: begin
            {output1} = {value_b1};
        end
        default: ;  // case default(必须)
    endcase
end

架构冻结铁律

ABSOLUTELY NO ARCHITECTURE MODIFICATION IN RTL
  • 严格按微架构文档实现
  • 疑问暂停标记 [ARCH-QUESTION]
  • 仅文档明显笔误时允许偏差,标注 [ARCH-DEVIATION]
  • 代码标注架构章节号:// Ref: Arch-Sec-4.2.1

Read the full file on GitHub · 158 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 158 lines · 72 tokens per session scan A 864638157c8f

Subscribe to this mod's changes

chip-impl-rtl-coding is a skill published in the GitHub repository zhaixin244-wq/fnw (28 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,775 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cardputer-buddy

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…

anthropics/claude-plugins-official · 109 tokens

doca-argp

Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…

NVIDIA/skills · 267 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

zener-language

Read or edit Zener HDL, package APIs, and tool-managed dependencies.

diodeinc/pcb · 19 tokens

embedded-stm32

Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…

Mindrally/skills · 87 tokens

003-skills-inventory

Use when you need to generate a checklist document with Java system prompts from skills.xml, following the embedded section template and producing INVENTORY-SKILLS-JAVA.md. This should trigger for requests such as Create Java system prompts checklist; Generate INVENTORY-SKILLS-JAVA.md; Use @003-skills-inventory…

jabrena/plinth · 88 tokens