데이터·AI 스킬

Choose, build, and review charts that answer a clear analytical question. The skill checks chart types, labels, units, colors, and data sufficiency, then refines the visual in its intended report, dashboard, notebook, or other output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a chart for a specific analytical question
• Improve charts that are hard to interpret
• Review charts for reports or dashboards

Create and maintain a reusable skill that records metric definitions, trusted data sources, and analytical caveats. Preserve supporting evidence and unresolved conflicts so future Data Analytics work can consult and cite the same documented context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save shared metric definitions for future analyses
• Document trusted sources and conflicting definitions
• Update or repair an existing semantic layer

Review reports, spreadsheets, dashboards, or other analyses before sharing them or making decisions. Check methods, calculations, charts, and conclusions, then receive a readiness assessment with prioritized fixes, supporting evidence, and limitations that readers need to know.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a report before sharing it
• Verifying key metrics and comparison periods
• Reviewing charts for misleading presentation

Design charts and dashboards that show data distributions, uncertainty, missing values, and sample sizes clearly. Choose visual forms that preserve meaningful variation and explain where averages, aggregation, or interval choices could mislead readers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a chart to show a data distribution
• Presenting confidence intervals clearly
• Revealing variation hidden by dashboard averages

Create interactive views of dense datasets, spatial paths, and flows using WebGL, which uses the GPU for rendering. Choose suitable libraries and design navigation, labels, animation, and static alternatives around the analytical task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore spatial trajectories and point clouds
• Build dense scatterplots and network views
• Animate flows between locations or nodes

Build charts from tables using Vega-Lite, Vega, or Observable Plot. Describe data, visual elements, and interactions in reusable definitions, choose a suitable tool, and assess mobile layout, performance, and when custom rendering becomes necessary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a Vega-Lite chart specification from a dataset
• Choosing between Plot, Vega-Lite, and D3
• Building layered charts with panels and tooltips

Generate new protein, peptide, antibody, or nanobody candidates that bind a chosen target using Boltz. The workflow covers target exploration, design setup, cost estimates, job submission, result downloads, and ranking by predicted binding confidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design new peptide binders for a target
• Generate antibody or nanobody candidates
• Explore binding sites and target input configurations

Decide whether geographic data needs a map, then choose suitable background maps, visual forms, and implementation tools. Plan overlapping markers, zoom behavior, and mobile interactions so the map supports the intended analysis or product task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deciding whether regional comparisons need a map
• Designing regional maps with meaningful color scales
• Planning overlapping markers and zoom behavior

Routes web visualization work to suitable specialist skills, from chart selection and critique to maps, dashboards, and software diagrams. Helps plan readable views, mobile interactions, accessible controls, shareable state, exports, and testing around the question the data should answer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a chart that answers a specific question
• Improve dashboard readability
• Design maps and project timelines

Generate new small molecules intended to bind a target protein with Boltz. The workflow covers cost estimation, job submission, result downloads, and ranking candidates by binding confidence or a score for improving promising molecules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate binding candidates without an existing compound library
• Rank generated molecules by binding confidence
• Review solubility and permeability of promising candidates

Inspect existing Boltz jobs, check local download progress, and recover results after an interrupted session. Use run names or job IDs to resume downloads into the existing output directory without starting a new job.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Listing recent Boltz jobs
• Checking local download progress
• Resuming interrupted result downloads

Build custom browser charts with D3, including precise labels, annotations, zooming, and range selection. Create SVG graphics that adapt to mobile screens, use meaningful contextual backgrounds, and support export when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating SVG charts with direct labels and annotations
• Adding zoom and range selection to scatterplots
• Plotting data over a soccer pitch or floor plan

Screen an existing compound library against a protein target with Boltz. Rank candidates by binding confidence or lead optimization score, download predicted structures, and review solubility, permeability, and lipophilicity results alongside the ranked hits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening an existing compound library against a protein
• Finding candidates with high binding confidence
• Comparing candidates for lead optimization

Estimate small molecule solubility, permeability, and lipophilicity with Boltz using SMILES, a text notation for molecular structures. Process individual molecules or lists, review costs before submission, and receive results mapped to each input.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Estimate properties for a molecule from its SMILES
• Evaluate a molecule list from a CSV file
• Compare predicted properties during initial screening

Query MySQL databases to summarize sales, user behavior, and business metrics. The skill checks available tables, runs read-only queries, and presents results as Markdown tables with explanations of key figures, changes, and conclusions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing sales data
• Analyzing user behavior
• Reporting business metrics

Build and debug Python agents with Swarms, a framework for coordinating multiple AI agents. Covers tool connections, saved memory, autonomous execution, and workflow choices such as sequential steps, parallel work, specialist delegation, and combined answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an agent that calls Python tools
• Coordinating sequential or parallel agent workflows
• Saving agent memory across restarts

Create clear, accurate charts for dashboards, data exploration, and reports. Choose chart types that fit the message, refine labels and scales, use accessible colors, and add context and annotations to help readers understand the findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a sales dashboard for executives
• Exploring patterns in customer behavior
• Creating charts for an annual report

Manage local projects for labeling text, images, audio, and video through the host application's MCP tools. Create projects, update labels and annotations, review saved work, and export approved results as JSON.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a text labeling project
• Update annotations and label names
• Review saved annotation results

Use Jev to choose among available tools, skills, or agents, or assess outputs against explicit criteria. Receive structured selections, scores, or probabilities to support decisions within a defined set of options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a tool from available candidates
• Assess which skills a task needs
• Score outputs against explicit criteria

Query trading activity, capital flows, and positions across Polymarket, Hyperliquid, and Meteora. The skill covers wallet scoring, large trades, and liquidity pool analytics through 63 API endpoints, paid per request with USDC on Solana without API keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracking large trades and capital flows on Polymarket
• Comparing Hyperliquid traders and their trading results
• Examining Meteora pools and liquidity providers

Build workflows on OpenServ where multiple AI agents share tasks and pass results between steps. Examples cover research, writing, and image creation, with guidance on finding agents, setting dependencies, and connecting sequential or parallel work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect research and writing agents
• Build a research-to-image content pipeline
• Combine results from parallel tasks

Connect applications to NEAR AI Cloud for AI responses generated in protected computing environments. Use its OpenAI-compatible API and follow the verification flow for hardware proofs and response signatures to check which protected environment signed a response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting a chat app to the OpenAI-compatible API
• Verifying GPU and CPU execution environment proofs
• Checking response signatures against verified signing addresses

Analyze cryptocurrency wallets using balances, profit and loss, transaction history, and address labels. Profile several wallets together, trace connections across transaction counterparties, compare shared tokens and contacts, and export selected results as CSV.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a wallet's balances and profit or loss
• Trace transaction counterparties across multiple steps
• Compare tokens and counterparties shared by two wallets

Integrate Birdeye API data to track token prices, charts, holders, trades, and wallet portfolios. Supports profit and loss analysis, token risk checks, and live price or large-trade streams, with access depending on the service plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieving token prices and candlestick chart data
• Finding newly listed and trending tokens
• Analyzing wallet portfolios and profit or loss