CoriChui/bakeoff
10 stars · Last commit 2026-07-09
Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.
README preview
# bakeoff **Turn one hard "which should I do?" into a judged tournament — and get back a defensible winner.** <p align="center"> <img src="demo/bakeoff.gif" alt="bakeoff deriving roles, auto-building a rubric, judging candidates, and ranking a winner" width="820"> </p> <p align="center"> <sub>Terminal summary from a real run — verdict and scores are from the saved <a href="examples/email-deadline-generation.md">report</a>, re-rendered at a readable pace.</sub> </p> `bakeoff` is a [Claude Code](https://docs.claude.com/en/docs/claude-code) skill. Hand it a decision and it **generates diverse candidate solutions**, **auto-derives the criteria that matter for _that_ specific problem** (so you don't have to know what to score on), **judges every candidate with independent scorers**, and returns the **winner plus a ranked shortlist** — with the reason each one won or lost. You just type your request; it infers the shape (a comparison, an improvement, an idea, a *"what if we do X"*, a problem, or a scoping call), the depth, and the rubric — **no flags**. The hard part of any comparison isn't the scoring — it's knowing *what to evaluate*. bakeoff derives the rubric for you. Here's the run shown in the GIF above: ``` /bakeoff "8h/24h email deadline: Batches vs keep-sync vs merge?" Roles → status-quo · cost-first · dedup · max-savings Rubric → Deadline-fit 28 · COGS 24 · Personalization 16 ·