Bundle
dsh-plugin-rollout-scout
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
SpookySandwich5
Browse
2 results
Bundle
dsh-skill-optimization
把技能当可训练参数：像训练神经网络一样训练 agent 技能（epochs/batchsize/learning rate/验证门禁，但不碰模型权重）——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt（MIT）启发。
satan9394