agentsclimarketplace

Second brain

Skill SkillMedev/skills/skills/second-brain

The open Skill Me catalog — every hosted skill as a portable, MIT-licensed SKILL.md

Install
npx -y skills add SkillMedev/skills --skill second-brain

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Sets up a PARA-based second brain in any notes app (Notion, Obsidian, Apple Notes, Logseq) - Projects, Areas, Resources, Archives buckets, a frictionless universal capture inbox, weekly organizing, wiki-link and map-of-content linking, progressive summarization for recall, and maintenance rituals. Use when someone says "help me set up a second brain", "my notes are a mess and I can never find anything", "how do I organize Obsidian with PARA", or captures ideas but never uses them. Do NOT use for designing the underlying Notion database properties and relations - use notion-database instead - or for a task-management workflow - use gtd-system instead.

SKILL.md

3.9 KB, as published. Nobody here has run it

Second Brain

A second brain is an external, trusted system for everything you want to remember and act on. This skill sets one up using the PARA method in any notes app (Notion, Obsidian, Apple Notes, Logseq).

The PARA model

Organize every note into one of four top-level buckets, ordered by actionability:

  • Projects - short-term efforts with a goal and a deadline (e.g. "Ship Q3 launch").
  • Areas - ongoing responsibilities with a standard to maintain (e.g. "Health", "Finances").
  • Resources - topics of interest for future reference (e.g. "Prompt engineering").
  • Archives - inactive items from the other three buckets.

Rule: a note lives where you will next act on it, not where it topically "belongs".

The four workflows

1. Capture

Lower friction to near zero. Set up one universal inbox note or quick-capture shortcut. Capture anything: ideas, links, quotes, tasks. Do NOT organize at capture time - speed beats structure here.

2. Organize (weekly)

Once a week, empty the inbox. For each item:

  • Is it actionable now? -> attach to a Project.
  • Is it an ongoing standard? -> file under an Area.
  • Might it be useful later? -> Resource.
  • Otherwise -> delete or Archive.

3. Link

Connect notes so recall works by association, not folders:

  • Add 2-3 [[wiki-links]] or relations to related notes when you file something.
  • Maintain a few index/MOC (map of content) notes that link out to clusters.
  • Tag sparingly - links beat tags for retrieval.

4. Recall (Express)

The point of the system is output. When starting work:

  • Search the relevant Project/Area note first.
  • Follow links outward to gather supporting Resources.
  • Distill into a working draft. Progressive summarization: bold the best lines, highlight the best of the bold.

Note template

# <Title>
Bucket: Projects | Areas | Resources | Archives
Created: <date>
Links: [[related-1]] [[related-2]]

## Summary
<2-3 sentence why-this-matters>

## Notes
<content>

## Next action
<the single next step, if any>

Maintenance rituals

  • Weekly review (20 min): empty inbox, mark finished projects, archive the dead.
  • Monthly (10 min): promote hot Resources, prune stale links.

Anti-patterns to avoid

  • Over-tagging or building deep folder trees - PARA stays flat (4 levels max).
  • Collecting without expressing - capture is only valuable if you later create.
  • Organizing at capture time - it kills capture velocity.

Quality bar

  • Capturing a new thought takes seconds and zero decisions - one inbox, no filing at capture time.
  • Every existing note lands in exactly one PARA bucket, placed by next action, not by topic.
  • Filed notes carry 2-3 outbound links, and each major cluster has an MOC note pointing into it.
  • The weekly and monthly rituals are written down with a trigger (day + time), not left as intentions.

Deliverable

Produce a working second-brain setup in the user's chosen app: the four PARA top-level buckets created, a universal capture inbox wired to a quick-capture entry point, the note template installed, 2-3 starter MOC/index notes for their main clusters, and a written maintenance checklist (the 20-minute weekly review and 10-minute monthly prune) with a scheduled trigger for each.

Gives 0 of the 12 instructions most note taking skills give

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-06

  • include a visual element on every slidein 44 of 686, across 13 files
  • use wikilinks for internal vault linksin 35 of 686, across 11 files
  • commit to a single visual motif across every slidein 34 of 686, across 9 files
  • read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
  • keep 0.5 inch minimum marginsin 30 of 686, across 7 files
  • use subagents to visually inspect rendered slidesin 30 of 686, across 6 files
  • re-verify affected slides after every fixin 27 of 686, across 5 files
  • run content QA checks before declaring successin 26 of 686, across 3 files
  • Use Markdown links for external URLs onlyin 26 of 686, across 10 files
  • pick a bold topic specific color palettein 24 of 686, across 2 files
  • read editing guide before editing existing presentationsin 23 of 686, across 1 file
  • use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

  • create four top-level PARA buckets
  • set up one universal capture inbox
  • empty the inbox weekly
  • add two to three wiki-links to filed notes
  • maintain map of content notes for clusters
  • search relevant project or area notes first

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.