Independent by design · no pay-to-rank placements  · How we evaluate tools →
Anclum Submit
P

productweaver/productweaver-plugin

Independent directory — not the official site. Details below come from the project's public repository.

Decide what to build by turning your discovery interviews into a clear map of needs and features linked to evidence.

3 ★ measured · checked 2026-11-19

Before you install: command ownership unverified - shown for reference only · license Apache-2.0 · link reachable

First step (reference only, ownership unverified): directly, the script needs pypdf (python3 -m pip install pypdf==6.21.4).

checked 2026-11-20 - the package in the command does not match this entry, so it is not shown as a copyable command.

★ 3·updated 2026-11-18
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site

After install: how to tell it works

  1. What you see after install — The command exits 0 and the terminal shows no "command not found" or "permission denied".
  2. One-line self-check — Run the smallest usage example from that repository's README. If the output matches what the README describes, it is working.
  3. If that does not work — This project has no troubleshooting notes. Search its issues for "install".

The install command comes from the repository; these checks describe observable results only and do not replace the project's own docs.

Star count
3 ★ · productweaver/productweaver-plugin · read from the GitHub search API · (checked 2026-11-19 20:00:48)
Source
read directly from its GitHub page · type: open-source project
Harvest history
first seen 2026-11-17 · last seen 2026-11-20 · seen 4× · listed by 1 sources
Score
score 103 · 3 ★ · 1 sources · repo
Install
see Install & config above
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Agent skills. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository productweaver/productweaver-plugin;first catalogued 2026-11-17;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.
README excerpt (English, untranslated) · Read the full README on GitHub →

# Product Weaver

Excerpted from the repository README (abridged)

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
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/en/s/productweaver-productweaver-plugin/)
Source
github · https://github.com/productweaver/productweaver-plugin
Browse by field
Agent skills
Traction
3 ★
added
today

More entries

All 471 →

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields →

← Back to index