Research Agent Skills for DeepSeek Harness

Search, download, and summarize academic papers from arXiv.

Assesses a research paper outline (.qmd file) against structured criteria from Kosuke Imai''s empirical research guide.

Autonomous research review loop using any OpenAI-compatible LLM API.

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop).

Design cross-national survey experiments: power, equivalence, localization.

Use when the user asks to "generate daily paper", "search arXiv for EEG papers", "find EEG decoding papers", "review brain-computer…

Computational methods for humanities research including text mining and netwo...

EADA — college athletics gender equity (~2,000+ institutions, 2002-2021).

EDFacts — K-12 outcomes: assessment proficiency, ACGR graduation rates, ESSA accountability at school/district level (2009-2020).

Use when the user asks to generate daily paper digests on a general topic.

Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ),

Comprehensive multi-dimensional review of the sewage-house-prices project.

Generate publication-quality figures and tables from experiment results.

Search patent databases and academic literature for prior art relevant to an invention.

Rigorous mathematical proof verification and fixing workflow.

Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro…

Writes rigorous mathematical proofs for ML/AI theory.

VS-Enhanced Quantitative Design Consultant with Materials & Sampling Enhanced VS 3-Phase process: Avoids obvious experimental designs…

Construct and verify polynomial-time reductions between computational problems

Skill for assessing feasibility of study replication

Research Coordinator v12.0 - Human-Centered Edition (Systematic Review Automation) Context-persistent platform with 24 specialized agents…