agentleFS
allanjohnyallanjohny/parce/skills/brain/SKILL.md

brain

Skill0 starsChanged 4 months agoMITView on GitHub

Rebuild the assistant's memory knowledge graph — generates graph.json, brain.html (navigable mind map) and auto-links related memories. Use after creating or editing memories, or when the user asks to "rebuild the brain" or "show me your brain".

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After creating or editing significant memories

    line 45
  2. Distinctive:

    When starting a new project (new memories → new links)

    line 46

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

Brain rebuild

Rebuilds the memory knowledge graph: generates memory/graph.json, memory/brain.html (interactive mind map) and updates the ## Related (auto) section in each memory .md file.

Usage

node skills/brain/build-graph.mjs

The script resolves the memory directory as: env MEMORY_DIR → <repo>/memory (relative to the script itself). Portable: runs in any clone with zero config.

What it does

  1. Reads every *.md in the memory directory (except MEMORY.md, _template.md)
  2. Computes weighted edges from: explicit links ([[wikilinks]] and markdown links), shared filename prefix, shared tags, same type, keyword overlap (TF-IDF cosine)
  3. Normalizes weights to [0, 1], discards < 0.25
  4. Writes memory/graph.json
  5. Patches ## Related (auto) (top-3 neighbors) into each memory file — idempotent
  6. Generates memory/brain.html — open in a browser, works fully offline

Expected output

Found 50 memory files
Computed 312 edges (raw: 1225)
graph.json: 50 nodes, 312 edges, avg 0.41
Patched 48 files with Related (auto)
brain.html written

Query the brain

node skills/brain/brain-query.mjs <terms...> [--top=N] [--type=feedback]

When to run

  • After creating or editing significant memories
  • When starting a new project (new memories → new links)
  • Monthly, as maintenance

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.