craft-arena
Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts. Use when one attempt would lock in the wrong shape.
- License 许可
- MIT
- 最近更新
- 2026-11-05
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- craft-arena
- description
- Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts. Use when one attempt would lock in the wrong shape.
02 资源文件 2
- 参考文档agents/openai.yaml82 B
- 参考文档CREDITS.md838 B
03 SKILL.md 正文
Arena
Run N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use when one attempt at a non-trivial artifact would lock in the wrong shape. Companion to craft-swarm (coverage and races) and review-adversary (adversarial review of one change).
Open a todo with one entry per phase before launching anything.
A. Frame
Every candidate gets the same prompt, so the prompt is the contract: the artifact each produces, and a rubric of 3 to 6 concrete gradeable criteria for this task (the picker's tool; candidates only see the task). Runners follow the repo model map; keep at least two runners, dropping to one only when the map lists one. Use the same model N times when the work is generation-bound rather than judgment-sensitive, more runners when covering multiple design directions. A rejected slug falls back to the closest valid one in the harness error message, else the map's default or your own model; a dropped seat is refilled on a remaining runner's model, else your own model. Either way, say so. Each candidate gets its own output location (a git worktree where possible, otherwise a separate directory) per rule 15.
B. Fan out
Spawn all N in one round, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact plus a short rationale naming the alternatives it considered and rejected. A candidate with no output means proceeding with N-1, dropout noted.
C. Cross-judge
After all candidates complete, one readonly judge (a different model family, from the map's judge entry, never your own model when it is an auto or inherit-parent entry) sees the rubric and the candidates by path label, scores each rubric criterion per candidate, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Never judge while candidates are still writing. When no other-family model runs, pick the base alone and say Phase C skipped the judge.
D. Pick a base
Read every candidate end to end before picking, score criterion by criterion against the rubric (not holistic feel), and compare with the cross-judge when Phase C ran one. Agreement confirms the pick; disagreement means bias or an ambiguous rubric, so read both rationales before deciding. Pick the base a future maintainer extends most easily without breaking invariants; ties break toward the cleaner boundary or smaller API (rule 1).
E. Graft
Walk each loser once more for the one or two things worth porting (not most of it), and fold each in by hand (rule 17) so the result stays coherent under one mental model. Convergence on one shape means shipping the consensus, no graft needed. Wild divergence means Phase A was under-specified: reframe and re-run, never average the divergence.
F. Verify
Verify the synthesized artifact like any other output (rule 3). A problem the arena missed means Phase A was wrong (re-run) or a graft was missed (back to Phase E); never paper over it.
Outputs
One synthesized artifact with a short note: the base and why, the cross-judge verdict (or that Phase C skipped the judge), each graft with its source, what was rejected and why, convergence or dropouts, and the verification result.
04 同仓库更多 Skills
whips
Route any non-trivial task through one entry: match a playbook, drive HIT skills plus subagents, open a reviewed ready PR with ship-pr-shaped evidence.
verify-upkeep
Periodic upkeep for a project's verification skill: source wave plus live pass per feature, at most one PR of proven corrections. Use to audit the verify skill.
verify-statechart
Check a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart. The report gives the shortest path to each state that breaks a rule. Use to show a bug as a path through states.
verify-new
Generate a project-local skill that drives the app like a user (launch, doctor, drive, evidence, feature map), proven once. Use when a project has no scripted proof.
ship-triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, interview if needed, and write agent-ready briefs.
ship-runner
Run ready-for-agent issue queues on any schedule through /whips intake, one fresh worktree each, landing per risk tier, with the agent and model you pick at setup.