Best · Curated
Best DSH Deep Research Plugins
Adaptive deep-research orchestrators and research workbenches built for DeepSeek Harness.
Editor's pick
Editor's pick
Agent preset for DeepSeek Harness that adds Cabinet Mode: a research-team Lead and four bureau members. A right-sidebar Cabinet panel shows the roster and task assignment, and Settings → Cabinet members edits each office's name, portrait, prompt and model.
Ranking
Workflow & Automation plugin ranking
01806,620 downloads/mo02896,029 downloads/mo03673,436 downloads/mo04723,244 downloads/mo05621,997 downloads/mo06671,875 downloads/mo07741,809 downloads/mo08691,538 downloads/mo09621,525 downloads/mo10791,410 downloads/mo11711,362 downloads/mo12621,198 downloads/mo1359689 downloads/mo1459664 downloads/mo1559659 downloads/mo1659644 downloads/mo1768130 downloads/mo18620 downloads/mo19550 downloads/mo20100 downloads/mo21570 downloads/mo22570 downloads/mo23570 downloads/mo24520 downloads/mo25570 downloads/mo26600 downloads/mo27590 downloads/mo28550 downloads/mo29250 downloads/mo30540 downloads/mo31590 downloads/mo32550 downloads/mo33600 downloads/mo34500 downloads/mo35100 downloads/mo36500 downloads/mo37520 downloads/mo38520 downloads/mo39550 downloads/mo40500 downloads/mo41500 downloads/mo42100 downloads/mo43100 downloads/mo44100 downloads/mo45550 downloads/mo
luodaoyi/dsh-cabinet-mode
Agent preset for DeepSeek Harness that adds Cabinet Mode: a research-team Lead and four bureau members. A right-sidebar Cabinet panel shows the roster and task assignment, and Settings → Cabinet members edits each office's name, portrait, prompt and model.
PerryLink/dsh-research-report
Verifiable research-report engine for DeepSeek Harness with a content-addressed evidence ledger, versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory, and retrieval orchestration that reuses the ctx.web and ctx.jobs seams.
ninipa/oh-my-dsh-slim
Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.
ChongCyrus/Vibe-Mathematics
Installs four multi-agent math-research presets for DSH: v2 (probability-driven pipeline with multi-verifier debate), v3 (paper-style Markdown knowledge base with a planner agent and a reusable method library), v4 (persistent self-organizing residents that message and meet), and v5 (a research institute with an academician who decomposes and assigns work, voting researchers, temp workers, group chat and a compare-and-set task board); all four support checkpoint resume, human intervention, and an optional Lean formal-verification switch (off/encourage/require) whose passing proof turns the vote into a fidelity check of the Lean statements.
zjukop3/dsh-review-outbox
Evidence-gated acceptance for research reports: claims, citations, data scope and method limits each need a tick plus written evidence before a deliverable can pass, with same-artifact revision history and a standalone SHA-256 receipt that says when the bytes moved.
Eason-0712/dsh-zotero-skill
Zotero skill for DeepSeek Harness: page-anchored Q&A, full-text translation and close reading, native highlights and Chinese notes, bilingual PDF and paragraph Markdown, evidence comparison tables, and reviews with citation tracking; finds papers on OpenAlex or Crossref, imports Chinese CNKI export files, classifies the library into research-direction folders, surfaces research gaps, and runs a ranked daily digest of new papers. Python-based (basic library management uses the standard library; the reading workflow downloads its PDF/OCR components on first use); writes need a one-time Zotero authorization, and daily scheduling is Windows-only. Adapted from the OpenAI MIT Zotero plugin.
stuarthu/dsh-crew
Runs work as a crew of role agents: a product manager writes the PRD or DoD, waits for your confirmation, then starts architect, engineer, QA and reviewers whose tool sets are locked per role, and shares work through files on disk.
IcyCreamDAS/shidi-skill
AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.
aa2246740/dsh-autoresearch
Creates, runs and monitors persistent research experiment loops from the DSH Web UI.
biociao/dsh-science
Claude Science-style research workbench: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), and 10 science skills for genomics/pathogens/bioinformatics.
MoonCoder-HAPPY/SpecWorkflow
Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.
hulibuld/dsh-sort-out-the-thoughts
Thinking-sorting plugin. A switch beside the composer puts the session into a three-stage mode — sort, critique, research — and each stage has a checklist of what it should produce before you press the advance button; finished ideas are filed by genre into Settings → Thoughts Center. A floating notebook holds half-formed sparks and opens a new session with the chosen one already written into the input box.
Z-Asset/ZA_ppt
PPT stage — presentation generation (Beamer/Quarto) from the paper for asset pricing and machine learning research. Ships one skill.
Z-Asset/ZA_report
Report stage — academic paper writing for asset pricing and machine learning research. Ships one skill.
Z-Asset/ZA_literature
Literature review stage — search, synthesis, and citation-chain tracking for asset pricing and machine learning research. Ships one skill.
Z-Asset/ZA_data
Data stage — data discovery and quality assessment for asset pricing and machine learning research. Ships one skill.
BillyChen123/qdd
Question-Driven Discovery research workflow for DeepSeek Harness with a QDD Agent Preset, durable Human and Auto runs, and an auditable research panel.
omdsh-dev/dsh-deep-research
Adaptive deep-research orchestrator built on the official workflow engine.
nullptr-DZF/dsh-academic-research-skills
Ported from the ARS Claude Code plugin (44k+ stars on GitHub): academic research skills for DeepSeek Harness — a deep-research agent team, a paper-writing pipeline, a multi-perspective peer-review panel, and an end-to-end orchestrator, plus sixteen /ars-* commands.
AngleZhang-ZhangJiao/dsh-orchestrator2#dsh-orchestrator2
Agent preset: one session runs a three-phase auto-development pipeline — interactive design with parallel research subagents, goal-driven development with reviewer/developer subagents and per-package budget ledgers, then an acceptance fix loop.
LouisHaoL/dsh-timer-agent
Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.
slow-stack/dsh-study-desk
Study workbench for exam prep and research: three-column task board with tags and filters, a spaced-repetition queue (simplified SM-2) that keeps finished cards coming back, a heatmap lit by actual focused minutes, weekly reports, per-day review notes, a pomodoro timer that survives panel switches, and Markdown export/import for Obsidian. Installable via dsh plugin add (dsh-study-desk on npm).
jinghuaihuaxiang-star/dsh-superagent-desktop
Desktop-bundle fork of the DeepSeek Harness team's dsh-superagent research prototype: turns requests from allowed people on GitHub issues or Feishu into tickets worked by isolated DSH sessions, with a panel for sources, setup, prompts and run history. By default only people on a source's allowed list can start work. Needs git 2.32+ and the gh CLI for one GitHub repository; Feishu is optional and needs lark-cli.
Lixiuxiu559/AgentForge
Six engineering skills for Claude Code and DSH: research, architecture scouting, implementation orchestration, three-axis diff review, complexity audit and mutation testing. Skills delegate through the host’s generic subagent tools when available.
QlzqQlzq/dsh-dual-agent-presets
Installs two selectable Agent Presets: a shell-restricted general-purpose agent and a repository-focused coding agent.
mengzhongjie/dsh-superagent-local
Fork of dsh-superagent for local use: each sidebar workspace gets a main session that turns a request into a ticket and has a worker session do the work inside that workspace's directory. Cannot be installed alongside upstream dsh-superagent: both use the package name dsh-superagent and mount the same plugin ids.
wct-lab/dsh-docchain
DocChain knowledge base, document conversion and knowledge-graph toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown (flowcharts and architecture diagrams are turned into PlantUML sketches, other images into text descriptions; the original image is replaced by a clickable link), a deep-research workflow, and a knowledge-graph layer (ontology inspection, read-only Cypher, ontology/entity/relation writes). Every script-backed capability also ships as a native DSH tool executed in-process: doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown, plus kg schema / kg cypher / kg upsert node / kg upsert relation / kg delete node / kg delete relation. All graph operations go through the DocChain API, so no Neo4j password is needed. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).
Azzygoatcoder/agent-useful-skills
Modular AI research/engineering skill pack, installable via dsh plugin add — registers 27 skills (security audit, paper reading/writing, figure drawing, dev workflow, storage analysis) on ctx.skills.
lkshjd/dsh-debate
Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.
Wattson-Law/Xiaobai-Reasearch
Chinese industry and technology research report skill with an offline DOCX build pipeline (build_docx.py). Enforces a 9-chapter structure with a plain-language timeline (Section 2.1), 5-dimensional technical bottleneck criteria, and Make-vs-Buy cost/compensation trade-offs, verified by check_threads.py and compiled to .docx with a 3-level auto TOC. Requires Python 3.9+ with lxml.
Kayungko/dsh-plugin-product-design
Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.
genesis-agents/dsh-deep-insight
Evidence-based research workspaces with archived sources, knowledge graphs, exact citations and exportable reports. Experimental alpha. Needs Node 24.9 or later, uv and Python 3.13, plus a one-time setup step (setup-engine.mjs) that copies the engine and runs a locked uv sync; pnpm must also be allowed to run the build scripts of onnxruntime-node and protobufjs.
JiamingShi-JsPhys/chelate-shell
Nineteen research and engineering skills run as one gated pipeline: each skill occupies a fixed stage, and a gate that fails blocks the skills downstream of it instead of passing its output along. The gates are falsifiable checks rather than flow control — atom conservation for chemical equations, CAS and unit validation for formulas, DOI resolution against Crossref, leakage detection on ml datasets, element checks on OBJ meshes — so a failed run names what failed instead of producing a plausible document. The four tools it registers drive the CLI: list the registry, run one skill, run the pipeline (with a dry run), and audit results/ for files no promotion accounts for. Requires Python 3.10+ on the host.
Z-Asset/ZA_analysis
Model training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.
CREAIT-nl/dsh-plugins#research-mode
Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.
woshipixiu1234/dsh-invest-bundle
Investment research bundle: 10 tools (search, page fetch, source audit, claim verification, numeric rigor, channel health, workflow loader, chart engine, PDF renderer, PDF gate) and 23 skills adapted from ai-berkshire. Runs a six-phase workflow where four parallel agents (Duan Yongping, Buffett, Munger, Li Lu) research a company, cross-examine each other, and ship a chart-rich PDF with cover, tables, captions and page numbers. Requires Python 3.10+; the chart and PDF tools also need python-docx and matplotlib.
xsoc1/math-research-dsh
Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.
duhu2000/dsh-pre-duediligence
Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.
hasan-aghayev/dsh-task-orchestrator
Automatically orchestrates complex DeepSeek Harness requests. It detects when delegation is useful, builds a dependency-aware plan, assigns bounded researcher, architect, backend, frontend, tester, and documentation workers, collects structured evidence, and sends the results to a final reviewer. The bundle atomically enables the workflow engine and model-facing subagent tools; disabling the plugin disables its complete tool group as well.
TZUKWAN/METIS_ACADEMIC
AI-assisted research workbench with editable step workflows, on-demand skill binding, a live execution graph and in-project document review (needs a local Python with python-docx, python-pptx, openpyxl and PyMuPDF), while keeping existing projects on their original configurations. Requires DSH 0.2.2 or later.
LoneLeave/dsh-research-solver
Research-style problem solving in four gated stages: record sources by retrieval tier with local before web, turn each shortfall of existing tools into a gap that needs evidence, score candidates against weighted metrics with a deterministic engine, fuse or improve the weak ones, then iterate on measured deltas. Also organizes a directory into human-facing and machine-facing trees.
oxmumu3/dsh-workproof#dsh-evidence-ledger
Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.
Karbo123/DSH-EvoResearch#evoresearch-plugin
Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.
piggy00544/dsh-workproof#dsh-evidence-ledger
Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.
jakehemmerle/dsh-aris-better
Adds an ARIS agent preset that loads the 84 ARIS research-workflow skills and runs their reviewer as an in-harness subagent from a different model family than the session model. Other presets are unchanged. A fork of wanshuiyin/Auto-claude-code-research-in-sleep's dsh-aris branch: install it instead of the upstream dsh-aris plugin, not alongside it - both register the mcp__codex__codex reviewer tools and the same ARIS skills.
View all Workflow & Automation plugins Workflow & Automation,Back to leaderboard dshplugins.cc。