claesbackman's review-paper skill runs eight review agents in parallel on an academic economics paper written in LaTeX and combines their findings into one structured referee report. You can name a target journal, such as the AER, QJE, Econometrica or a top finance or macro journal, and one agent reviews it as that journal's referee would. It is meant for checking a paper before you submit it.
Repo Intake and PlanScans a research repository and drafts a README-first reproduction plan before coding.ResearchResearchData
Run a biomedical literature review through an MCP research serverThis AWS sample skill helps a developer's agent search scientific literature, find papers, pull content from publications and assemble evidence summaries. It works through an MCP server of Biomni research tools that the developer deploys on Amazon Bedrock AgentCore. The skill maps question types to sources, for example clinical trials, ClinVar for variants, OpenFDA for drug safety and Reactome for pathways. It is a sample from a healthcare and life sciences repository, not a finished product.ResearchResearchHealthcare
Run cited deep research with the Tavily CLITavily's tavily-research skill has an agent run multi-source research through the Tavily command-line tool and return a report with citations. It fits comparisons, market overviews and literature reviews where a quick search is not enough. One command gathers and analyzes sources and takes about 30 seconds to two minutes, with a larger model option for deeper work. It needs the Tavily CLI and a Tavily account.Researchresearchcitations
Turn interview notes, surveys and tickets into ranked findingsAnthropic's synthesize-research skill, from its product-management plugin, makes sense of a pile of user research such as interview notes, survey answers and support tickets. It groups the material into themes, ranks findings by how often they come up and how much they matter, describes user segments and suggests opportunities for the roadmap. The result is a structured research summary.ResearchProduct managementResearch
Environment and Assets BootstrapPrepares a conservative environment and assets bootstrap for README-first machine-learning reproduction.ResearchResearchOps
Get cited answers from Brave Search, quick or in depthBrave's answers skill shows an agent how to call the Brave Search answers endpoint, which uses the same request format as OpenAI chat completions. It covers a quick mode that answers from one search, with optional citations, and a research mode that runs several searches and returns a combined answer with sources. Responses can be streamed or returned at once. It needs a Brave Search API key on a plan that includes answers.ResearchResearch
