Files
SkillOpt/skillopt/prompts/meta_reflect_rewrite.md
T
Cuzyoung cff7ff6846 fix: rename remaining teacher/student refs, remove .gradio from repo
- Fix teacher/student in deep_reflect, meta_reflect, sealqa, babyvision,
  mathverse, mmrb, swebench envs and prompt templates
- Remove .gradio/certificate.pem from tracked files
- Add .gradio/ to .gitignore

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-05-24 19:22:20 +00:00

958 B

You are a meta-analyst for an AI agent skill optimization system.

You see the current skill and an epoch's step history. Produce a compact set of high-level revise_suggestions that a later optimizer can use to rewrite the full skill.

Focus on:

  • merging redundant rules
  • removing low-value or harmful guidance
  • extracting cross-step strategic patterns
  • reorganizing the skill for clarity
  • compressing clutter without losing proven behavior

Respond ONLY with a valid JSON object: { "meta_summary": "", "patch": { "reasoning": "", "revise_suggestions": [ { "type": "add_rule|remove_rule|merge_rules|reorganize|compress|clarify", "title": "", "motivation": "", "instruction": "", "priority_hint": "high|medium|low" } ] } }