← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

lunheng-article-pipeline-dsh

Multi-agent long-form writing and research pipeline bundle with human-in-the-loop validation and audit gates.

VisionUI & ProductivityDeveloper ToolsBrowser & WebSecurity & PolicySkills & WorkflowsRemote Execution
6GitHub Stars0ForksUpdated2026-09-27

Install

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

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
Lunheng is a DeepSeek Harness plugin bundle orchestrating a 9-role pipeline (T1-T9 across 6 phases) for producing long-form articles, academic papers, and industry analysis. It incorporates parallel retrieval for literature, data, and case studies, human checkpoints, independent audits, AI-trace reduction, and mechanical verification gates.

Key Capabilities

  • Orchestrates 9 specialized subagent roles (T1 literature scout through T9 peer reviewer) across 6 writing and verification phases
  • Provides triangular evidence validation combining structured literature, data, and case cards
  • Includes mechanical audit tools such as lunheng_m_gate, lunheng_char_count, and lunheng_handoff_check
  • Exposes 11 slash commands for drafting, auditing, stats telemetry, and rollback operations
  • Implements built-in write protection to prevent tool calls from altering mechanism configuration files

Useful For

  • Drafting rigorous academic papers and pre-submission peer review simulations
  • Generating deep industry analysis and business commentary with verified citations
  • Multi-step structured article authoring requiring human review at outline and draft milestones

Who It Fits

  • Researchers and academic writers
  • Industry analysts and technical content creators
  • DeepSeek Harness users requiring structured, multi-agent long-form document pipelines

Documented Limitations

  • Chinese-first workflow defaults for prompts, file names, and output structures
  • Requires significant token expenditure across 15+ subagent invocations
  • Cannot conduct primary experimental research or execute statistical analysis like SPSS/Python natively
  • Cannot bypass paywalls or fetch offline sources for automated network validation

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 3 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
zuoyunlai/lunheng-article-pipeline-dsh
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
e5cce3c · 2026-09-27

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
6GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-27
Last release
2026-09-27
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app