DeepSeek Harness (DSH) Plugin: dsh-research-autoresearch
`dsh-research-autoresearch` is a research workflow plugin for DeepSeek Harness (DSH) that transforms the AutoResearch framework into a pluggable toolkit. It includes six core tools covering literature search, LQS scoring, state management, stagnation detection, and five-personality review. Its design follows MEDIAN review principles and a dual-cap stagnation detection mechanism. The plugin supports flexible three-level visualization control and addresses defects in citation window correction, orchestration-layer completion, and tool invocation in versions v0.3.0 and v0.4.0. Testing shows that it performs well in host compatibility, installation stability, and end-to-end simulation, providing a standardized closed-loop process for building research-oriented agents.
Read MoreDeepSeek Harness (DSH) Plugin: f1star/dsh-research
`f1star/dsh-research` is a research-focused plugin under DeepSeek Harness (DSH), designed to enable “evidence-first” paper reading and cross-paper synthesis. Its core features include PDF import, structured outlines, precise retrieval, scientific extraction, and cross-paper research logging. The plugin provides a web sidebar workspace, supports exporting to formats such as Markdown/LaTeX, and can save research state. Installation requires Node.js 24 LTS, and note that profile data between 0.3 and 0.4 is incompatible.
Read More@amphilagus/dsh-literature: DeepSeek Harness Literature Retrieval and Targeted Tracking Plugin
`@amphilagus/dsh-literature` is a literature retrieval and tracking plugin within the DSH ecosystem. It requires the "Literature Tracking Assistant" preset and is not loaded by default in standard coding sessions. Its core functions include retrieving topics or researchers (requiring ORCID) via Crossref and arXiv; writing results to a new global SQLite database after manual grading; and providing session-level expiry reminders and continuous tracking based on a schedule. The plugin registers three runtime skills—`literature-survey`, `literature-tracking-setup`, and `literature-tracking-search`—and supports search caching, researcher profile management, and SCI journal directory queries.
Read Moredsh-scholar: Integrating Research Dialogues, Experiments, and Papers into a Single Project within DSH
dsh-scholar is a DSH research workspace plugin maintained by lzszq, designed for computational research such as machine learning and data science. It integrates project conversations, materials, controlled experiment runs, evidence, and TeX manuscripts into a single resumable project, offering gate-only governance, Runner Profile controlled execution, and Claim-Evidence traceability. The article introduces core capabilities, usage from building and installing from source code to typical slash commands, and explains permission and security boundaries.
Read Moredsh-science: Claude Science-Style Research Workbench for DSH
dsh-science is a DSH science-oriented plugin (v0.2.0, MIT) maintained by biociao. It provides a ReAct research loop engine (research_* tools), versioned artifact tracing (artifact_* tools), SSH remote computing (remote_* tools, supporting workstations and SLURM clusters), a remote host configuration UI, and 11 research skills tailored for genomics, pathogens, and bioinformatics. Complemented by dsh-model-tier, it enables cross-provider model tier routing. It can be installed via profile bundles or the "Scientific Mode" preset, making it suitable for researchers who require structured scientific workflows and remote computing resource scheduling.
Read More