Generate a Personalized Second Brain Build Plan

Generates a personalized Product Requirements Document for building an AI second brain from a requirements template. Instead of guessing how to wire Claude into your personal tools and workflow, this skill reads your tech stack and preferences, researches your platforms, and produces a detailed 9-phase build plan tailored to your specific setup.

1. Fill out the requirements template with your tools, top tasks, proactivity level, and security boundaries. 2. Run the skill with the path to your completed template. 3. The skill loads the architecture reference, researches every API in your stack, and generates a personalized PRD. 4. You follow the phases in order (Memory Layer, Hooks, Search, Integrations, Skills, Proactive Systems, Chat, Security, Deployment). Output: a step-by-step build guide with code paths, API specifics, dependencies, and personalization notes for each phase.

A second brain tailored to your exact platform stack and proactivity preference, with no guesswork on API auth, hook setup, or security hardening.

Requires Claude Code SDK for PRD generation and research capability. The generated second brain uses FastEmbed ONNX models for local embeddings (70MB model cache), SQLite with sqlite-vec and FTS5 for memory search, and Python for heartbeat scheduling. If building the chat interface, requires Slack SDK and Socket Mode. The heartbeat requires concurrent file locking (fcntl on Unix, msvcrt on Windows) because multiple background processes write to daily logs simultaneously. See generated PRD Phase 2 (Hooks) for shared.py implementation patterns.

Requires Claude Code to run. The generated PRD assumes you will implement each phase sequentially. Later phases depend on earlier ones (e.g., integrations require the hooks layer). Each phase is estimated Medium-High complexity; the full build timeline is 3-4 weeks for a solo developer. The PRD generates code paths and patterns but does not auto-scaffold the actual codebase.