agentleFS
Sign inStart free
fullerzzfullerzz/agent-skills/skills/arena/SKILL.md

arena

Skill2 starsChanged 28 days agoMITView on GitHub

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

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 64 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:

    Wait for terminal results and read every artifact.

    line 13
  2. Distinctive:

    Verify the synthesis. Record base, grafts, rejections, reviewer identities, gaps, and evidence.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 64 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

Arena

Produce independent candidates, choose a base, adapt useful ideas, and verify. Use the native contract.

  1. Define the artifact and 3-6 success criteria. Choose 2-3 candidates through the selected execution method unless the user specifies another useful count. Follow its model semantics; report actual identities if exposed.
  2. Give each the same task/grounding, exclusive output or worktree, and artifact plus rationale. Queue within host limits.
  3. Wait for terminal results and read every artifact. A dropout remains a gap.
  4. A fresh read-only judge scores completed candidates. It must not be a writer. If unavailable, label the judgment parent-only.
  5. Pick by criteria and reconcile disagreements. Adapt ideas coherently; convergence needs no forced graft.
  6. Verify the synthesis. Record base, grafts, rejections, reviewer identities, gaps, and evidence.

Same-model independent runs are useful but do not satisfy cross-provider comparison. A requested cross-provider comparison requires verified provider identities and available execution capabilities; report missing coverage.

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.

Reviews can't be read right now.

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