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
am-will/gooey-pi
最近更新
2026-10-25
Stars
★ 974
Forks
87

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

Fan out N parallel attempts at the same task. Read every candidate end to end. Pick the strongest as the base. Graft the best ideas from the others into it. Verify the synthesized result.

Start

Open a todolist with one entry per phase before launching anything. The arena runs autonomously and the list keeps phases from silently disappearing.

  1. Frame
  2. Fan out
  3. Cross-judge
  4. Pick
  5. Graft
  6. Verify

Phase A: Frame

The N candidates will receive the same prompt, so the prompt is the contract. Get it right before spawning anything.

  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. Concrete: Adds a --dry-run flag that skips writes. Vague: code is correct. The rubric is the picker's tool in Phase D; candidates only see the task.
  3. Pick a task-appropriate number of independent runners, normally two to four. Vary the design constraints or review focus when useful. Every runner inherits the current session model unless the human explicitly chooses an override for this invocation.
  4. Assign output paths. Each candidate writes to its own location (a git worktree where possible, otherwise /tmp/arena-<slug>/candidate-<n>/). N candidates writing to the same path is shared mutable state and fails the the separate-before-serializing-shared-state principle skill test.

Phase B: Fan out

Spawn all N subagents in one message with run_in_background: true, 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.

The rationale is mandatory. Without it, the parent cannot tell whether a candidate's structure is principled or accidental, which makes Phase E grafting unreliable. Each rationale names the alternatives the candidate considered and what it rejected.

If a candidate fails to produce output, proceed with N-1 and note the dropout in the synthesis record.

Phase C: Cross-judge

After all Phase B candidates complete, spawn one readonly judge subagent, inheriting the current session model by omitting model. It sees the rubric and 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 while candidates are still writing: a judge reading partial outputs can mistake unfinished work for a dropout.

Phase D: Pick a base

Read every candidate end to end before picking. Skimming N candidates surfaces only the candidate whose surface looks most familiar.

Score each candidate against the rubric criterion by criterion, not on holistic feel. Compare against the cross-judge. 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 on which candidate a future maintainer can extend most easily without breaking invariants. Prefer the cleaner boundary or smaller surface area when two feel tied, per the Laziness Protocol.

Record the pick and the reason in a short synthesis note alongside the base artifact, including the cross-judge's verdict.

Phase E: Graft

Walk each losing candidate once more and identify what is worth porting into the base. The signal is 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. Don't paste mechanically. The result has to remain coherent under one mental model.

Record what was grafted, from which candidate, and what was rejected and why. The rejection notes are the highest-signal part of the record. Future readers learn from what you considered and dropped, not just what you kept.

When N candidates converge on the same shape, that is a strong agreement signal. Note the convergence in the record and ship the consensus shape. No graft is needed. When N candidates wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.

Phase F: Verify

The synthesized artifact has to hold up under the same scrutiny as any other output, per the prove-it-works principle skill. The arena does not earn you a pass.

If verification surfaces a problem the arena did not catch, either Phase A was wrong (re-frame and re-run) or one candidate caught it and you missed the graft (go back to Phase E). Don't paper over.

Outputs

One synthesized artifact. One short synthesis note alongside, naming the base, the grafts (with source candidate), the rejections, the dropouts if any, and the verification result.

04 同仓库更多 Skills

am-will
am-will/gooey-pi

prime-work-schedules

Create, inspect, edit, pause, resume, run, and delete durable GooeyPi scheduled tasks. Use when the user asks to schedule recurring or one-time work in the current project or thread. Use rlm-heartbeat instead for temporary internal polling while actively working.

★ 974
am-will
am-will/gooey-pi

prime-work-browser

Drive the GooeyPi in-app browser for this thread with the browser_* tools - open tabs, navigate, read pages, click, type, scroll, screenshot, and extract data. Use when the user asks to open, test, inspect, or interact with a website or a local dev server inside GooeyPi.

★ 974
am-will
am-will/gooey-pi

gooeypi-computer-use

Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.

★ 974
am-will
am-will/gooey-pi

verify-gooeypi

Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a GooeyPi UI change or confirming the app still works end to end.

★ 974
am-will
am-will/gooey-pi

review-pr-viability

Review a pull request or issue for value, implementation quality, maintainability, regression risk, and reliance on upstream changes.

★ 974
am-will
am-will/gooey-pi

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 974