Plugins

Compare multiple skills on the same task and pick the winner.

Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.

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.

Adaptive deep-research orchestrator built on the official workflow engine.

Multi-engine fused web search, page fetch, real-time X (Twitter) search with credential-free fallback, deep research and parallel multi-agent research for DeepSeek Harness. Free layer: Bing / DuckDuckGo / Yahoo / Exa MCP (all keyless, live-probed); api la

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

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.

Interactive candlestick cards for dsh web: market_snapshot and get_ohlcv results render as K-line charts with MA overlays, volume, and the indicator regime the model actually read

Financial research workflow and portfolio risk tools with source discipline for current market facts.

Native Search1API (s1) web research tools: search, news, page crawling, sitemap discovery, and trending topics as first-class `s1_*` tools, with a bundled s1 skill.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

Bundled Xiaohongshu/RED viral-note agent skill: hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing.

RigorQuant preset + skill pack: unattended walled multi-agent research for empirical and computational mathematics (economics, finance, portfolio), with a four-part pre-implementation check battery and a jacobian/Lean escalation lane.

A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots.

The research plugin market inside DeepSeek Harness: browse a curated index of literature, reference, writing and workbench plugins in Settings and install them with one click — 科研插件市场，在设置里浏览并一键安装。

dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.

Claude Science-style AIDD research workbench for DeepSeek Harness — ReAct research loop, versioned artifacts with provenance, and 17 skills for virtual screening, molecular generation, ADMET prediction, DTI modeling and model reproduction.

Evidence-driven company and job intelligence plugin for DeepSeek Harness.

DeepSeek Harness adapter for Agent Research Copilot (ARC)