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

digital-employee-skill

v0.1.1

Published

Self-contained, local-first digital employee skill: collect evidence, AI-organize the employee profile, and bundle one portable harness ZIP.

Readme

digital-employee-skill

自包含的本地数字员工 SKILL:代码负责采集和建立证据索引,AI 负责二次整理,最终只产出一个 数字员工XXX.zip。

最终产物

数字员工示例.zip
  manifest.json
  codex-home/
  claude-home/

ZIP 是完整 harness 环境,包含身份、岗位职责、权限边界、长期/近期/短期记忆、项目进度、agents、skills、AGENTS.md 和 CLAUDE.md。

不再把 versions/、packages/、单独实例目录或技能包作为最终交付物提供。

工作流

digital-employee scan --home $HOME --output .digital-employee
digital-employee collect-skills --home $HOME --output .digital-employee
digital-employee prepare --output .digital-employee
digital-employee distill --output .digital-employee

# AI 读取证据,确认岗位卡,按固定格式二次整理员工文档;从经历中提炼可迁移能力,并判断是否有成熟方法值得封装成专属技能。
digital-employee save-card --input .\employee-card.json --output .digital-employee

# AI 创建 build\<employee_id>\ 暂存目录并写最终文档。
digital-employee validate --instance .\build\example-employee
digital-employee bundle --instance .\build\example-employee --to .\数字员工示例.zip

严格的 ZIP、员工偏好、核心能力说明、employee/memory/、employee/projects/ 和员工专属技能格式见 harness package。

AI 的必选工作

  • 判断项目是否与工作相关,无法判断时询问用户;
  • 把工作内容整理成长期、近期、短期;
  • 将偏好、决定和原有 Agent 规则按项目上下文整理,再把员工级内容归纳成不带项目名称的通用规则;
  • 从实际做法和结果中整理可迁移能力,明确方法、交付和自检方式;
  • 评估是否存在步骤完整、证据充分、值得复用的经历,并将其整理为 Codex 与 Claude 共用的员工专属技能;
  • 每个项目单独写目标、我负责的部分、长期脉络、近期进展、当前短期状态和项目进度;
  • 把原有长期协作规则压缩到入口文件的“员工偏好”,同时保留来源规则以供按需读取;
  • 员工级能力、偏好和通用记忆不直接列项目名称或项目专属决定;
  • 删除非工作项目、过程说明、证据编号和候选标记;
  • 最终文档不能有空白、待定、提问句或“说明性”文字;
  • 信息不足时先问用户,确认后再打包。

代码只负责采集、去重、整理、索引、技能收集、结构校验、凭据扫描和 ZIP 打包。

工程结构

scripts/
  python/
    main.py
    digital_employee/
  pwsh/
    run.ps1

Python 入口固定为 scripts/python/main.py;PowerShell 入口固定为 scripts/pwsh/run.ps1。两种运行时不再混在同一层。

桌面软件

桌面软件只做:

  1. 导入 数字员工XXX.zip;
  2. 读取 manifest.json;
  3. 保存当前 harness 配置为“原始配置”;
  4. 用 ZIP 中对应 harness 覆盖当前配置;
  5. 记录当前激活实例。

软件不生成员工、不调用 AI、不运行扫描、不编辑岗位卡,也不启动 Codex 或 Claude。切换后由用户自行运行 codex 或 claude。

开发验证

npm test
npm run test:python
npm pack

validate 会阻止空章节、待定词、提问句、凭据文件和凭据内容进入最终 ZIP。

npm 发布

仓库使用 GitHub Actions 发布 npm 包。发布前在 GitHub 仓库的 Settings > Secrets and variables > Actions 中创建 NPM_TOKEN。首次发布新包时使用允许发布新包的 npm Automation token;后续可以使用具有该包发布权限的 token。

首次发布当前版本:

git tag v0.1.0
git push origin v0.1.0

后续升级发布:

npm version patch -m "release: v%s"
git push origin master --follow-tags

推送 v* 标签后,.github/workflows/publish.yml 会执行以下操作:

  1. 校验标签版本与 package.json 版本一致;
  2. 执行 Node 和 Python 测试;
  3. 使用 NPM_TOKEN 发布到 npm;
  4. 通过 npm provenance 生成来源证明。