calibratinglisted

# Calibrating ## Overview mindpowers does one loop: shape, draft, review, and remembers what you like. This skill is the "remember" step, and the only one that writes `docs/mindpowers/preferences.md`. `mindstorming` step 1 reads that file before it starts a new session, so what gets recorded here shapes every future spec of that template type. This is a light skill. Don't turn it into an interrogation: most of the time there are 1-3 short questions and one write. ## Process 1. **Identify what this is about.** Figure out which spec/draft the feedback concerns. Scan `docs/mindpowers/specs/` and `docs/mindpowers/drafts/` for a matching topic or recent file; if it's genuinely ambiguous, ask which one. Note its template `type`: preferences are filed under that type. 2. **Ask at most 3 questions**, skipping any already answered by what the user just said: - What landed: what worked and should happen again? - What got cut or rewritten by a human: where did the draft miss? - What should change next time? 3. **Distill into 1-3 one-line preference entries.** Short, concrete, reusable, not a summary of the conversation. 4. **Show the entries and get approval before writing.** Let the user edit the wording. 5. **Append to `docs/mindpowers/preferences.md`** under the matching template's section. ## preferences.md format Markdown, sectioned by template type, each section a flat bullet list of dated one-liners: ```markdown <!-- Read by mindstorming step 1. Written only by c