document-generate (gstack)
- Docs
Writes documentation that does not exist yet — reads a feature, module, or whole project and produces the missing docs from scratch. It creates fresh documentation for undocumented code, distinct from updating docs after a release, rendering a doc to PDF, or pulling data off a web page.
A situation it fits
A whole feature shipped with no docs at all. You want documentation created for it from nothing, so new engineers can understand it.
3 scenarios in the bank answer to document-generate (gstack). The rest are in the game.
Skills it gets confused with
These share a family with document-generate (gstack), which is another way of saying they are the ones you might reach for by mistake.
- document-release (gstack)Brings existing documentation back in sync AFTER a change ships — updating the changelog, guides, and references to match what actually landed. It maintains docs post-release, not authoring brand-new docs for undocumented code, converting a file to PDF, or scraping a website.
- make-pdf (gstack)Turns a Markdown file into a polished, publication-quality PDF ready to hand off or print. Its job is the format conversion — Markdown in, styled PDF out — not writing or updating the documentation's content, and not extracting data from web pages.
- scrape (gstack)Pulls structured data out of a web page that does not offer it cleanly — reading the page and extracting the fields you need. It gathers data from the web, unrelated to authoring documentation, maintaining it after a release, or rendering a document to PDF.
Knowing what document-generate (gstack) does is the easy half. Telling it apart from the others under time pressure is the game.
Today's sessiondocument-generate (gstack) is part of garrytan/gstack. Licence: MIT. The description above was written for this game, not taken from the skill.