dsh-quality-review
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
控制已登录的网页版 ChatGPT 生成图片并下载到本地 — DSH bundle 插件。
插件工坊:在任意工作区按 dph 格式快速脚手架 DSH 本地插件,并维护踩坑经验库持续修正开发 — DSH bundle。
飞书机器人 → DSH 会话桥:在指定工作区开真会话,用 DSH 现有模型+插件执行任务并回传结论 — DSH bundle。
No description
飞书多助手机器人控制台:开启/关闭/重连守护进程、状态与最近动态、直达任务工作区 — DSH bundle。
系统理解简报工作流:解析 PRD/PDF、分批追问澄清目标系统并沉淀 BRIEF.md,最终打包可上传交付物 — DSH bundle。
Force the DeepSeek Harness model to reply in a chosen language (default Simplified Chinese), switchable anytime via tools. 强制大模型使用指定语言回复。
Poll Feishu (Lark) chats, extract candidate tasks, two-way sync with the task-board plugin, with a floating browser panel — DeepSeek Harness bundle. 轮询飞书会话提取任务。