agentleFS
Sign inStart free
WaichLWaichL/brainrot-skill/SKILL.md

brainrot

Skill0 starsChanged 20 days agoMITView on GitHub

Turn the last AI reply into a vertical brainrot reel (TTS voice, big centered captions, Minecraft parkour or Subway Surfers background). Use when the user types /brainrot.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. nicknisi/skills★ 5same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a spoken script. Default ~40s (about 120 words).

    line 9
  2. Distinctive:

    Every technical word gets a plain explanation the first time, ideally an everyday comparison ("cwnd, basically how many packets you send …

    line 13
  3. Distinctive:

    Keep the core point and the facts that matter.

    line 14
  4. Very specific:

    If it says there are no background clips, tell the user to run ~/.claude/skills/brainrot/setup.sh once.

    line 27

≈ “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

Turn the previous assistant reply (or whatever the user names) into a short reel.

  1. Write a spoken script. Default ~40s (about 120 words); if a number is given, aim for 3 words per second.
    • Open with a hook line ("Okay so here's the deal.", "Wait, this actually matters.").
    • Then set the scene in 1–2 lines: what the question was and why anyone cares, in everyday words. Assume the viewer knows nothing about the topic.
    • Pick at most 3 points. Say how many up front ("3 things."), then announce every switch out loud: "First...", "Second...", "Last one...", "Okay, but here's the catch...". Never jump to a new idea without a signpost.
    • Every technical word gets a plain explanation the first time, ideally an everyday comparison ("cwnd, basically how many packets you send before waiting for a reply"). If it can't be explained in one line, drop it.
    • Keep the core point and the facts that matter. Drop code, paths, tables, caveats.
    • Plain spoken English, short sentences. No markdown, emoji, URLs, or symbols. Write numbers as digits (2, 64, 30%), never as words.
    • End with a one-line takeaway.
  2. Render it with one Bash call (pass --bg parkour or --bg subway if the user asked for one):
uv run --quiet ~/.claude/skills/brainrot/brainrot.py <<'EOF'
<script>
EOF

It prints only the mp4 path and opens the video. Reply with that path and nothing else. Don't paste the script back.

If it says there are no background clips, tell the user to run ~/.claude/skills/brainrot/setup.sh once.

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