Change management, SkillOpt optimization, and evidence-gated evals for agent skills.

Darwin Skill 2.0: autonomous evaluator and optimizer for Agent SKILL.md workflows

Microsoft SkillOpt-Sleep integration for DeepSeek Harness (dsh): nightly sleep cycle - harvest sessions, replay recurring tasks, consolidate validated skills behind a held-out gate. ?? DSH ? SkillOpt ??

Bilingual SkillOpt-inspired Codex skill writer for SKILL.md creation, validation gates, bounded edits, and agent skill optimization

A Codex skill that researches and learns unfamiliar domains before building.

AI artifact lifecycle management for prompts and agent skills: optimize, evaluate, version, trace, and promote changes from raw data and policies.

病理影像異常區域定位與結構化分析系統 結合 YOLO 異常區域定位、教師模型引導的技能／提示詞最佳化，以及學生多模態模型的結構化推論。系統先在病理影像中找出候選異常區域，再由使用者選擇真正要分析的 ROI，最後以固定 JSON Schema 產生逐區域、可追溯且可保存的形態學報告

Obsidian + Hermes agent intelligence economy kit: clippings harvest, skill optimization, token efficiency, verification, loop scoring.

A Claude Code skill that researches and learns unfamiliar domains before implementation.

Systematic methodology for optimizing agent skills using deep-learning-style approach. Based on arXiv:2605.23904

Codex plugin for freebuff2api with a SkillOpt self-improvement loop

Self-improving memory for coding agents.

Train AI agent skills like model parameters. Offline text-space optimizer implementing SkillOpt (arXiv:2605.23904v2) for Hermes Agent. Bounded edits, validation gating, zero inference overhead.

EvoSkillOpt — When SkillOpt Meets Evolutionary Game Theory (EGT) and Reinforcement Learning (GRPO)

Train agent skills like neural networks — with epochs, batch size, learning rates, and validation gates — without touching model weights. Based on Microsoft SkillOpt.

Optimize local AI agent workflows and system prompts using an iterative evaluate-and-refine process while keeping your model weights frozen.