From the author
Several subagents build the same artifact from one brief in isolation, a read-only judge scores them, and you pick a base and graft in the best parts of the rest. Use for "arena this", "competing attempts", "second opinion on this approach".
Install
npx skills add hashgraph-online/awesome-codex-plugins --skill arena -a claude-code
Installs to .claude/skills/arena/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 88
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.Testing★ 996
- roundtablett-a1i/matt-skills-with-to-goalConvene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review, then a chaired verdict reporting consensus and dissent.Engineering★ 191
- interrogatebacknotprop/pstackUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.Testing★ 3.2K
- parallelhashgraph-online/awesome-codex-pluginsBuild a planned game with several agents at once — game logic and netcode, levels, art, sound, the landing page — each in its own folders, then one merge, a two-browser check, a playtest and a blind review. Use only when parallel work is requested and the host supports it. Use after the plan step, or when someone asks to "build it in parallel", "use more agents", "split the work" or "go faster".Design★ 1.5K
- orchestrationAThevon/genjutsuRunning a team of subagents on one design build: clone briefs, disjoint file ownership, isolated builds, the evidence packet, review lenses, the fix plan, verdicts, cold eyes and the stop rule, with the workflow templates bunshin runs.Design★ 708
- agni-kaitmcfarlane/team-avatarZuko's Agni Kai for bakeoffs. The formal firebending duel, where competing implementations fight under the same rules and a judge declares the winner. Use for arena, /arena, "arena this", "throw it in the arena", "bakeoff", or when one attempt at a nontrivial design or artifact would lock in the wrong shape. Spawns N parallel candidates at the same task, picks a base with a cross-judge, and grafts the strongest parts of the losers into it.Design★ 111
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in