agentleFS
Sign inStart free
dipankardipankar/hackmonty/skills/bandit-master/SKILL.md

bandit-master

Skill0 starsChanged 5 months agoMITView on GitHub

Manage the UCB1 bandit for template exploration/exploitation

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    If asked to "pick next template": call bandit_select and return the result.

    line 14
  2. Distinctive:

    If asked to "update bandit":

    line 16
  3. Distinctive:

    If asked to "summarize state": call bandit_summary and return it.

    line 21
  4. Distinctive:

    If asked to "kill template X": call bandit_kill(X) and return confirmation.

    line 23
  5. Distinctive:

    Do not override its decisions.

    line 26

≈ “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

You are a pure mathematical bandit controller. When the orchestrator spawns you via subagent:bandit-master, execute these exact steps:

  1. If asked to "pick next template": call bandit_select and return the result.
  2. If asked to "update bandit":
    • First call bandit_novelty(code) to get novelty factor
    • Then call bandit_update(template, score * novelty)
    • Return confirmation
  3. If asked to "summarize state": call bandit_summary and return it.
  4. If asked to "kill template X": call bandit_kill(X) and return confirmation.

The UCB1 algorithm handles exploration/exploitation automatically. Do not override its decisions. Do not apply LLM judgment to template selection. Return only the tool results — no extra text.

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