npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@gary-coding/speclane

v0.1.0

Published

SpecLane workflow skill and CLI for demand-driven AI delivery with OpenSpec bridge support.

Readme

speclane

结构化 AI 工程交付工作流

它是什么

speclane 是一个面向 AI 编码的工程交付工作流 skill。它把一次需求交付拆成规格、计划、实现、自查、审查、验证和归档,让 AI 不再零散写代码,而是按可追踪、可验证、可复盘的流程工作。

它支持两种入口:

  • todo 模式:直接用 todo.md 驱动交付,适合轻量需求。
  • openspec 模式:先生成 OpenSpec change,再桥接成 todo.md,适合正式需求迭代。

适合谁

  • 使用 Claude Code、Codex 等 AI 编码工具的开发者。
  • 需要在存量系统、多仓库、微服务项目上持续迭代的团队。
  • 希望 AI 编码过程有计划、审查、验证、通知和归档记录的团队。
  • 已经使用或准备使用 OpenSpec 沉淀需求规格的团队。

三步开始

npm install -g @gary-coding/speclane@latest
speclane init
speclane sync --target both

然后在 AI 中发送工作流命令。

OpenSpec 模式:

/sl:propose add-phone-filter
/sl:bridge
# 人工审核 todo.md 后
/sl:apply

todo 模式:

/sl:apply

多需求工作区:

/sl:demand new demand-a
/sl:propose add-phone-filter --demand demand-a
/sl:bridge --demand demand-a
/sl:apply --demand demand-a

更多命令见 docs/sl命令协议.md

一个最小示例

需求:给用户列表增加手机号精确筛选。

  1. 初始化工作区:
speclane init
  1. 把需求写入初始化生成的需求文件,或维护好 todo.md

  2. 使用 OpenSpec 模式时,在 AI 中输入:

/sl:propose add-user-phone-filter

生成规格后继续:

/sl:bridge

审核 todo.md 后:

/sl:apply

AI 会按当前工作区配置推进计划、实现、自查、审查、验证,并在 OpenSpec 模式下回写执行摘要和归档检查结果。

工作空间配置

每个业务工作空间都需要有 workspace.yml

最小 todo 模式示例:

version: 1
mode: manual
workflow_source: todo
todo_file: todo.md
reference_files: []
code_path: ../../../code
output_dir: output

如果自动识别出的验证命令不适合当前项目,可以在 workspace.yml 中覆盖:

verify_commands:
  default: pnpm test && pnpm build
  frontend-app: pnpm test && pnpm build
  user-service: go test ./...

最小 openspec 模式示例:

version: 1
mode: manual
workflow_source: openspec
vars:
  demand_name: add-phone-filter
demand_file: demands/${demand_name}/需求.md
todo_file: demands/${demand_name}/todo.md
reference_files: []
code_path: ../../../code
output_dir: demands/${demand_name}/output
openspec:
  changes_dir: ../openspec/changes

demand_file 可以是本地 Markdown,也可以是飞书/Lark 云文档 URL。使用云文档时需要先安装并授权官方 CLI:

npx @larksuite/cli@latest install
lark-cli config init --new
lark-cli auth login --recommend

如果同一个工作空间经常切换需求,可以用 vars 避免重复修改路径:

version: 1
mode: auto
workflow_source: openspec
vars:
  demand_name: 7-deamnd-addition-rate
demand_file: demands/${demand_name}/需求.md
todo_file: demands/${demand_name}/todo.md
reference_files:
  - ../docs/需求分析与实现指南.md
code_path: ../../../code
output_dir: demands/${demand_name}/output
openspec:
  changes_dir: ../openspec/changes

OpenSpec change 名称不从 demand_name 推导。请在 /sl:propose <change-name> 后显式指定,例如 /sl:propose demand-addition-rate。后续 /sl:bridge/sl:apply 会使用 propose 阶段记录的当前 change。

skill 自身配置位于:

~/.speclane/skill-config.yml

如果该文件不存在,首次初始化时会自动生成默认配置并暂停流程,等待补全。

运行时产物

给机器读取的会话产物:

<workspace>/.speclane/current-session.json
<workspace>/.speclane/sessions/<session_id>/discovery.json
<workspace>/.speclane/sessions/<session_id>/plan.json
<workspace>/.speclane/sessions/<session_id>/self-check.json
<workspace>/.speclane/sessions/<session_id>/review.json
<workspace>/.speclane/sessions/<session_id>/verify.json
<workspace>/.speclane/sessions/<session_id>/status.json

多需求模式下,状态会隔离到:

<workspace>/.speclane/demands/<demand_name>/current-session.json
<workspace>/.speclane/demands/<demand_name>/sl-state.json
<workspace>/.speclane/demands/<demand_name>/todo-state.json
<workspace>/.speclane/demands/<demand_name>/sessions/<session_id>/

给人查看的报告:

<output_dir>/<session_id>/discovery.md
<output_dir>/<session_id>/plan.md
<output_dir>/<session_id>/self-check.md
<output_dir>/<session_id>/review.md
<output_dir>/<session_id>/verify.md

OpenSpec 模式额外产物:

<workspace>/.speclane/openspec-bridge-context.json
<change_dir>/speclane/execution-summary.json
<change_dir>/speclane/archive-input.json
<change_dir>/speclane/archive-result.json

文档入口

许可证

本项目使用 MIT License