Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

🌹安装即自带mattpocock/skills v1.3.1的27个工程与效率技能，无需手动装技能。520亿token打造本插件，在原始技能之上提供10倍的开发效率，也能帮助新手更快上手该技能套件。支持 GitHub 与 GitLab 的 issue；本地 Markdown 为预览版。感谢您的使用和支持💗