dsh-mimir
Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness
114 results
Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness
Academic mode for DeepSeek Harness (dsh): a research persona, anti-fabrication rules for citations and data, and bilingual conventions. Pairs with dsh-ai4scholar (literature tools) and dsh-research (research skills).
DSH-native multi-runtime baseline, ablation, and reproducible evaluation control plane
Search arXiv for ML/DL/RL papers and check claims against real abstracts.
DeepSeek Harness bundle: two academic research agent presets — scopus-scholar (搜索驱动模式, Scopus/OpenAlex search with a claim-verify loop) and scopus-knowledge (知识驱动模式, a code-enforced knowledge pipeline consulting a tool-free 科学顾问 persona)
DeepSeek Harness 插件:用户研究合成 Agent 包——把访谈 / 问卷 / 观察笔记合成用户画像、痛点与机会点。
Quant factor research pipeline: probe to panel to IC/5-gate to backtest to regime, with persistent project object + genui dashboards.
AutoResearch Project Mode preset for DeepSeek Harness.
一个提供网络研究和发现功能的综合模型上下文协议(MCP)服务器,包含13种工具用于搜索、爬取和分析网络内容。
Z Research PPT stage — presentation generation (Beamer/Quarto) from the paper. Ships one skill.
DeepSeek Harness bundle: a bounded, de-confounded hyperparameter sweep ledger with a research-campaign playbook skill and paper-ready report tables
Research writing bundle for DeepSeek Harness: literature search/citation (dsh-lit-search) + LaTeX/BibTeX guard (dsh-latex-guard) in one install.
Research lab for DeepSeek Harness: AutoSci-style wiki (experiments/literature/decisions), ASI-Bench-grade eval rigor ledger, arXiv digest, adversarial paper review, and academic writing checks.
Z Research literature stage — literature search, synthesis, and citation-chain tracking for asset pricing + ML/DL research. Ships one skill.
Z Research data stage — data discovery and quality assessment for asset pricing + ML/DL research. Ships one skill.
Z Research report stage — academic paper writing for asset pricing + ML/DL research. Ships one skill.
Education mode for DeepSeek Harness: research a course, teach it, write the class notes, and quiz the learner.
Z Research analysis stage — end-to-end model training and estimation for asset pricing + ML/DL research. Ships one skill.