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

foundry-product-thinking-toolkit

v0.1.0

Published

Foundry local-first skill project that turns product ideas into Product Dossier and related deliverables.

Downloads

164

Readme

Foundry Product Thinking Toolkit

English | 简体中文

Foundry 是一个面向 Codex、Claude Code、OpenCode 以及其他 coding agents 的 local-first skill project。它把一个需求或粗略产品想法推进成结构化产品交付包:Product Dossier、PRD、pitch outline、prototype、design brief、research appendix 和 artifact manifest。

它不是 Web app、SaaS 产品,也不是给每个 agent 做一套独立实现。它是一套共享 Foundry skill core,通过不同安装目标暴露给不同 agent 的发现路径。

安装

默认安装:

npx foundry-product-thinking-toolkit install

默认目标是 .agents/skills/,Codex 和 OpenCode 都可以读取这个路径。它会安装 foundry-product-thinking-toolkit/,以及同级的 foundry-* 阶段和支持 skill 入口。

可选目标:

npx foundry-product-thinking-toolkit install --target agents,claude-code
npx foundry-product-thinking-toolkit install --target opencode
npx foundry-product-thinking-toolkit install --target all

安装到当前仓库:

npx foundry-product-thinking-toolkit install --scope repo

预览安装计划:

npx foundry-product-thinking-toolkit install --dry-run

产出内容

  • Product Dossier
  • PRD Markdown artifact
  • pitch outline
  • HTML/SVG 或 prompt 形式的 prototype artifact
  • Basic Product Identity Kit
  • Design Brief
  • Research Appendix
  • artifact-manifest.md

工作方式

工具包由一个 root Foundry orchestrator skill 和多个可直接调用的 Foundry stage skills 组成。

从头开始或需要 Foundry 判断下一阶段时,使用根目录 SKILL.md。源码中阶段 skill 位于 skills/;安装后它们会成为同级 foundry-* skill 入口,可用于聚焦 idea intake、problem framing、market discovery、product definition、MVP scope、identity、screen-level shape、artifact generation 和 dossier review。

产品状态保存在本地 product-memory/ 中。Markdown 文件是事实来源,state.json 只保存轻量 runtime 状态。

运行可以使用 lightstandarddeep 推进模式。弱发现阶段可以在 light 模式下快速通过,把未解决的不确定性记录到 questions.md;除非用户要求更深工作,否则不应默认变成完整调研项目。

阶段流程

  1. Idea Intake
  2. Problem Framing
  3. User Discovery
  4. Market Discovery
  5. Competitive Scan
  6. Concept Lock
  7. Product Definition
  8. Target Product Shape
  9. MVP Scope
  10. Basic Product Identity
  11. Screen-Level Product Shape
  12. Artifact Generation
  13. Dossier Review

Concept Lockfoundry-concept-lock 处理。它是从 weak discovery gates 进入 strong delivery gates 的切换点,必须获得显式用户确认。fixture confirmation 只允许用于 examples、smoke tests 或显式 fixtureMode

直接调用的 Skill 入口

完整流程使用 foundry-product-thinking-toolkit。聚焦某个阶段时,直接使用对应阶段 skill:

| Stage | Skill | | --- | --- | | Idea Intake | foundry-idea-intake | | Problem Framing | foundry-problem-framing | | User Discovery | foundry-user-discovery | | Market Discovery | foundry-market-discovery | | Competitive Scan | foundry-competitive-scan | | Concept Lock | foundry-concept-lock | | Product Definition | foundry-product-definition | | Target Product Shape | foundry-target-product-shape | | MVP Scope | foundry-mvp-scope | | Basic Product Identity | foundry-basic-product-identity | | Screen-Level Product Shape | foundry-screen-level-product-shape | | Artifact Generation | foundry-artifact-generation | | Dossier Review | foundry-dossier-review |

额外聚焦 skill:foundry-concept-revision 用于锁定后的方向修订,foundry-research-fanout 用于 research plan validation 和 synthesis。

安装目标

安装目标只是很薄的 packaging layer,不拥有产品逻辑。

| Target | Path | 用途 | | --- | --- | --- | | agents | .agents/skills/ | 默认目标。安装 root、stage、transition 和 support skill entries。 | | claude-code | .claude/skills/ | 可选的 Claude Code native skill discovery。 | | opencode | .opencode/skills/ | 可选的 OpenCode native discovery path。 |

安装目标不能 fork stage sequence、memory schema、stage skill output shape、research synthesis structure、artifact manifest fields、gate rules 或 required confirmations。

仓库结构

.
├── SKILL.md
├── agents/
├── CONTEXT.md
├── skills/
├── templates/
├── scripts/
├── examples/
├── targets/
└── package.json

开发验证

docs/ 是开发记录和设计历史。它会被 git 忽略,不属于安装后的 Foundry skill core、runtime surface,也不进入 npm package。正式产品行为以 SKILL.mdskills/templates/scripts/targets/、README 和 CONTEXT.md 中的稳定术语为准。

examples/ 是开发期 fixture 和回归材料,不是正式产品 surface。它不会安装到 agent skill 目标目录,也不会进入 npm package。

运行正式产品级检查:

npm run check:product

运行开发期 fixture 检查。examples/solo-ai-tool 不存在时,这个命令会正常跳过:

npm run check:fixture

npm run check 是默认正式产品级检查:

npm run check

同时运行正式产品级和 fixture 检查。fixture 检查仍然只属于开发期,缺少本地 fixture 时会正常跳过:

npm run check:all

发布前用本地 npx 方式预览安装计划:

npx --yes --package . foundry-product-thinking-toolkit install --dry-run

运行边界

这个工具包帮助 agent 引导产品思考并生成产品交付材料。它不负责实现最终产品本身。

Foundry stage skills 返回结构化建议,也可以直接用于聚焦阶段。orchestrator 负责从头到尾的推进、跨阶段移动、product memory 写入、research synthesis 和 artifact indexing;除非用户明确要求阶段 skill 应用已接受的 memory patches。