agentleFS
Sign inStart free
fredoliveirafredoliveira/agents/skills/index-atomic-notes/SKILL.md

index-atomic-notes

Skill24 starsChanged 5 months agoMITView on GitHub

Index an atomic note in existing maps of content and find potential connections to related atomic notes.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add a link to the atomic note in the appropriate section of each relevant MOC

    line 25
  2. Very specific:

    Add those topics to the note's frontmatter topics property

    line 26
  3. Distinctive:

    Ask the user whether to create a new topic or leave the note unindexed for now

    line 30
  4. Distinctive:

    Start by exploring notes already linked from the relevant topics

    line 34
  5. Distinctive:

    If the answer to the last question is "yes", suggest the link to the user instead of adding it.

    line 56
  6. Distinctive:

    Update the MOC: Add a link to this note in an appropriate section of the AI topic file

    line 89
  7. Very specific:

    Update the note's frontmatter: Add the topics property:

    line 90
  8. Distinctive:

    Explore connections: Look at other notes linked from the AI topic and ask the user about potential cross-links

    line 105

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Atomic note indexer

Purpose

Integrate a new atomic note into the knowledge graph by:

  1. Filing it under relevant topic maps of content (MOCs)
  2. Discovering and creating meaningful connections to other atomic notes

Instructions

1. Understand existing topics

Browse the Topics/ folder to understand what maps of content already exist and what subjects they cover.

2. File the note under relevant topics

If the note fits existing topics:

  • Add a link to the atomic note in the appropriate section of each relevant MOC
  • Add those topics to the note's frontmatter topics property

If no suitable topic exists:

  • Ask the user whether to create a new topic or leave the note unindexed for now

3. Find connections to other atomic notes

  • Start by exploring notes already linked from the relevant topics
  • Identify notes that relate meaningfully to the new one
  • Always ask the user before modifying other notes

Preserving Atomicity When Cross-Linking

Each atomic note should contain a single, focused insight. Cross-links must enhance without diluting.

Principles

DoDon't
Add brief links that provide nuanceAdd explanatory text that expands the scope
Suggest connections to the userModify notes without permission
Preserve the original focusTurn notes into discussion hubs

Self-check before adding a link

  • Does the note title still capture the complete insight?
  • Could a reader understand the core idea from the title and first paragraph alone?
  • Am I changing what this note is fundamentally about?

If the answer to the last question is "yes", suggest the link to the user instead of adding it.

Examples

Good cross-link — adds nuance to existing insight:

Original: "Large language models understand concepts" Addition: "However, [[Performance depends on verifiability]], which means they show stronger capabilities on verifiable tasks."

Bad cross-link — dilutes atomicity:

Original: "AIs are currently trained very broadly" Addition: "This broad training is particularly effective for verifiable tasks because..." Problem: Shifts focus from describing training to explaining task performance.

Example Workflow

Given this atomic note:

---
title: The AIs of today are more grown than written
created: 2025-07-05
tags:
  - note/atom
category:
  - "[[Atoms]]"
---

Steps:

  1. Identify topic: This note belongs under Topics/Artificial Intelligence.md
  2. Update the MOC: Add a link to this note in an appropriate section of the AI topic file
  3. Update the note's frontmatter: Add the topics property:
---
title: The AIs of today are more grown than written
created: 2025-07-05
tags:
  - note/atom
topics:
  - "[[Artificial Intelligence]]"
category:
  - "[[Atoms]]"
---
  1. Explore connections: Look at other notes linked from the AI topic and ask the user about potential cross-links

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free