Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Second Brain

ASecurity

Build a second brain: a trusted external system for capturing, organizing, and retrieving everything you learn and need. Use when knowledge is scattered or you want ideas to compound over time.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgoexpressawsdatabase

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill second-brain --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Second Brain?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Second Brain
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-second-brain/badge)](https://www.skillsdirectory.com/skills/aicodedecode-second-brain)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: second-brain
description: Build a second brain: a trusted external system for capturing, organizing, and retrieving everything you learn and need. Use when knowledge is scattered or you want ideas to compound over time.
category: productivity
---

# Second Brain

## Overview

A second brain is an external, organized, searchable system holding what your biological brain shouldn't have to: notes, ideas, resources, tasks, references.

Purpose: free your mind for thinking by trusting capture; make knowledge compound by connecting and revisiting it.

Built on four capabilities: capture everything, organize for action, distill to essence, express by creating.

Tool-agnostic — Notion, Obsidian, or any notes app works. The system matters, not the software.

## When to use

- Knowledge scattered across apps, notebooks, and memory
- Reading/learning a lot but retaining and reusing little
- Creative or knowledge work needing a personal idea library
- Setting up a long-term personal knowledge management system
- Wanting past work and learning to compound instead of evaporate

## Core concepts

- **Capture everything.**
  Fleeting ideas, quotes, highlights, meeting notes, voice memos — into one inbox within seconds. The brain is for having ideas, not storing them.
- **Organize for actionability.**
  File by where it's useful (projects, areas, resources), not by source or topic taxonomy. Organization serves retrieval, not aesthetics.
- **Distill progressively.**
  Bold key passages, highlight the best, summarize, extract the essence. Each layer compresses; the top layer is what you'll actually reuse.
- **Express regularly.**
  Knowledge compounds when used: write, build, teach, decide. A second brain that only collects is a museum; expression is the point.
- **Projects over topics.**
  Organize primarily around active projects (things with goals and deadlines). Topic-based filing creates beautiful libraries nobody opens.
- **Search-first retrieval.**
  Design for search: good titles, consistent naming, full-text search you trust. Retrieval beats perfect folders.
- **Interoperability.**
  Plain text / standard formats where possible. Your second brain should survive app changes — export regularly, avoid lock-in.
- **Review rhythms.**
  Weekly inbox processing, monthly project reviews, quarterly archive sweeps. A brain without maintenance becomes a attic.

## Practical workflow

1. **Choose one home.**
   One primary app for the second brain. Notion, Obsidian, Apple Notes — pick by your needs (database vs. markdown vs. simplicity).
2. **Set up capture everywhere.**
   Mobile quick-add, desktop hotkey, email-to-inbox, read-later integration. Capture in under 10 seconds from anywhere.
3. **Create the structure.**
   Top-level: Inbox, Projects (active), Areas (ongoing responsibilities), Resources (topics/interests), Archive. Keep it shallow.
4. **Migrate gradually.**
   Don't big-bang migrate years of notes. Move things as you touch them; leave the rest in a legacy archive, searchable.
5. **Build the distilling habit.**
   When saving anything: bold the key sentence, add one line in your own words. Thirty seconds now saves hours later.
6. **Create retrieval paths.**
   Project dashboards, an index note, consistent titles (`YYYY-MM-DD topic`). Test: can you find it in 30 seconds?
7. **Schedule expression.**
   Weekly writing/building time that draws on the brain. Retrieval practice is what converts storage into knowledge.
8. **Maintain quarterly.**
   Archive dead projects, merge duplicates, delete the useless. A second brain is a garden, not a warehouse.

## Common pitfalls

- **Collecting without expressing.**
  10,000 saved articles, zero created. Capture without expression is hoarding with extra steps.
- **Organizing as procrastination.**
  Perfecting folders and tags instead of thinking. Organization serves retrieval; beyond that it's avoidance.
- **Tool obsession.**
  Migrating apps yearly, rebuilding the system each time. The system is the habits, not the software. Commit.
- **No capture habit.**
  Elaborate structure, empty inbox. If capture takes >10 seconds, ideas stay in your head and die there.
- **Over-distilling.**
  Five layers of highlighting on every article. Distill the keepers; most inputs deserve capture-only or deletion.
- **Topic-based everything.**
  Beautiful topic hierarchies nobody browses. Organize by active projects first; topics are secondary.
- **No backups/exports.**
  Years of thinking in a proprietary format with no export. Regular exports; prefer portable formats.
- **Review-less accumulation.**
  Inbox growing forever, archive never touched. Without review rhythms, the brain becomes an attic of good intentions.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →