Show HN: Nanopm – Claude 代码的 PM 自动化（审计 → 策略 → 路线图）
3 分•作者: nmrtn•5 个月前
Garry Tan 的 gstack 证明了你可以通过 SKILL.md 标准，让 Claude Code 拥有一个完整的工程团队。我问：那 PM 层呢？
一个命令（/pm-run）可以在你的终端内运行完整的规划周期——审计 → 目标 → 战略 → 路线图 → PRD。每个技能都会编写一个 Markdown 文档，下一个技能会读取它。上下文会在整个流程中不断累积。
我发现最有用的部分是：它在 ~/.nanopm/memory/ 中构建了你产品的持久性记忆。六个月后重新运行 /pm-audit，它就知道你之前尝试过什么。没有其他 PM 工具能做到这一点，因为没有其他 PM 工具存在于你的编辑器中。
/pm-breakdown 可以直接从 PRD 创建 Linear 或 GitHub Issues 中的工单。
[https://github.com/nmrtn/nanopm](https://github.com/nmrtn/nanopm)
还在早期阶段，很想知道：在你的编辑器内运行 PM 感觉合适吗，还是它应该属于一个单独的工具？
查看原文
Garry Tan's gstack proved you can give Claude Code a full engineering team
via the SKILL.md standard. I asked: what about the PM layer?<p>One command (/pm-run) runs the full planning cycle inside your terminal —
audit → objectives → strategy → roadmap → PRD. Each skill writes a markdown
artifact, the next one reads it. Context compounds across the whole pipeline.<p>The part I find most useful: it builds persistent memory of your product in
~/.nanopm/memory/. Re-run /pm-audit six months later and it knows what you
tried before. No other PM tool does this because no other PM tool lives in
your editor.<p>/pm-breakdown creates tickets directly in Linear or GitHub Issues from the PRD.<p><a href="https://github.com/nmrtn/nanopm" rel="nofollow">https://github.com/nmrtn/nanopm</a><p>Early days, would love to know: does running PM work inside your editor feel right, or does it belong in a separate tool?