cerebellum
Skill9 starsChanged 6 months agoApache-2.0View on GitHub
Single fast-execution skill for macOS / Linux / Windows app operations. The "cerebellum" to the LLM's "cerebrum" — the brain decides intent, this skill executes the canonical multi-step pattern in one syscall sequence (no LLM round-trip per step).
In this repository22 other files it gives its agents.
- app_open_cleanSkill
- browser_sessionSkill
- git_commitSkill
- imsg_sendSkill
- learnSkill
- locationSkill
- mail_draftSkill
- music_pauseSkill
- music_playSkill
- notes_attach_imageSkill
- notes_checklistSkill
- notes_export_pdfSkill
- notes_formatSkill
- notes_move_to_folderSkill
- notes_pinSkill
- notes_tableSkill
- sttSkill
- summarizeSkill
- translateSkill
- ttsSkill
- weatherSkill
- webSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 108
All of that lives in the cerebellum.
≈ “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.
Files
cerebellum — fast cross-platform operation dispatcher
A single skill that wraps battle-tested canonical sequences for common app patterns. Single LLM round-trip in, one syscall sequence out. Designed to eliminate the LLM-tax on "obvious" multi-step operations. Per-OS backends:
- macOS — AppleScript / osascript / shell
- Linux — shell + POSIX tools (xdg-open, gtk-launch, gsettings, pactl, …)
- Windows — bash → powershell.exe (Move-Item, AppActivate, WMI, UIA, …)
When to use
For ANY of these patterns, prefer cerebellum over raw shell + multi-step:
- File ops (rename, move, copy, zip, mkdir, trash)
- Finder view/sort/sidebar settings
- Notes CRUD (create, append, delete, pin, format, export)
- Mail draft creation
- Tag operations
Architecture
LLM (cerebrum) cerebellum OS
────────────── ────────── ──
"rename old.txt
to new.txt" ───► parse intent ───► mv old.txt new.txt
run canonical ◄─── return ok
(handles retries,
iCloud sync waits,
kHasCustomIcon flag,
etc — all without
bothering the LLM)
◄─── ok
◄─── "done"Internal verify, retry, and platform quirks are baked in — the LLM
doesn't need to know that macOS 14+ removed the AppleScript pinned
property, or that Notes' table requires Cmd+Opt+T after AXFocus,
or that Mail draft saving needs tell app Mail to launch + sleep.
All of that lives in the cerebellum.
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
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.

