独立运营 · 不出售排名位置  · 我们怎么评估工具 →
Anclum 提交收录
P

productweaver/productweaver-plugin

本站为独立目录,非该工具官网;下方信息取自其公开仓库。

Decide what to build by turning your discovery interviews into a clear map of needs and features linked to evidence. (原文为英文)

3 ★ 本站实测 · 核对 2026-11-19

装之前:命令归属未核实,仅作参考展示 · 许可证 Apache-2.0 · 链接可访问

第一步(仅参考,归属未核实):directly, the script needs pypdf (python3 -m pip install pypdf==6.21.4).

checked 2026-11-20 — 命令里的包名与条目不一致,未作为可复制命令展示。

★ 3·更新 2026-11-18
在 GitHub 查看 ↗链接已于 2026-11-17 核查 · HTTP 200 · 打开的是厂商自己的官网

装完之后怎么算装好了

  1. 装完该看到什么 — 命令正常结束时退出码为 0,终端里没有 "command not found" 或 "permission denied"。
  2. 一行自检 — 按该仓库 README 里给出的最小用法跑一次;能按 README 的描述输出就是通了。
  3. 答不出来怎么办 — 这个项目没有写排错说明,去仓库的 Issues 搜 install。

安装命令取自该仓库;以上判据只描述可观察到的结果,不替代项目自己的文档。

★ 数取值
3 ★ · productweaver/productweaver-plugin · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
来源明细
从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
收录与活跃
收录于 2026-11-17 · 最近见到 2026-11-20 · 共见到 4 次 · 被 1 个来源列出
评分构成
综合分 103 · 3 ★ · 1 个来源 · repo
安装
安装命令见上方「安装与配置」。
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: Agent 技能。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库 productweaver/productweaver-plugin;我们收录于 2026-11-17;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
README 原文(英文,未翻译) · 在 GitHub 读完整 README →

# Product Weaver

以下摘录自该仓库的 README(片段)

Product Weaver is a plugin for AI assistants like Claude, ChatGPT/Codex, and Copilot that turns customer interview transcripts into a
consolidated and growing knowledge base, with every quote checked word for word against its transcript.
Free, under the Apache 2.0 license. It runs on your computer, needs only
Python, and sends nothing unless you say yes.
The discovery map of the example study, made from 6 interviews.
Open the live map.
## What you get
You give your assistant a folder of interview transcripts and ask in plain
words. You get back a discovery map you can open in any browser. It shows
what your customers are trying to get done: their jobs, the steps of
each job, and the outcomes they measure success by;
the proof: every finding is backed by quotes in the words people used.
Each quote is checked against its transcript before it goes in, so the
study never holds paraphrased evidence;
who does which job, when the people you interviewed do different jobs;
what people use today to get each step done, and what they stopped
using;
value themes: the outcomes grouped into a few needs, such as "Help me
order what the week will really need", so your team can sort ideas;
your next interviews: who to talk to and what to ask, to back up what
still rests on too few people.
Leave the map open while you work: it updates itself a few seconds after
each run, keeps your place, says what changed, and marks what is new. While
your assistant reads a batch, the map says so and about how long is left.
The study grows with every batch of interviews you add. The method is
Outcome-Driven Innovation (ODI), a way to do jobs-to-be-done research. You
do not need to know it to start.
## Try it in 10 minutes
You do not need your own interviews to try it.
1. Install the plugin in your assistant:
Claude desktop app,
Claude Code, ChatGPT and Codex or
GitHub Copilot CLI.
2. Get some interviews. Use a folder with your own transcripts
(.md, .txt, .docx or .pdf). Or
download 6 sample interviews
and unzip the file. You get a folder called bookkeeper-interviews.
3. Open your assistant in that folder (in Cowork, choose the folder) and
say
> Help me get started with Product Weaver.
What happens next
The assistant reads the interviews. This takes about a minute or two for
each interview, so about 10 minutes for the 6 samples.
The discovery map opens in your browser.
The assistant asks you in the chat, with a click, whether it got right
what these people are trying to get done.
It names one next step.
No interviews yet? Say the same sentence in an empty folder. The assistant
asks 3 questions and writes a guide for your first interviews: who to talk to
and what to ask.
## Install
### Claude desktop app (Cowork)
No terminal needed.
1. Open Customize in the left menu.
2. Choose Plugins, then Yours.
3. Click Add, then Add marketplace.
4. Choose Add from repository.
5. Type productweaver/productweaver-plugin.
6. Turn on Sync automatically.
7. Click Sync.
8. In the list, find Product Weaver and click Add.
Then start a task in Cowork, choose the folder with your transcripts, and
ask in plain words.
If you use claude.ai in a browser, run the plugin in the desktop app: it works
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/zh/s/productweaver-productweaver-plugin/)
来源
github · https://github.com/productweaver/productweaver-plugin
按领域浏览
Agent 技能
Traction
3 ★
收录于
今天

更多条目

全部 471 →

所属领域与标签

每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。

浏览全部领域 →

← 返回索引