Pinned Loading
-
microsoft/SkillOpt
microsoft/SkillOpt PublicSkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
-
dsh-kubectl
dsh-kubectl PublicKubernetes (kubectl) 的 DeepSeek Harness 插件 — 查资源/日志/describe/端口转发/执行,JSON 结构化输出
-
dsh-token-caveman
dsh-token-caveman PublicTerse prose — fewer tokens on the way out. A DeepSeek Harness skill.
-
dsh-token-diet
dsh-token-diet PublicDSH token-saving toolkit: proactively slim large text/JSON/CSV before they enter context (diet_text / diet_json / diet_csv / diet_estimate). Zero-dependency pure functions.
TypeScript 2
-
dsh-skillopt
dsh-skillopt PublicNightly self-improvement for your DeepSeek Harness agent: harvest past sessions, replay recurring tasks, and consolidate validated skills behind a held-out gate. Brings microsoft/SkillOpt's SkillOp…
JavaScript 3
If the problem persists, check the GitHub status page or contact support.


