This skill helps founders test a real or prototype consumer product, such as food, drinks, cosmetics, household goods or hardware, with real users. It picks the right test for the stage, from concept to prototype to in-home use to claims, and sets up recruiting, the protocol and what to record. It keeps you honest about what each result proves, favoring what people actually do over what they say. You get a test plan and a way to read the results.
Run an autonomous AI research project with two loopsThis skill has an agent manage a whole research project on its own, from literature survey to a written paper. An inner loop runs fast experiment iterations against a clear target, while an outer loop reviews results, spots patterns, and decides the next direction. It keeps state in files such as research-state.yaml, a research log and a findings file, and hands execution to domain-specific skills. It also sets up a continuity loop so work carries on between sessions, and it produces progress presentations for the human. Note: it tells the agent to keep working without asking permission, so review it before using it on a shared machine.ResearchAutonomous researchExperiments
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
Write a cited deep-research report with FirecrawlThis skill uses Firecrawl to search and read the web on a complex topic, then writes a formal report with sources. The report has an executive summary, key findings, detailed analysis, contrarian views and risks, and open questions. It is meant for hard scientific, technical, policy, or market questions, not quick lookups or product picks.ResearchWeb ResearchReports
Find every company or person that fits a descriptionThis skill uses the Parallel FindAll API to list every company, person, product, or other item that matches a plain-language description. You can ask for extra fields on each match, and every result comes with evidence. It returns a list, not web pages or a narrative report. The Parallel CLI is required.ResearchEntity SearchWeb Research
Merge search results into one cited answerThis skill combines results from several search sources into a single answer with duplicates removed. Each claim keeps a citation, confidence depends on how fresh and authoritative the source is, and conflicting information is called out. It changes how it summarizes depending on how many results come back.ResearchEnterprise SearchSynthesis
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 an autonomous AI research project with two loops
Turn interview notes, surveys and tickets into ranked findings
Write a cited deep-research report with Firecrawl
Find every company or person that fits a description
Merge search results into one cited answer