skill-optimizer
能把历史修正视为训练信号，自动提出经验证的技能改动。
会自动修改技能 markdown，可能引入错误或不期望的变更。
把用户纠错作为轨迹，用 LLM 优化并验证后自动打补丁技能文件。
把用户的纠错记录当作训练轨迹，用 LLM 自动提出并验证对 SKILL.md 的补丁，像给技能做“离线优化”。适合某个 skill 积累了很多 learn-rule、想让技能自己变得更聪明而不是一直堆规则时用。特别在于不改模型参数，只改技能文档，所有候选补丁必须通过基于用户历史纠错的验证集才会生效。
▸ 展开 SKILL.md 英文原文
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
帮我安装这个 skill：https://raw.githubusercontent.com/rohitg00/pro-workflow/main/skills/skill-optimizer/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/rohitg00/pro-workflow/main/skills/skill-optimizer/SKILL.md"# Skill Optimizer Train an existing SKILL.md the way a deep-learning optimizer trains weights: via rollouts, gradient-like reflections, validation-gated acceptance. No model retraining; only the skill markdown changes. ## When to use Use this skill when: - A pro-workflow skill has accumulated 8+ learn-rule rows for it - The user reports the skill is "getting bloated" or "rules keep being repeated" - The user wants offline, budget-capped improvement over multiple sessions Do not use when: - Skill has fewer than 8 trajectories (nothing to learn from) - The user wants real-time edits (this is offline, single-shot) - No `ANTHROPIC_API_KEY` (or equivalent provider key) is available ## Archit