Agent skill

X Npi

by BLANK2077 in BLANK2077/xverif

当 AI agent 需要使用 Synopsys pynpi 编写 Python 脚本,进行批量 FSDB 波形统计、值扫描、APB/AXI/valid-ready stream 协议分析、VCS/Verdi coverage database 查询,或静态设计 driver/load 查询时使用。离线大规模分析脚本和报告优先使用本 skill;xdebug 风格的实时…

MITAuto-check passed

Install X Npi

skills CLI
$ npx skills add BLANK2077/xverif --skill x-npi -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BLANK2077/xverif x-npi --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BLANK2077/xverif.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/x-npi .claude/skills/x-npi && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
x-npi
GitHub stars
108
Token cost
~1.4k tokens
SKILL.md length
377 words
Files
26 (incl. scripts, references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

当 AI agent 需要使用 Synopsys pynpi 编写 Python 脚本,进行批量 FSDB 波形统计、值扫描、APB/AXI/valid-ready stream 协议分析、VCS/Verdi coverage database 查询,或静态设计 driver/load 查询时使用。离线大规模分析脚本和报告优先使用本 skill;xdebug 风格的实时…

  • SKILL.md covers 任务路由, 可复用 helper, 决策规则 and 示例入口
  • Runs Python scripts from its folder

What it does

X Npi is an agent skill from BLANK2077/xverif. 当 AI agent 需要使用 Synopsys pynpi 编写 Python 脚本,进行批量 FSDB 波形统计、值扫描、APB/AXI/valid-ready stream 协议分析、VCS/Verdi coverage database 查询,或静态设计 driver/load 查询时使用。离线大规模分析脚本和报告优先使用本 skill;xdebug 风格的实时 active-driver 根因定位或 PVC active-driver 检查不要使用本 skill。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/coverage-patterns.md` and `references/design-trace-patterns.md`).

It works with Python. The repository describes itself as: xverif is a local toolkit for chip-verification debug agents. It contains deterministic tools for design and waveform debug, coverage, bit calculations, structured entry…. The licence is MIT.

Example prompts

  • “/x-npi”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 25bb715. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

X Npi loads about 1.4k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 377 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from BLANK2077/xverif at commit 25bb715, republished under its MIT licence (© BLANK2077). 377 words, ~1,374 tokens.

Download SKILL.mdSave it as .claude/skills/x-npi/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
x-npi
description
当 AI agent 需要使用 Synopsys pynpi 编写 Python 脚本,进行批量 FSDB 波形统计、值扫描、APB/AXI/valid-ready stream 协议分析、VCS/Verdi coverage database 查询,或静态设计 driver/load 查询时使用。离线大规模分析脚本和报告优先使用本 skill;xdebug 风格的实时 active-driver 根因定位或 PVC active-driver 检查不要使用本 skill。

x-npi

**License 环境优先规则:**如果当前 EDA/NPI 环境存在 license 约束,优先尝试使用 bsub 提交到 LSF 队列运行。提交失败必须明确报告,不得静默回退到本机执行。

x-npi 用来教 AI agent 编写可复用的 Python pynpi 批量分析脚本。交互式会话查询和 active-driver 因果追踪继续使用 xdebug;当任务需要扫描大量信号、时间窗口、事务、coverage database 或设计 handle 时,使用 x-npi。

任务路由

任务优先阅读
配置 VERDI_HOME、导入 pynpi、管理 npisys.init/endreferences/pynpi-runtime.md
读取 FSDB 值、变化、统计信息或时钟沿采样references/waveform-patterns.md
提取 APB、AXI 或 valid-ready stream 摘要references/protocol-patterns.md
导出 VCS/Verdi coverage summary、coverage detail 或管理原生 exclusionreferences/coverage-patterns.md
从 daidir/design DB 查询静态 driver/load 事实references/design-trace-patterns.md

可复用 helper

可 import 的 helper 包位于 scripts/x_npi/。

python
from x_npi.runtime import json_stdout_quarantine, pynpi_lifecycle
from x_npi.wave import open_fsdb, iter_edge_samples
from x_npi.protocol import axi_summary
from x_npi.urg import export_summary, parse_summary
from x_npi.coverage import load_exclusion_files, open_covdb, compile_csv_to_el
from x_npi.container import plan_container_records, write_csv_set

公共 helper 按模块分组:

  • runtime:verdi_home、configure_pynpi、json_stdout_quarantine、pynpi_lifecycle。
  • wave:open_fsdb、close_fsdb、time_in、preflight_signals、sample_values、iter_signal_changes、iter_edge_samples、clock_edges、edge_samples、value_statistics。
  • protocol:apb_transactions、apb_summary、axi_transactions、axi_summary、stream_summary。
  • urg:urg_path、export_summary、parse_summary;coverage read/export 的默认且推荐入口, 固定 -full64 -xml_verbose -format text -show summary,不加载 pynpi。
  • coverage:只负责 exclusion 的 open_covdb、close_covdb、test_names、 merged_test_handle、load_exclusion_files、set_report_time_excluded、 save_exclusion_file、unload_exclusions、compile_csv_to_el。不再提供 NPI coverage read。
  • exclusion_csv:parse_document、parse_directory、validate_directory、 format_document、format_directory;reason 只保存在 CSV sidecar。
  • design:handle_name、statement_row、trace_driver、trace_load。
  • jsonio:ok、error、print_json、split_limited。

运行示例时,可以把 skill 的 scripts 目录加入 PYTHONPATH,也可以直接执行 scripts/examples/ 下的文件。

决策规则

  • 针对已经打开的 xdebug 会话做一次性 AI debug 时,使用 xdebug。
  • 需要批量 FSDB 扫描、事务提取、coverage export、值分布统计或报告生成时,使用本 skill 编写 Python 脚本。coverage 读取优先 URG;不要把 x-npi 的名字误解为所有 coverage 工作都必须走 pynpi。
  • 不确定 pynpi API、类名、枚举或调用约定时,AI 可以直接查看 $VERDI_HOME/share/NPI/python/pynpi/ 下当前安装版本的 Python 包和实现;例如 waveform 的时间归并遍历可查 pynpi/waveform.py 中的 TimeBasedHandle。先核对当前安装 API,再写脚本,不凭记忆猜接口。这是正式 API 查证入口,不是失败后的 fallback。
  • 做波形协议分析、事务统计、窗口验证或跨信号相关性判断时,必须基于同一个 clock 的 edge 采样。公开配置只接受 edge=negedge|posedge;posedge 还必须显式指定 sample_point=before|after,negedge 禁止 sample_point。默认使用 negedge。
  • 大窗口优先使用流式 iter_edge_samples,让 Python 状态机边读边聚合;只有确实需要完整采样行时才使用会物化列表的 edge_samples。
  • AI 可直接用 Python 对结构化结果做过滤、分组、关联、统计、临时索引或任务内缓存,具有很高的自定义自由度。优先一次扫描生成任务需要的聚合,不默认建设持久化缓存数据库,也不为通用示例增加固定业务过滤器。
  • 需要 active-driver、active-driver-chain、activeTime、PVC active check、force/root-cause 分类,或在某个症状时间点做接口因果追踪时,改用 xdebug/C++ NPI。当前 Python pynpi 不暴露这些 active trace 所需 API。
  • Python NPI coverage API 没有 bulk summary,必须从 instance/metric/object/bin 逐层遍历;设计越大, 启动和遍历成本越高,而且容易把 parent aggregate 与 child bin 重复计分。普通 summary、层次、 test list、code/assert/functional typed 统计和 detail export 一律优先 URG;NPI 在 coverage 部分只用于 exclusion target 的必要遍历以及 EL load/set/save/unload。
  • compile_csv_to_el(db, test, csv_dir, output_dir) 内建 indexed resolver:code/assertion 对 CSV 中 唯一 exact scope 使用 handle_by_name,不遍历 instance hierarchy;functional 预检按请求的 group/point/cross 前缀剪枝,apply 用短生命周期 locator trie 重放,不做第二次全树扫描。零/多匹配 和两遍间身份变化均失败并回滚;不缓存 native handle、不建立全 bin 索引、不接受外接 resolver。
  • container_exclude.py 是 x-npi 独立容器入口:从既有 fixed URG report 解析,或使用固定 full64 URG 命令新生成 report;递归 instance 只展开 XML 真实节点,然后生成 exact container CSV 并原子 发布四份 EL。NPI 在该流程只用于排除定位和 EL 操作。
  • URG summary 百分比使用其 typed subtree ratio;root scope 从 XML 的 instance parent 关系推导, 不假设名称为 top。单 metric pct 为 covered/coverable;多 root 时先按 metric 合并 root 分子/分母,多 metric root/scope SCORE 再对可评分的非 null metric pct 做算术平均。无 coverable object 的 0/0 保留 null 且不参与平均;全部不可评分时 SCORE 为 null。 count 不是 coverage pct。
  • 不支持从固定 summary 伪造 per-test attribution、source evidence 或 functional bin;需要 gap 时使用受限 URG text detail,不回退 NPI 全树扫描。
  • 脚本 stdout 必须只有一个 JSON document。使用 json_stdout_quarantine 隔离 NPI native banner;summary 默认输出到 stdout,transactions|timeline|full 必须配合 --output 写文件,stdout 只返回摘要和文件位置。协议工具不提供 line_limit。
  • 时间字段保持 FSDB integer tick,并在 meta.scale_unit 返回数据库 time scale;不要先转换成 float 时间再做配对或排序。
  • 当环境需要 Synopsys license 访问时,真实 pynpi/FSDB/daidir 验证应在受限沙箱外运行。
Show full SKILL.md (9 more words)Show less

示例入口

  • scripts/examples/wave_stats.py
  • scripts/examples/apb_summary.py
  • scripts/examples/axi_summary.py
  • scripts/examples/stream_summary.py
  • scripts/examples/coverage_summary.py
  • scripts/examples/csv_to_el.py
  • scripts/examples/container_exclude.py
  • scripts/examples/trace_driver_summary.py

© BLANK2077, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references) in skills/x-npi of BLANK2077/xverif.

  • SKILL.md
  • agents/openai.yaml
  • references/coverage-patterns.md
  • references/design-trace-patterns.md
  • references/protocol-patterns.md
  • references/pynpi-runtime.md
  • references/waveform-patterns.md
  • scripts/examples/apb_summary.py
  • scripts/examples/axi_summary.py
  • scripts/examples/container_exclude.py
  • scripts/examples/coverage_summary.py
  • scripts/examples/csv_to_el.py
  • scripts/examples/stream_summary.py
  • scripts/examples/trace_driver_summary.py
  • scripts/examples/wave_stats.py
  • scripts/x_npi/__init__.py
  • … and 10 more

Open the folder on GitHubat commit 25bb715

Compare with similar skills

X Npi next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

X Npi compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
X Npi this skillBLANK2077/xverif108—~1.4kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k47 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use29k6 repos~3kAutomated safety check: PassMIT
PPT Masterhugohe3/ppt-master59k1 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 47 repos~2k tokens
    Documents & OfficeAuto-check passed
  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    29k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    59k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Scikit Learn

    zLanqing/codex-claude-academic-skills

    Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 16 repos~3.9k tokens
    Data & AnalyticsAuto-check passed

More from BLANK2077/xverif

  • Xsimdebug

    BLANK2077/xverif

    当 AI agent 需要定位 SystemVerilog/UVM 验证问题、重新编译代价过高或不允许再次编译,并需要直接通过终端 PTY 使用 Synopsys VCS UCLI 或 Cadence Xcelium/Xrun Tcl 实时调试正在运行的仿真时使用,包括断点、Ctrl-C 暂停、运行时变量查询和控制流。若已有仿真 log 已足以定位问题,则不使用本 skill。

    108 GitHub stars~590 tokensUpdated yesterday
    Auto-check passed
  • Xwiki

    BLANK2077/xverif

    当 AI agent 需要在芯片验证任务中复用持续记忆时使用:查询或维护由 XWIKIDIR 指向的验证项目 LLM wiki,了解验证环境、DUT 功能、 接口、testbench、sequence、checker、coverage、workflow、debug 入口、 BT/IT/ST/SoC 项目上下文,并在用户明确要求、项目 AGENTS.md 授权或任务明确…

    108 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Xverif

    BLANK2077/xverif

    用于芯片验证中的确定性事实查询和计算:daidir/FSDB debug、coverage、 SystemVerilog bit 计算、entry 解码、日志位置恢复、SVA 解释和波形渲染。

    108 GitHub stars~931 tokensUpdated yesterday
    Auto-check passed
  • Xverif Admin

    BLANK2077/xverif

    用于 xverif 的安装配置、MCP direct/LSF backend、ssh 远端 MCP(mcpssh)、 SDK-free LSF CLI、UDS/TCP/file transport、session tombstone/gc、timeout、 环境变量、license 和 server 启动排障。普通波形、coverage、bit 或协议查询使用 xverif。

    108 GitHub stars~428 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about X Npi

What does X Npi do?

当 AI agent 需要使用 Synopsys pynpi 编写 Python 脚本,进行批量 FSDB 波形统计、值扫描、APB/AXI/valid-ready stream 协议分析、VCS/Verdi coverage database 查询,或静态设计 driver/load 查询时使用。离线大规模分析脚本和报告优先使用本 skill;xdebug 风格的实时…. X Npi is an agent skill from BLANK2077/xverif.

How do I install X Npi in Claude Code?

Run `npx skills add BLANK2077/xverif --skill x-npi -a claude-code`. Or copy the skill folder (skills/x-npi in BLANK2077/xverif) into .claude/skills/x-npi in your project. Claude Code loads it when a task matches its description.

How do I install X Npi in Codex?

Run `npx skills add BLANK2077/xverif --skill x-npi -a codex`. Or copy the skill folder (skills/x-npi in BLANK2077/xverif) into .agents/skills/x-npi in your project. Codex loads it when a task matches its description.

Can I use X Npi in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BLANK2077/xverif --skill x-npi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/x-npi, .gemini/skills/x-npi, .github/skills/x-npi and .opencode/skills/x-npi in your project.

What does X Npi need to run?

Going by SKILL.md and its folder, X Npi needs Python for the scripts in its folder. Our summary lists: Python 3.

Does X Npi access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is X Npi safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does X Npi use?

X Npi is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does X Npi use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.

What are the alternatives to X Npi?

Skills that share tags, products or a category with X Npi: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains X Npi?

BLANK2077 (a GitHub user) maintains it in BLANK2077/xverif, which has 108 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 2026.

Source: BLANK2077/xverif on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.