Research, academic papers, education, and exam prep (4.3K skills)
Retrieve HLA alleles, forms of HLA genes, and cell metadata from the public IPD API. Filter allele records by name, limit returned items, and receive concise summaries, with raw JSON or text available on request.
Search ClinVar and NCBI Variation for genetic variants, or look up records using VCV, RCV, SCV, and RefSNP identifiers. Get concise summaries, check identifier mappings, and save full JSON responses when needed.
Retrieve gene data, search downloads, and tissue or cell-line pages from Human Protein Atlas. Get concise summaries by default, with raw JSON or HTML saved to a file only when requested.
Look up existing predictions and protein information in the AlphaFold Protein Structure Database. Retrieve concise structure metadata, UniProt summaries, sequence summaries, and annotations, with an option to save the full response for later inspection.
Look up compound–target binding data in BindingDB using PDB or UniProt identifiers, or search for similar chemical structures. Receive concise summaries of matching records, with full API responses saved to a file when requested.
Retrieve concise Ensembl summaries for gene identifiers, genomic regions, links to related database records, and genetic variants. Use a bundled Python script to request data, limit displayed results, or save the full response when needed.
Retrieve concise information about microbiome studies, samples, and habitat metadata from MGnify. Narrow requests by study or sample identifier or biome, a type of biological environment, and receive readable summaries or JSON for further processing.
Predict the structure and binding of one defined protein, RNA, DNA, or ligand complex with Boltz. The workflow covers cost confirmation, job submission, result downloads, and summaries of structure and binding metrics.
Screen supplied proteins, peptides, antibodies, or nanobodies against a target with Boltz. Prepares inputs, obtains a cost estimate for approval, downloads results, and ranks candidates by binding confidence, a score for predicted binding reliability.
Understand how Airtable organizes data into bases, tables, fields, and records. Learn how views, automations, and interfaces relate to that structure, giving you context for discussing data organization and workflows with an agent.
Search configured Yuxi knowledge bases to answer questions using internal or uploaded documents. Open source text, locate relevant passages, inspect mind maps, and identify supporting files so answers can be traced back to their evidence.
Organize complex research by splitting a topic into focused questions, assigning research agents, and checking important claims. Findings become a structured report with source links, conflicting evidence, and clearly stated uncertainties.
Research an unfamiliar topic or turn a collection of sources into structured notes, a reference article, or a publish-ready draft. The workflow connects sections to evidence, makes conflicting claims visible, and guides revision before publication.
Retrieve content from URLs and PDFs, then summarize, quote, convert, or save it as readable Markdown. When built-in search falls short, use DeepSeek as an optional search fallback, with explicit handling of extraction failures.
Find the right official documentation before answering technical questions. It identifies the library and version, retrieves focused references and examples, and explains relevant APIs while separating documented behavior from inference.
Search the private research library in Acme Research and summarize relevant material. Include each returned document's title and source URL so readers can identify the sources and check the material behind the summary.
Find and compare information in connected Notion pages and databases. The skill checks relevant sources, produces concise answers with available page links, and distinguishes current evidence from outdated notes, conflicting information, and inferences.
Turn AI-assisted coding work into optional, short learning exercises. Predict behavior, compare your approach with the implementation, or explain code in your own words, with feedback that helps clarify how the code works and why design choices were made.
Investigate a specific crypto token through price history, trading volume, holders, fund flows, trades, and profit or loss data. Use Nansen commands to examine spot activity and perpetual futures, contracts without an expiry date, with optional CSV exports.
Search Nansen for tokens, people, or organizations by name to find matching records and full token addresses. Narrow results by blockchain, limit the number of matches, and choose which fields appear in the output.
Browse Polymarket prediction markets with the Nansen CLI. Find active events and markets by trading volume, search by keyword, inspect prices and liquidity, or review closed markets and categories to understand where trading activity is concentrated.
Research crypto markets using live token data, decentralized finance metrics, wallet holdings, project profiles, and Twitter/X posts. Heurist Mesh agents provide focused lookups and deeper analysis for questions about market trends, projects, and blockchain activity.
Search the web and specialized subject areas, run multiple searches in parallel, and extract page text from URLs. Use the bundled command-line tools to gather current information, check claims, and read beyond search snippets.
Guide role-specific work in LoopX auto-research, from defining research conditions and proposing hypotheses to experiments, evaluation, and adoption or retirement decisions. Keep evidence, failed attempts, task handoffs, and stopping conditions tied to each worker’s assigned role.