arena
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.
How do I install this agent skill?
npx skills add https://github.com/painhardcore/pstack --skill arenaIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill coordinates a parallel execution and synthesis workflow using subagents. It is safe for its intended purpose but carries a low risk inherent to processing untrusted output from multiple sub-tasks.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Arena
Open a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.
Phase A: Frame
Every candidate gets the same prompt, so the prompt is the contract.
- State the artifact each candidate is producing.
- Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on this task. Concrete:
Adds a --dry-run flag that skips writes. Vague:code is correct. It is the picker's tool in Phase D. Candidates only see the task. - Pick the runners. Use the parent model by default. When the host supports model selection, prefer different available model families for judgment-heavy work. If the host rejects a requested model, run that seat on the parent model or drop it, and say so. Keep at least two runners. Spawn more runners when the arena covers multiple design directions. Use the same model N times when the work is generation-bound rather than judgment-sensitive. Pick each subagent's reasoning level for the job, per the Subagents section of the poteto-mode skill.
- Give each candidate its own output location (a git worktree where possible, otherwise
/tmp/arena-<slug>/candidate-<n>/), per the separate-before-serializing-shared-state principle skill.
Phase B: Fan out
Use the host's native subagent tool to start all N candidates concurrently, in the background when the host supports it. Give each candidate the task, the shared grounding path, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected. If subagents are unavailable or forbidden, produce the candidates sequentially in the same isolated locations before judging them.
If a candidate produces no output, proceed with N-1 and note the dropout.
Phase C: Cross-judge
After all Phase B candidates complete, use one read-only judge subagent. The judge never comes from the parent model's family, so its bias differs from yours. When the host supports model selection, pick an available model from another family. A model that inherits the parent never judges. If no model from another family can run, or the host cannot select models, skip the judge, pick the base alone in Phase D, and say so. If you do not know the parent's model, say that the family check did not run. The judge sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Don't spawn it while candidates are still writing.
Phase D: Pick a base
Read every candidate end to end before picking. Score each against the rubric criterion by criterion, not on holistic feel, and compare with the cross-judge when Phase C ran one. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.
Pick the base a future maintainer can extend most easily without breaking invariants. When two feel tied, prefer the cleaner boundary or smaller API, per the Laziness Protocol.
Phase E: Graft
Walk each losing candidate once more for what is worth porting into the base, usually one or two things per candidate, not most of it. Fold each graft in by hand, per the redesign-from-first-principles principle skill, so the result stays coherent under one mental model. Don't paste mechanically.
If the candidates converge on one shape, that is strong agreement. Note it and ship the consensus shape. No graft is needed. If they wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.
Phase F: Verify
Verify the synthesized artifact like any other output, per the prove-it-works principle skill. If verification finds a problem the arena missed, either Phase A was wrong (re-frame and re-run) or a candidate caught it and you missed the graft (go back to Phase E). Don't paper over it.
Outputs
One synthesized artifact, with a short synthesis note alongside naming the base and why, the cross-judge's verdict or that Phase C skipped the judge, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/painhardcore/pstack/arena">View arena on skillZs</a>