Turn research notes into insights with evidence

Overview

Use cases

• Research synthesis
• User research
• Customer interviews
• Survey analysis
• Evidence synthesis

Alternatives

• 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
• 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
• 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
• Scientific Agent Skills: a pack of 177 science skillsScientific Agent Skills is a library of 177 skills from K-Dense that turns a general AI agent into a research assistant for biology, medicine, chemistry and drug development, with access to more than 100 scientific databases. It was previously called Claude Scientific Skills and now uses the open Agent Skills format, so it runs in Codex, Cursor, Google Antigravity, Claude Code and other agents that support that format. The repository runs security scans and skill tests, and an accompanying paper is on arXiv (2609.00065). K-Dense also offers a free desktop co-scientist app built on the same skills, where you bring your own model keys.ResearchScienceAgent skill packs
• Test whether a physical consumer product works for real usersThis 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.Research
• Answer questions about your data, from one number to a full reportAnthropic's analyze skill, from its data plugin, handles questions about data at three sizes: a single number, a deeper look at what is driving a trend, or a formal report for stakeholders. If a data warehouse is connected over MCP it explores the schema, writes and runs SQL and checks odd results; otherwise it asks you to paste results, upload a file or describe the tables. It validates figures before presenting them and adds charts where they help. It works best with a data warehouse connected; without one, you supply the data.ResearchData analysisSQL