dknowc-dsh
Trusted office suite for government/enterprise work by Beijing Caizhi Technology (深知可信智能): three skills — trusted consulting (policy/regulation Q&A with citation markers + provenance HTML), trusted search (authoritative policy/standard retrieval with traceable HTML + clean Markdown), and official-document writing (draft/rewrite/Word/red-head delivery); all interfaces go through the dknowc trusted workbench MCP (Bearer auth), products land in the session workspace, one-time key setup persists for later sessions; ships on npm as dknowc-dsh.
彩智科技深知可信智能出品的可信办公全家桶 dsh 插件：包含深知可信咨询（政策/法规/办事问答，带真实来源角标 + 可点击溯源 HTML）、深知可信搜索（权威政策/标准检索与深度研究，溯源 HTML + 干净 Markdown）、深知公文写作（正式公文起草/改写/Word/红头交付）三个 Skill；接口统一经深知可信工作台 MCP 转接（Bearer 认证），产物写入会话工作区，API Key 一次配置长期免注册；已发布 npm 包 dknowc-dsh。
How to install
dsh plugin add dknowc-dsh About
dknowc-dsh 深知可信办公全家桶 —— DeepSeek Harness（dsh）插件包。 通过一个 bundle 交付彩智科技的三个深知 Skill（深知可信咨询 / 深知可信搜索 / 深知公文写作），并内置深知可信工作台 MCP 转接层配置：**接口能力统一走 MCP，skill 不再直连深知接口**。 包含什么 dknowc-dsh/ ├── skills/ │ ├── dknowc-trusted-consulting/ 深知可信咨询（MCP 转接 credible_chat） │ ├── dknowc-trusted-search/ 深知可信搜索（MCP 转接 trusted_search / deep_query） │ └── dknowc-official-doc-writer/ 深知公文写作（搜索走 MCP；范文大纲保留原脚本直连） ├── src/index.js 注册 3 个 skill 到 dsh ctx.skills └── cordis.patch.yml 挂载 skill provider + mcp-client（Bearer 认证） | Skill | 能力 | 接口调用方式 | |---|---|---| | 深知可信咨询 | 政策/法规/办事咨询，带角标答案 + 溯源 HTML | mcp__dknowc__credible_chat |…
Recommendation signals
Meta
- License
- MIT
- Language
- Python
- GitHub stars
- 0
- mo. downloads
- 0
- Last push
- 2026-08-18
- Created
- 2026-08-17
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
superpowers
obra/superpowers
An agentic skills framework & software development methodology that works.
ruflo
ruvnet/claude-flow
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
caveman
JuliusBrussee/caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman