Brain to docs
Use when David wants to extract project vision, decisions, and preferences from his head into clear documentation (README + ADRs) through a back-and-forth Q&A loop. Triggers on "brain-to-docs", "build out the docs", "extract the vision", "let's document this project".From its SKILL.md
npx -y skills add adriannoes/awesome-agentic-ai --skill brain-to-docsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.7 KB, 361 tokens by cl100k_base, as published. Nobody here has run it
brain-to-docs
The whole purpose: extract as much of David's taste, judgment, knowledge, vision,
preferences, and decisions as possible into text — saved as clear, concise
markdown docs for the project. README holds the vision; docs/adr/ holds the
decisions.
The loop
- Check docs first, every time. Read
docs/adr/(andREADME.md) before doing anything — other agents and people add/edit ADRs constantly. - Ask 5 different questions in plain text (never a questions UI) — default 5 unless David asks for a different number. Make them high-variety: a wide, creative spectrum of unique angles, not all the same type (e.g. not all "tech stack" or all "product" or all "monetization"). Exception: if David asks for a specific focus area, follow it. David answers whichever he finds most useful.
- Update docs after EVERY answer — no exceptions. You decide whether it
updates
README.mdor becomes a new ADR — whatever makes sense. - Repeat until David says "we're done" (or similar).
Rules
- All answers & responses during this "brain to docs" process must be VERY CONCISE, all sentences should be SHORT, and everything should be written in PLAIN ENGLISH.
- ADRs: short, numbered
NNNN-slug.md, Status + Context + Decision + Consequences. - README: vision only. Decisions go in ADRs.
- Don't challenge David's thinking unless he asks, or he's making a severe mistake.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.