close-my-loops

# Close My Loops This skill has three parts. They build on each other but are each independently useful — jump to whichever one matches what the user asked for. 1. **Build/refresh `brain.md`** — a profile of the user's working life, from their own email/Slack. 2. **Set up a Cowork Project** so that file gets read automatically every session, instead of only when someone remembers to mention it. 3. **Set up a scheduled task** that refreshes the file daily and sends a summary of what needs attention. The three connect: Part 2 is what makes Part 1's file actually useful without the user re-uploading it every time, and Part 3 is what keeps it current without the user having to ask again. A brain.md nobody re-reads, or one that goes stale, is much less valuable than the sum of its parts — so if the user only asks for Part 1, it's worth mentioning Parts 2 and 3 exist once the file is built. --- ## Part 1: Build or refresh brain.md ### What this produces A single markdown file (default name `brain.md`) that a future Claude session can read to answer things like "find my important emails," "draft a reply to X in my style," or "who owns this initiative." It's not a knowledge base of facts about the world — it's a profile of *the user's working life*: who they talk to, how, and what's currently in flight. The file has different kinds of content, and it matters that you keep them distinct: - **Stable content** — role, reporting line, key people, communication style. Changes slo...