Best hypothesis generation skills for Claude Code, Codex and other agents.

Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

spacering-net/codeg

Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

Yuan1z0825/nature-skills

This skill enriches vague prompts with targeted research and clarification before execution.

severity1/claude-code-prompt-improver

Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready…

K-Dense-AI/claude-scientific-writer

A skill your agent uses when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled…

Rimagination/good-question

Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.

zjYao36/Auto-Research-Refine

Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.

limingrui679-design/high-stakes-analytics-decision-lab

Creative research ideation and exploration. An agent skill from spacering-net/codeg.

spacering-net/codeg

Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

aiming-lab/AutoResearchClaw

A skill your agent uses when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance)…

ai4s-research/ai4s-skills

Get a deep critical review of research idea from GPT via Codex MCP.

GRIND-Lab-Core/night_owl_research_agent

Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.

zjYao36/Auto-Research-Refine

Help with humanities scholarly writing: sharpen research questions, map supplied readings, plan and draft arguments, review chapters, preserve authorial voice, and respond to reviewers.

tizzy916/humanities-writing-companion

Turns completed system-internals and adversary-tradecraft research into one focused, testable threat hunt hypothesis about a single attack pattern.

OTRF/ThreatHunter-Playbook

A skill your agent uses when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions…

luwill/research-skills

Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

Oleafly/Oleafly

Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

K-Dense-AI/scientific-agent-skills

Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey → section-by-section expansion → summary…

EvoScientist/EvoSkills

Personalized academic literature digests and ranked research ideas grounded in the researcher's papers and persistent memory.

junshi-research/research-junshi

A skill your agent uses when a contributor wants to create, repair, or complete an OpenRSI-Index AutoResearch task proposal grounded in a remote model-development repository, including…

OpenRSI-Foundation/OpenRSI-Index

Turn vague or partially formed AI, computer-science, data-driven, and engineering-method research directions into evidence-grounded, falsifiable, paper-ready Research Idea Briefs through heuristic…

cpt13-g/clarify-research-idea

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.

aws-samples/amazon-bedrock-agents-healthcare-lifesciences

Two-perspective co-reasoning for AI4Science hypothesis generation.

boheling/deltasci

This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature…

Galaxy-Dawn/claude-scholar

A skill your agent uses when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot…

jameslemon2002/research-idea-explorer

Find and read academic papers (S2 + arXiv). An agent skill from EvoScientist/EvoSkills.

EvoScientist/EvoSkills

全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis…

ZS520L/HanakoPro

Use only the current SciAtlas automated review workflow (reviewpipeline) to take a novice user from zero setup to a final automated review of a research idea or paper, including setup, registration…

zjunlp/SciAtlas

Evaluates a draft research idea like a top-venue reviewer and advisor, scoring it on five dimensions, checking fit with your capacity and returning a clear verdict.

HKUSTDial/Supervisor-Skills

A skill your agent uses when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model

K-Dense-AI/science-superpowers

Analyze connections across read papers and generate actionable research ideas.

AlphaLab-USTC/ResearchClaw

Takes a field of study or practice and finds the few independent generators behind it, testing each set by whether it can regenerate the observed phenomena.

lijigang/ljg-skills

Use only the current SciAtlas multi-step idea-generation workflow (sciatlasideagen) to take a novice user from zero setup to final literature-grounded research idea seeds, including setup…

zjunlp/SciAtlas

Filter, compare, and rank papers, posts, captures, threads, bookmarks, product claims, or research ideas for high-entropy mechanistic insight and underpriced leverage.

tokenbender/agent-guides

Legal abductive reasoning skill for generating and evaluating the most reasonable explanatory hypotheses when evidence is incomplete or facts are ambiguous.

THUYRan/Legal-Skills-Chinese

Research viral content ideas from a project profile for Instagram, YouTube, X, and TikTok.

swaroop2004/Proven-Viral-Content-System

Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.

brycewang-stanford/Auto-Empirical-Research-Skills

Clusters the latest news-feed results by topic and writes a briefing of research idea seeds with citations, plus a structured seeds file, without crawling new sources.

OpenLAIR/dr-claw

Interactive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy

maxwell2732/paper-replicate-agent-demo

Use only SciAtlas search-papers to take a novice user from zero setup to final prior-art grounding for a research idea, including setup, registration guidance, configuration, retrieval, artifact…

zjunlp/SciAtlas

Stress-test an academic research question, proposal, study design, analysis plan, manuscript claim, review protocol, or AI research project through a one-question-at-a-time interview until its…

Exekiel179/psyclaw

Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…

AI4Scientist/nano-scientist

Comprehensive product research and opportunity analysis for Amazon sellers.

nexscope-ai/Amazon-Skills

Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty.

lingzhi227/agent-research-skills

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication.

davila7/claude-code-templates

學術研究的 Idea 產生技能——從發散到收斂，系統化地產出高品質研究構想。當使用者想腦力激盪研究方向、找新 research idea、或問「我接下來可以做什麼研究」時，一定要使用此技能。觸發詞包括：brainstorm、想 idea、研究方向、下一步做什麼、有什麼可以研究的、找 gap、research proposal。適用於任何階段的學術研究構想生成。

voidful/academic-skills

Automated hypothesis generation and testing using large language models.

davila7/claude-code-templates

Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset

maxwell2732/paper-replicate-agent-demo