DeepSeek Harness PluginManifest Valid

dsh-research-lab

Research lab toolkit for DeepSeek Harness providing wiki tracking, eval ledgers, arXiv digests, and academic writing reviews.

Developer ToolsSkills & Workflows

0GitHub Stars0ForksUpdated2026-10-01

Source

Install

No clear install command was found in the current repository evidence.

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

dsh-research-lab is a research workflow bundle for DeepSeek Harness that integrates experimental tracking, evaluation discipline, literature digests, and paper review workflows. It maintains an on-disk project research repository under `.rlab/` with structured experiment sheets, benchmark protocol validation (eval 口径), self-building SQLite FTS5 keyword retrieval, arXiv digest summaries, and academic writing checkers.

Key Capabilities

Manage structured research wikis including experiments, literature, decisions, and todos via rlab_wiki
Track hypothesis-to-verdict lifecycle pages with rlab_experiment
Maintain benchmark evaluation ledgers in bench.jsonl with protocol and split mismatch checks via rlab_bench
Perform 8-point adversarial paper reviews from arXiv identifiers via rlab_paper_review
Fetch and digest recent arXiv papers into project digests via rlab_arxiv_digest
Conduct line-anchored academic writing reviews for weak verbs, passive voice, and term consistency via rlab_writing
Retrieve project documents using dynamic SQLite FTS5 search with TF-IDF mined lexicon via rlab_related
Summarize project status, eval metrics, and open items with rlab_status

Useful For

Organizing and tracking machine learning research experiments and decision records
Auditing benchmark evaluations to prevent dataset split contamination and protocol mismatches
Curating daily literature digests and conducting peer-review checks on research papers
Refining academic manuscripts for writing quality and terminology consistency

Who It Fits

AI and machine learning researchers
Academic paper authors
DeepSeek Harness users conducting rigorous experiment evaluations

Documented Limitations

Requires DeepSeek Harness runtime >=0.2.0-rc.1 and peer dependency @deepseek-ai/dsh-tools
Relies on local filesystem storage under <project>/.rlab/ and local SQLite FTS5

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, 3 development, 2 peer, and 0 optional dependencies.

info

Dsh Bundle Declared

package.json declares DSH bundle metadata.

info

License Not Declared

GitHub did not report an SPDX license for this repository snapshot.

low

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: snow-The/dsh-research-lab
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin Bundle
Source checked: e696be7 · 2026-10-02

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.