arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /pstack: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
- 最近更新
- 2026-10-14
- Stars
- ★ 0
- Forks
- 0
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 /pstack:arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
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.
- State the artifact each candidate is producing.
- Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on this task. It is the picker's tool in Phase D. Candidates only see the task.
- Pick the runners. Use the
arena runnersline inpstack-models.md. If the file or that line is missing, default to one each onopus xhighandsonnet high. Anautoorinherit-parententry in this line or the cross-judge line means the parent model, so omitmodelandeffortfor it. Pass each other entry's model and effort as the Agent tool'smodelandeffort. If the Agent tool rejects a configured entry, run that seat on its tier's default and say so. Tiers go by model:opus,sonnet,haiku,fable. With no tier match, useopus xhigh. 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. - 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 (${CLAUDE_PLUGIN_ROOT}/skills/principle-separate-before-serializing-shared-state/SKILL.md).
Phase B: Fan out
Spawn all N subagents in one message with run_in_background: true, and isolation: "worktree" for a candidate that writes in the repository, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected.
If a candidate produces no output, proceed with N-1 and note the dropout.
Phase C: Cross-judge
After all Phase B candidates complete, choose one model from the arena cross-judge pool line in pstack-models.md. If the file or that line is missing, choose from opus xhigh and sonnet xhigh. Prefer a different model tier from the parent's. Spawn one pstack:readonly-agent judge on that model. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Don't spawn it while candidates are still writing.
Phase D: Pick a base
Read every candidate end to end before picking. Score each against the rubric criterion by criterion, not on holistic feel, and compare with the cross-judge. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.
Pick the base a future maintainer can extend most easily without breaking invariants. When two feel tied, prefer the cleaner boundary or smaller API, per the Laziness Protocol.
Phase E: Graft
Walk each losing candidate once more for what is worth porting into the base, usually one or two things per candidate, not most of it. Fold each graft in by hand, per the redesign-from-first-principles principle (${CLAUDE_PLUGIN_ROOT}/skills/principle-redesign-from-first-principles/SKILL.md), 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 (${CLAUDE_PLUGIN_ROOT}/skills/principle-prove-it-works/SKILL.md). 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, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.
Model configuration. Read the project file .claude/pstack-models.md when it exists, otherwise the user file ~/.claude/pstack-models.md. The project file replaces the user file, with no per-line merge. A line is <role>: <model> <effort>, and a panel role lists comma-separated entries. Pass the model and the effort as the Agent tool's separate model and effort parameters.
04 同仓库更多 Skills
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.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.