DSH Plugin HubDSH 插件市场

zuoyunlai/lunheng-article-pipeline-dsh

Bundle捆绑包 Native原生 ⭐ 7 MIT Subagents & Orchestration子代理与编排Docs & Writing文档与写作

论衡（lunheng-article-pipeline）DeepSeek Harness bundle 插件（DSH 适配版）

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native DeepSeek Harness (DSH) bundle that registers an on-demand agent skill purpose-built for multi-agent long-form writing. It is built exclusively for DSH, including a formal DSH bundle manifest, cordis patch configuration, and a plugin entry that registers the skill directly via the DSH context object. The pipeline splits long-form projects like academic papers, industry analysis, and business commentary into six phases with nine interchangeable independent roles, all orchestrated via DSH native subagent calls. It enforces a triangular evidence rule that requires every claim made in the text to map to supporting literature, data, and case sources.

This pipeline is designed for writers working on long-form pieces over 2000 characters that require verifiable evidence and structured output. It includes four human-in-the-loop checkpoints at phase 0 (topic confirmation), phase 2.5 (outline review), phase 3.5 (first-hand context input), and finalization, so users can step in to adjust work at any key stage. A full run will produce structured outputs including literature cards, data cards, case cards, an analysis outline, multiple draft versions, audit and review reports, and a final polished markdown deliverable. It is ideal for projects that need to hold up under scrutiny, with a full run typically taking 1 to 3 hours to complete.

This project is released under the open-source MIT license. It defaults to Chinese language prompts, file naming, and workflows, so it works best for Chinese-language long-form writing. It cannot perform first-hand data collection, statistical analysis, original image generation, or code execution for unapproved scripts, so users need to supply this content upfront if required. Users can override the default model provider and model name for each tier of work (retrieval, analysis, audit) via environment variables, and full runs typically use more than 15 separate subagent calls, leading to higher overall token consumption for the full pipeline.

这是一个专门为DeepSeek Harness（DSH）开发的原生bundle插件，提供了端到端的长文写作多智能体工作流，适用于撰写学术论文、行业分析、商业评论等2000字以上的长文作品。它将长文创作拆分为6个阶段共9个独立可替换的角色，通过DSH的子代理调用完成编排，要求每一个论点都匹配文献、数据和案例构成的三角证据基础。

这个工作流设置了4个人机检查点，分别在确认选题、审核大纲、补充一手信息和最终定稿环节，用户可以在每个节点介入调整。整个流程会输出结构化的文献卡、数据卡、案例卡、分析大纲、多轮草稿、审核报告和最终成品，适合需要经得起推敲、有公开证据支撑的长文创作需求。

该项目采用MIT许可证开源，默认角色提示、输出格式优先适配中文，不支持一手数据采集、统计分析、原创图像生成等操作，完整运行需要调用15个以上子代理，token消耗较高。用户可以自定义配置不同推理阶段使用的模型提供商和模型，处理敏感内容时可选择本地模型端点避免额外外部调用。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：lunheng-article-pipeline-dsh（zuoyunlai/lunheng-article-pipeline-dsh）
仓库：https://github.com/zuoyunlai/lunheng-article-pipeline-dsh
本站详情页：https://www.yhbd.top/plugins/zuoyunlai-lunheng-article-pipeline-dsh/
本站登记：类型 bundle · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 7 · 最近提交 2026-10-03 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 7 stars - very few users, little community feedback星标只有 7，几乎没人在用，遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add lunheng-article-pipeline

把 zuoyunlai/lunheng-article-pipeline-dsh 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

18.5 KB · 缓存于 2026-10-03 22:10:13 · 18.5 KB

Lunheng (lunheng-article-pipeline) — a DeepSeek Harness bundle for multi-agent long-form writing

🌐 English (this file) ｜ 中文 ｜ Español ｜ Português ｜ हिन्दी

版本：v18.72.0（DSH bundle：package.json + cordis.patch.yml + lib/index.js）

A DeepSeek Harness (DSH) bundle that registers two on-demand agent skills: lunheng-article-pipeline (the main 9-role pipeline) and lunheng-commands (a thin wrapper exposing 11 /lunheng-* slash commands for draft / resume / cite / audit / journal / ppt / history / rollback / status / stats / help — no new role, no new M-gate item; see skills/lunheng-commands/SKILL.md). The main skill turns long-form production — academic papers, industry analysis, business commentary, and long-form articles — into a 9-role pipeline with a human in the loop.

What this is

Lunheng is a writing pipeline, not a text generator. It splits a long-form deliverable into 9 independent roles (T1–T9) across 6 phases, orchestrated with DSH subagent calls, and produces output with an evidence base, counter-argument review, independent audit, and human checkpoints.

The nine roles are independent and interchangeable with nothing else: T1 literature scout, T2 data scout, T3 case scout, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer (executed by the coordinator itself), T9 peer reviewer.

When to use it

  • You need a long-form piece (over 2000 characters) that has to hold up under scrutiny, and you can wait 1–3 hours.
  • The topic involves facts, figures, or multiple viewpoints, so it needs an evidence base rather than opinion only.
  • You want human checkpoints: confirm the outline before drafting, and review the final draft.

When not to use it

Lunheng actively collects published evidence and integrates evidence you supply. It cannot produce the following on its own; supply the material first, or use another tool:

  • First-hand data collection — experiments, surveys, interviews, field work.
  • Statistical analysis — it can cite results but does not run SPSS/R/Python.
  • Raw chart data collection — it renders data visualizations; scraping, OCR, and speech-to-text need dedicated tools.
  • Original images or video — DSH has no built-in text-to-image. Covers fall back to local SVG or supplied files.
  • Code execution — the pipeline runs only whitelisted scripts; anything else needs your explicit approval.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 zuoyunlai/lunheng-article-pipeline-dsh 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev harness-lark 下一个 Next dsh-plugin-notify →