Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes. Use when you…
Research: which skills are worth installing
We read 2 125 skills tagged “Research” from open catalogs: checked the files for dangerous content, against the Agent Skills spec, and for whether the process runs to the end. 1 807 passed; 318 we advise against. Below: the ones that passed, and separately the ones to walk past.
Passed the checks
Use when planning, running, or learning from chaos engineering experiments. Triggers on "chaos experiment", "fault injection", "gameday", "resilience…
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with…
Use when designing or revisiting product pricing — selecting a pricing model (subscription seat-based, usage-based, value-based, freemium, or…
Use when planning and synthesizing product/user research as a method-and-repository discipline — selecting the right method for the goal (generative…
Use when managing the money for an internal R&D program or portfolio — building a multi-period program budget with the F&A (indirect) split, tracking…
Use when doing upstream market-research methodology — sizing a market as TAM/SAM/SOM computed BOTH top-down and bottoms-up (never a single unsourced…
Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist…
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as…
Optimize content for AI citation (GEO). Use when user says "GEO", "generative engine optimization", "AI citation", "get cited by AI", "AI-friendly…
Find and compile academic literature with citation lists across Google Scholar, PubMed, arXiv, IEEE, ACM, Semantic Scholar, Scopus, and Web of…
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key…
All 2 125 in the rating, with filters →
And these — walk past
全球12亿文献知识库（8千万中文期刊可下载）——通过 SmartLib 开放平台 API 提供中外文学术文献检索与下载能力，覆盖 8000 万篇授权中文期刊全文 + 12.28 亿条全球文献元数据（期刊 7.19 亿 / 专利 2.15 亿 / 会议 7155 万 / 学位论文 2473 万 /…
面向学术研究者的个人知识中枢。整合 Karpathy LLM Wiki 知识编译能力 + SmartLib 海量文献检索能力，形成私有知识库与外部文献库双轨联动的研究助手。…
核查用户提交的论文稿件或AI生成参考文献是否真实，防止AI幻觉。基于SmartLib API，输出HTML核查报告（含差异标记、验证链接、统计分析）。支持GB/T 7714-2025（2026年7月1日起实施）/APA/MLA/Chicago/BibTeX多格式解析与输出，并行检索（8条/批）+…
The grade comes from static analysis of the files, not from opinions: how exactly, on the Method page. You can check your own skill for free. Method · Check your own skill