AGENT SKILL

arena

Use when asked to compare parallel candidate implementations or designs and combine the strongest results.

License 许可
MIT
所属仓库
gutierrezje/jstack
最近更新
2026-11-11
Stars
★ 0
Forks
0

01 前言 Front Matter

name
arena
description
Use when asked to compare parallel candidate implementations or designs and combine the strongest results.
disable-model-invocation
true

02 资源文件 1

03 SKILL.md 正文

Arena

Produce competing attempts, choose a base, and graft only proven improvements.

Read the global routing table before dispatching. Inspect the current subagent tool's supported model and effort overrides; never silently inherit the parent after a pinned-model rejection.

  1. Freeze one shared brief, grounding files, output contract, and judging rubric.
  2. Select Arena design runners for design alternatives, or implementation runners when candidates must produce working code. Use the user's N or the selected route's default candidate count. Keep candidate work isolated or read-only.
  3. Dispatch candidates without showing them one another's work. Require an artifact and a short rationale naming alternatives considered and rejected.
  4. Verify each artifact with the same checks. Reject any candidate that fails the hard gates.
  5. Judge evidence blind to model prestige. Select one base and list exact grafts from other candidates.
  6. Apply grafts one at a time and rerun the relevant check after each.
  7. Report the candidates, scores, selected base and why, accepted grafts with their source candidates, rejected ideas, any dropouts or convergence, and final verification.

Completion means one verified artifact remains and every graft has an observed benefit.

04 同仓库更多 Skills