lunheng-article-pipeline-dsh
A DeepSeek Harness bundle orchestrating a 9-role multi-agent pipeline for rigorous long-form writing and research.
Install
$ dsh plugin --profile web add lunheng-article-pipelinePlugin 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.
Key Capabilities
- Registers two DSH agent skills: the main 9-role article pipeline and 11 slash commands (/lunheng-*)
- Coordinates 9 distinct subagent roles across 6 writing and verification phases
- Performs triangular evidence collection across literature (L), data (D), and case (C) cards
- Provides built-in verification tools: lunheng_m_gate, lunheng_char_count, lunheng_handoff_check, and lunheng_ethics_sanitize
- Enforces human-in-the-loop checkpoints at topic confirmation, outline review, insight injection, and final delivery
- Supports model-tier routing for retrieval, strong reasoning, and auditing via Cordis patch definitions
Useful For
- Drafting in-depth academic preprints and research papers with cited evidence cards
- Creating verified industry analysis, business reports, and long-form commentary
- Executing structured fact-checking, AI-trace reduction, and pre-submission peer review simulations
Who It Fits
- Academic researchers and scholars
- Industry analysts and technical writers
- DeepSeek Harness power users managing complex multi-agent writing workflows
Documented Limitations
- Chinese-first workflow: prompts, deliverables, file templates, and outputs default to Chinese
- Cannot conduct primary fieldwork, run raw statistical code (SPSS/R), or fetch paywalled/offline data directly
- High token consumption due to multi-agent context reads across 15+ subagent invocations
- Automated M-gate scripts may yield false positives on non-standard formatting, requiring manual justification
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
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
- cbc1c4c · 2026-10-23
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
- 21GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-22
- Last release
- 2026-10-22
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →