How do I install the Recursive Arena skill?

Run npx skillmds@latest add lollipopkit/recursive-arena in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Recursive Arena safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Recursive Arena?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Recursive Arena free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Recursive Arena?

lollipopkit (@lollipopkit) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Recursive Arena by lollipopkit — Agent Skill

Name: Recursive Arena
Author: lollipopkit

Recursive Arena

Combine recursive outer-loop refinement with multi-model arena generation each round. Use when users request recursive arena, multi-LLM consensus with iterative refinement, or recursive plus model-battle workflows.

lollipopkit f2f30d2 2 files · 7.0 KB Updated Sep 17, 2026

File contents

Recursive-Arena

Use the orchestrator: python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py".

How to run

python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py" \
  --prompt "<task>" --iters 4 --arena-iters 3 --json

Common flags: --max-judges, --temperature, --max-tokens, --timeout.

Iteration Loop

For each outer iteration:

Run multi-model to generate a best candidate.
Use judge summaries as critique input.
Refine the prompt with the current best answer.
Keep the global best by score and continue.

Configuration

Reuses multi-model .env configuration:

ARENA_MODELS
ARENA_OPENAI_BASE_URL or ARENA_PROVIDER_<NAME>_BASE_URL
Optional API keys (ARENA_OPENAI_API_KEY, ARENA_PROVIDER_<NAME>_API_KEY)

Optional orchestration env:

RLM_ARENA_ARENA_ITERS default inner arena iterations
RLM_ARENA_MAX_JUDGES default judge cap

Output and Safety

Final answer is the best outer-iteration result.
When useful, show a compact evolution table:
- iteration
- winner_model_id (numeric ID only)
- avg_judge_score
- refinement_applied
Never disclose provider/model names.
Never print secrets from .env.

Frequently asked questions