AGENT SKILL

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.

License 许可
MIT
所属仓库
casualjim/pi-mimir
最近更新
2026-11-10
Stars
★ 16
Forks
9

01 前言 Front Matter

name
arena
description
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.
disable-model-invocation
true

03 SKILL.md 正文

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.

  1. State the artifact each candidate is producing.
  2. Derive the rubric. State what success looks like for this task, then turn it into 3-6 concrete gradeable criteria. The rubric is the picker's tool in Phase D. Candidates only see the task.
  3. Pick the runners. Use your configured arena-runners models (default inherit-parent each) and the thinking level the work needs per the Subagents section of the poteto-mode skill. If a configured entry fails to resolve, run that seat on its family's default and say so. Families go by prefix: claude-*, gpt-*, and grok-*, with cursor-grok-* and composer-* counting as grok-*. If the family has no default that resolves, drop the seat and say so. If dropped seats leave fewer than two runners, add runners until there are two, or one when the pool has one entry. Run each added runner on a remaining runner's model, or the parent model when none remain, and say so. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.
  4. 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

Spawn all N subagents in one message with the parent waiting for and aggregating the results, each with the task, the path to the shared grounding, its own output path, and instructions to produce both the artifact and a short rationale naming the alternatives it considered and what it rejected.

If a candidate produces no output, proceed with N-1 and note the dropout.

Phase C: Cross-judge

After all Phase B candidates complete, choose one model from your configured cross-judge pool (default inherit-parent each). The judge is never from the parent's family, as Phase A step 3 defines families, so an inherit-parent entry never judges. Try the pool's entries from another family, in pool order. If no entry from another family runs, skip the judge, pick the base alone in Phase D, and say so. Spawn one readonly judge subagent on the chosen model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with the parent's reading in Phase D, not with the candidates themselves. Don't spawn the judge 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.

04 同仓库更多 Skills