@huanghai-lab/dsh-custom-instructions
DSH Web manager for global AGENTS.md with Markdown preview, reusable templates, version history, import rollback, and revision-conflict protection.
11 results
DSH Web manager for global AGENTS.md with Markdown preview, reusable templates, version history, import rollback, and revision-conflict protection.
DeepSeek Harness 输入栏提示词优化插件:6 种策略 × 3 种语言与自定义指令重写草稿,可选携带聊天上下文(含压缩摘要)、目标与任务清单,结果确认弹窗、最近 5 次历史与三级设置持久化。Input-bar prompt optimizer for DeepSeek Harness: rewrites drafts with 6 strategies × 3 languages plus custom instructions, optional chat context (with compaction summary), goal and todo injection, a confirm dialog, last-5 history and three-tier settings persistence.
Command history for the DeepSeek Harness web GUI composer: press Up/Down to cycle through your previously sent instructions, and reach the oldest draft again at the end of the history. 在 DSH Web 输入框中用上下方向键浏览此前发送的指令,回到历史末尾时恢复切换前的草稿。
Sidebar skill hub for DeepSeek Harness Web GUI — shows the current/used skills of the active session and enables one or several skills at once by injecting their instructions into the conversation. 🌟 侧边栏技能中心:显示当前会话正在使用/已使用的技能,并可一次启用一个或数个技能(注入技能说明,整轮对话可用)。
Inject a configurable dsh-ui status card instruction before every DSH agent reply
Agent instruction manager for DeepSeek Harness: edit, refine, and template the AGENTS.md files the harness actually reads — the user-global ~/.dsh/AGENTS.md and per-workspace AGENTS.md — from a sidebar panel.
Declutter the DeepSeek Harness chat: hide agent execution-log rows (Think / context injection / tool calls), tighten message spacing and font sizes, wrap messages in rounded-corner bubbles, and inject an editable "reply concisely" instruction into the system prompt.
Auto-fold context/system messages in DSH conversation — hide the large system prompt / instructions by default, click to expand.
Floating DualSense controller overlay for the DeepSeek Harness web surface: lights up pressed buttons and fires bound vibe-coding instructions.
统一管理 DSH 规则:编辑全局规则 ~/.dsh/AGENTS.md、编辑项目 AGENTS.md、LLM 自动拆分项目规则为分层 AGENTS.md + skills。合并自 dsh-global-rules 与 dsh-rule-splitter。
User-only instruction memory for DSH: long-term instructions maintained in the settings UI and auto-injected into every conversation — the model has no write access. 指令记忆:只由用户在设置页维护的长期指令,自动注入此后每轮对话;模型没有任何写入口。