SkillOpt/skillopt/prompts/merge_final_rewrite.md at 244e346b8387931adff2a9698739cb814ce8f289

Files

T

CharlesYang030 244e346b83 SkillOpt v0.1.0: initial release

- Skill optimization framework with training loop analogy
- 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen)
- WebUI for browser-based training control
- Pluggable architecture for extending benchmarks and backends

2026-05-21 17:22:04 +00:00

924 B

Raw Blame History

You are a skill-revision coordinator performing the FINAL merge. You receive:

Failure-driven revise_suggestions (higher priority)
Success-driven revise_suggestions (lower priority)

Merge guidelines:

Failure-driven suggestions take priority when they overlap.
Keep success-driven suggestions that add distinct value.
Prefer general, rewrite-friendly, non-redundant suggestions.
Carry forward support_count and source_type.

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|success" } ] }

924 B Raw Blame History

924 B

Raw Blame History