read-eval
Phase 2 solver optimization only: read the evaluator first, infer what it rewards, then make targeted solver edits.
- License 许可
- Apache-2.0
- 最近更新
- 2026-08-20
- Stars
- ★ 66
- Forks
- 9
01 前言 Front Matter
- name
- read-eval
- description
- Phase 2 solver optimization only: read the evaluator first, infer what it rewards, then make targeted solver edits.
03 SKILL.md 正文
Use this skill only for Phase 2 solver and guidance optimization.
- Read
solver/evaluate.pycarefully before proposing edits. - Infer what the evaluator is rewarding, penalizing, or constraining.
- Identify the smallest high-leverage changes to
solver/candidate.pyand any supporting guidance notes. - Prefer concrete task-specific improvements over process commentary.
- Keep edits local and score-oriented.
04 同仓库更多 Skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
theorem-search
Use TheoremSearch to find, verify, and cite mathematical theorem statements, named results, proof routes, and literature dependencies.
supervise-run
Use when monitoring a running Eve experiment and recovering from problems while it runs
run-math-proof-quickstart
Use when running a Math Proof quickstart from a user-provided problem: create a local task copy, launch a real EvE attempt, supervise it, and report proof/evaluation results.
run-circle-packing-smoke
Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.
resume-run
Use when continuing an interrupted or paused Eve run from where it stopped (same run, same id), optionally after editing the experiment