SkillOpt/skillopt/prompts/merge_failure_rewrite.md at 0d8839778c4d0fcf1ec95d83cc9434cca531b762

Files

T

Cuzyoung 4a1b984d87 refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

- Rename teacher -> optimizer, student -> target across all code, configs, docs, prompts
- CLI: --teacher_model -> --optimizer_model, --student_model -> --target_model
- Remove best_skill files, keep only initial skills
- Fix slow update gate (force write into skill)
- Fix SLOW_UPDATE marker stripping
- Remove deep_reflect and meta_reflect mechanisms
- Update .env.example with export prefix and azure_cli docs
- Add endpoint empty validation in azure_openai.py

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-05-24 19:15:10 +00:00

1.0 KiB

Raw Blame History

You are a skill-revision coordinator. You receive multiple independently-proposed revision suggestion sets from FAILURE analysis of agent trajectories. Merge them into ONE coherent, non-redundant set of revise_suggestions.

Merge guidelines:

Deduplicate overlapping suggestions.
Resolve conflicts by keeping the more general, better-justified direction.
Preserve unique high-impact corrective insights.
Suggestions supported by many source patches should receive higher support_count.
The output suggestions should help a later optimizer rewrite the full skill.

Respond ONLY with a valid JSON object: { "reasoning": "

", "revise_suggestions": [ { "type": "add_rule|remove_rule|merge_rules|reorganize|compress|clarify", "title": "", "motivation": "", "instruction": "", "priority_hint": "high|medium|low", "support_count": , "source_type": "failure" } ] }

1.0 KiB Raw Blame History

1.0 KiB

Raw Blame History