Skip to content

Productivity Blueprint

Safety checked

Generate a Personalized Second Brain Build Plan

5coleam00May 2026

A Claude Code skill that generates a phase-by-phase PRD for building an AI second brain with memory, integrations, proactive monitoring, and security hardening.

PRD GenerationSecond Brain ArchitectureMulti-Platform IntegrationSecurity Hardening

Install Prompt

Copy this prompt and paste it into your AI agent to install.

What problem does this solve?

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.

How does it work?

  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.

Included Skill Groups

View Blueprint →

What's the biggest win?

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

What's required to run this?

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.

What should I watch out for?

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.

Key Features

Personalized PRD Generation

Reads your requirements and generates a 9-phase build plan with code paths, API details, and implementation notes specific to your platforms.

Multi-Platform Research

Automatically researches Gmail, Slack, Linear, Asana, GitHub, Calendar, and other integrations to ensure API-accurate implementation guidance.

Proactivity-Level Mapping

Maps your choice (Observer, Advisor, Assistant, Partner) to concrete behaviors in heartbeat scheduling, draft generation, and automation scope.

Security-First Phases

Includes dedicated phases for credential protection, external data sanitization, guardrails, and API key isolation with specific code patterns.

Starter Memory Templates

Includes ready-to-use BOOTSTRAP.md, SOUL.md, USER.md, and daily log templates for instant vault setup.

Tools in this Blueprint

Claude logo
4.6(456 reviews)
Claude logo
4.4(68 reviews)
Claude Agent SDK
FastEmbed

About This Blueprint

Industry
Technology
Skills
1 skills total
2 Skills
Product & DesignSafety checked

Send Weekly Product Defect Reports

Catch product defects before scattered support tickets obscure a rising trend. Weekly reports group faults by product and type, compare them with the prior four weeks, and include customer photos and quotes for faster quality investigations.

Yuma AIYuma AIClaudeClaudeShopifyShopify

Urska Blagojevic

GTM Lead at Yuma AI (YC W23)

2 Skills
Customer ExperienceSafety checked

Fix Wrong AI Agent Answers Before They Recur

Stop the same support mistake from frustrating customers again: trace incorrect Yuma replies to the Handbook, missing order data, failed actions, or bugs, then test a proposed fix before publishing it. A weekly report highlights recurring causes and the next tickets to investigate.

Yuma AIYuma AIShopifyShopifyClaudeClaude

Urska Blagojevic

GTM Lead at Yuma AI (YC W23)

1 File
Customer ExperienceSafety checked

Onboard a new agency client in Hive from a project template

Avoid a client’s first week starting with unowned tasks or a missing kickoff. The setup shifts template dates, flags weekend deadlines and open owners, then verifies approved updates in Hive before handing over a week-one list and welcome-note draft.

HiveHiveClaudeClaude