chip-impl-sdc-sva

chip-impl-sdc-sva is a skill for Claude Code from zhaixin244-wq/fnw. It costs 78 tokens per session (1,148 once invoked), scanned A, original, MIT.

A guide for generating timing constraints, hardware assertions, and a testbench for RTL designs. SDC files describe timing requirements, SVA assertions express expected behavior, and a testbench drives and checks the design.

In plain words
What is it for?
Use it to generate clock and I/O timing constraints, handshake and data-stability assertions, a clock-and-reset testbench, and scripts for linting and Yosys synthesis.
Why use it?
It turns the design’s microarchitecture and verification requirements into files that tools can use to check timing and behavior. It also creates supporting file lists and run scripts.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to generate clock and I/O timing constraints, handshake and data-stability assertions, a clock-and-reset testbench, and scripts for linting and Yosys synthesis.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva/github.svg)](https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva)
Your own site
<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva/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-sdc-sva

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-impl-sdc-sva.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,148 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 $0.00078 $0.01148
Opus 5 $0.00039 $0.00574
Sonnet 5 $0.00016 $0.00230
Haiku 4.5 $0.00008 $0.00115

Measured 11d ago against content hash 6f5adc0e6e57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

chip-impl-sdc-sva 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 11d 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-sdc-sva/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDC/SVA/TB 编写 Skill

任务

基于微架构时钟策略和验证要点生成 SDC 约束、SVA 断言、TB testbench。

输入

  • rtl_files: RTL 文件列表
  • microarch_doc: 微架构文档
  • port_list: 端口列表

执行步骤

  1. Glob 搜索 {module}_work/ds/doc/ua/*.md 获取微架构文档列表。若文件不存在,暂停并提示用户

SDC 约束

  1. 从微架构 §6 提取时钟定义(频率/来源)
  2. 生成 create_clock / set_input_delay / set_output_delay
  3. 设置 set_false_path(复位信号)
  4. 保存到 {module}_work/run/{module}.sdc

SVA 断言

  1. 从微架构 §10 提取验证场景
  2. 实现握手稳定性:valid && !ready |=> valid
  3. 实现数据稳定性:valid && !ready |=> $stable(data)
  4. 实现非法状态检测
  5. 所有 SVA 放在 `ifdef ASSERT_ON
  6. 保存到 {module}_work/ds/rtl/{submodule}_sva.sv

TB testbench

  1. 生成基本 testbench 框架
  2. 时钟/复位生成
  3. 实例化 DUT
  4. 保存到 {module}_work/ds/rtl/{submodule}_tb.v

Run 脚本

  1. 生成文件列表 {module}_work/run/{module}.f
  2. 生成 Lint 脚本 {module}_work/run/lint.sh
  3. 生成综合脚本 {module}_work/run/synth_yosys.tcl

输出

  • sdc_file: {module}_work/run/{module}.sdc
  • sva_file: {module}_work/ds/rtl/{submodule}_sva.sv
  • tb_file: {module}_work/ds/rtl/{submodule}_tb.v
  • filelist: {module}_work/run/{module}.f
  • lint_script: {module}_work/run/lint.sh
  • synth_script: {module}_work/run/synth_yosys.tcl

Gate

无强制门禁,但 SDC 时钟周期必须与微架构 §6 一致。

Metrics

执行完成后记录到 {work_dir}/ds/report/metrics/sdc_sva.json

{"stage_id": "sdc_sva", "duration_ms": 0, "iteration_count": 1}

使用示例

示例 1

  • 用户:「为 data_adpt 生成 SDC 约束和 SVA 断言」
  • 行为:从微架构 §6 提取时钟定义生成 create_clock/set_input_delay/set_output_delay,从 §10 提取验证场景生成握手/数据稳定性断言,保存到对应目录

示例 2

  • 用户:「帮我写 buf_mgr 的 testbench 框架」
  • 行为:生成基本 TB 框架(时钟/复位生成 + DUT 实例化 + 文件列表),保存到 buf_mgr_work/ds/rtl/buf_mgr_tb.v,同步生成 run/lint.shrun/synth_yosys.tcl

异常处理

场景 触发条件 处理动作
微架构时钟定义缺失 §6 无时钟频率/来源 暂停,提示用户补充时钟策略
验证场景缺失 §10 无验证要点 仅生成基础握手断言,标注 [SVA-PARTIAL]
SDC 时钟周期不一致 生成的 SDC 与微架构 §6 矛盾 以微架构为准,修正 SDC
RTL 文件未就绪 rtl_files 列表为空 暂停,提示先完成 RTL 实现

检查点

检查前

  • 确认 RTL 文件列表非空
  • 确认微架构文档包含 §6(时钟复位)和 §10(验证要点)

Read the full file on GitHub · 92 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. 11d ago First seen · 92 lines · 78 tokens per session scan A 6f5adc0e6e57

Subscribe to this mod's changes

chip-impl-sdc-sva is a skill published in the GitHub repository zhaixin244-wq/fnw (29 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,148 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.