← ClaudeAtlas

pw-discoverylisted

Turn raw customer interview transcripts into Outcome-Driven Innovation (ODI) knowledge and fold it into a knowledge base, one JSON file, that grows with every batch. Use whenever someone shares new interview transcripts, notes or emails (md, txt, docx, pdf), also from someone already interviewed, and wants jobs-to-be-done extracted, job executors and core jobs identified, job steps or desired outcomes updated, the tools and workarounds people use today collected and grouped, evidence quotes attached, the outcomes grouped into a few value themes to guide ideation, or an existing ODI/JTBD knowledge base updated or started. Also use for "add these interviews to the KB", "add my follow-up call with Dana", or starting an ODI study for a new client, even if the user doesn't say "ODI" or "JTBD". Also use for answers to its decisions, such as "In my Product Weaver study, the goal is right", and when the user asks to stop sharing usage statistics. From Product Weaver (productweaver.com).
productweaver/productweaver-plugin · ★ 3 · Data & Documents · score 76
Install: claude install-skill productweaver/productweaver-plugin
# pw-discovery: fold interviews into an ODI knowledge base *A free skill from [Product Weaver](https://productweaver.com).* One JSON file is the knowledge base (KB). Each run reads new transcripts, extracts ODI knowledge with verbatim evidence, and merges it into the KB through `scripts/kb_tool.py`. The script checks every quote against its transcript and refuses the whole merge if one does not match. That makes the KB safe to build on over many runs: nothing in it is paraphrased evidence or a duplicate. ## Running the script The script needs Python 3.9 or newer and nothing else: it uses only Python's standard library, so `kb_tool.py` installs nothing and needs no network. It finds its schemas and the map template next to itself, so run it from the root of the workspace, where the study lives: ``` python3 <skill folder>/scripts/kb_tool.py <command> ... ``` Below, `kb_tool` stands for that line. Do not write plain `python`; many machines do not have it. On Windows, if `python3` is missing, use `py -3`. Write the script's full path in every command: never put it in a shell variable (`S=<skill folder>`), never `cd` into the skill folder, and never run it in a `for` loop: write each command out. Claude Code cannot check such a command, so it asks the user or refuses it. Several `kb_tool` commands may share one call. Transcripts can be `.md`, `.txt`, `.docx` or `.pdf`. The script reads `.docx` itself. It reads `.pdf` with pypdf when that package is installed. When it is no