데이터·AI 스킬

Use Apify Actors, prebuilt web scraping tools, to collect structured data from social media, search engines, ecommerce sites, and other pages. The skill selects an Actor for the request and can return results as JSON or CSV, with rate limits and ethical scraping guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Collecting posts or profiles from social platforms
• Gathering search results, maps, or reviews
• Extracting product details and prices

Manage algorithm experiments, adjust parameters, and review visualized results while working to optimize complex algorithms. It is intended for tasks that involve iterative algorithm improvement and experiment tracking, and its included script requires an AppBuilder token.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Managing a set of algorithm experiments
• Optimizing model parameters
• Reviewing experiment results visually

Support visual inspection and management in industrial settings across more than 20 sectors, including retail, energy, mining, ports, chemicals, and steel. The provided script can analyze an image or generate a report using Baidu Qianfan AppBuilder.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect an industrial product image
• Analyze a production line quality inspection
• Use visual management in a supported industry

Use this skill to understand image contents with GPT-4 Vision. It can describe a picture, extract text from screenshots, identify visible objects, and answer questions about an image, returning the result in a structured format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Describe what is shown in a photo
• Extract text from a screenshot
• Identify objects in an image

Use this skill to design ClickHouse tables, improve analytical queries, and shape data ingestion and ETL workflows. It provides practical patterns for aggregations, materialized views, monitoring, and common analyses such as time series, retention, and funnels.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a ClickHouse table for analytics
• Speeding up aggregation queries
• Building a batch or streaming ingestion flow

Plan a parsing workflow for repeated text such as forms or quizzes. Use regular expressions for predictable patterns, score extraction confidence, and reserve language model checks for uncertain edge cases to help control cost.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Parsing quiz questions and answers
• Extracting fields from forms or invoices
• Choosing between regex and an LLM

Design ClickHouse tables and write faster analytical queries for large datasets. The skill covers MergeTree choices, partitioning and sort keys, batch ingestion, materialized views, performance checks, and common analyses such as time series, funnels, and cohorts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing ClickHouse tables for analytics
• Improving slow analytical SQL queries
• Loading large batches of data

Use this skill to design ClickHouse tables, improve analytical queries, and build data pipelines. It provides patterns for bulk and streaming inserts, materialized views, performance monitoring, and common analyses such as retention and funnels.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing tables for time-based analytics
• Optimizing slow ClickHouse queries
• Building bulk or streaming data loads

Use this pattern to help sub-agents find the code and project context they need. It starts with a broad search, rates file relevance, identifies gaps, and refines the query for up to three cycles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding relevant files before assigning a coding task
• Discovering project terminology and code patterns
• Reducing irrelevant context in a multi-agent workflow

Design LLM API pipelines that manage spending through task-based model selection and budget tracking. The skill also shows how to retry transient failures with backoff and cache long system prompts, while keeping cost records auditable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Route simple and complex requests to different models
• Track API spending against a defined budget
• Retry temporary network or rate limit failures

Apply ClickHouse patterns to analytical data work, from MergeTree table design and query optimization to bulk or streaming ingestion, materialized views, and performance checks. It also covers time-series, funnel, retention, and cohort analyses for large datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design MergeTree tables for analytical queries
• Speed up ClickHouse queries and aggregations
• Ingest large data batches or streams

This skill describes a Claude Code learning system that observes sessions through hooks and records small, confidence-rated behavior patterns called instincts. It keeps project-specific patterns separate from global ones, and can group instincts into reusable skills, commands, or agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning recurring coding preferences from Claude Code sessions
• Keeping framework-specific patterns scoped to their projects
• Reviewing confidence-rated instincts and their evidence

Plan a parser for repeated, structured text such as forms or quizzes. Start with regular expressions, score extraction confidence, and reserve large language model checks for uncertain cases that need review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Parsing quiz questions and answers
• Extracting data from forms or invoices
• Building a hybrid parser for repeated text

Use this skill to design LLM API workflows that track spending, choose models based on task complexity, retry temporary failures, and cache repeated prompts. It outlines how to combine these practices into a reusable pipeline with budget checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Routing simple and complex tasks to different models
• Tracking API spending against a set budget
• Retrying temporary API errors safely

Process and compare MS/MS spectra in metabolomics workflows. Build repeatable pipelines to import and clean spectra, standardize metadata, filter peaks, normalize intensities, and calculate similarity scores for library matching or clustering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cleaning MGF or MSP spectra before analysis
• Comparing query spectra with a reference library
• Scoring spectra for metabolomics clustering

Create Circos configuration files for circular views of genomic variation, chromosome structure, cell-to-cell communication, or custom data tracks. The generated files can be rendered as PNG or SVG figures with Circos, once the required rendering software is installed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Visualizing SNPs, CNVs, or structural variants
• Showing cell-to-cell communication networks
• Layering genomic data tracks in a circular plot

Query more than 40 bioinformatics services through a consistent Python interface. Retrieve and combine data from resources such as UniProt, KEGG, ChEMBL, and Reactome, map identifiers across databases, and explore pathways, annotations, sequences, and interaction networks in one workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine protein and pathway data from several databases
• Map identifiers between UniProt, KEGG, and ChEMBL
• Query pathway relations, annotations, or protein interactions

Clean and prepare tabular data with pandas and numpy. Handle missing values and duplicates, reshape and filter tables, merge datasets, scale numeric columns, convert types, aggregate results, and create derived features for analysis or later modeling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cleaning a CSV before analysis
• Reshaping a table from wide to long format
• Merging datasets and creating derived columns

Review FASTQC reports for sequencing data to identify quality problems and explain what the metrics indicate. Get actionable recommendations for RNA-seq, DNA-seq, or ChIP-seq, with batch summaries available when several reports need review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking read quality before downstream analysis
• Finding adapter contamination or duplicated reads
• Comparing quality across several FASTQC reports

Create a forest plot for a meta-analysis of continuous outcomes from a CSV of study means, standard deviations, and group sizes. The skill checks the input and produces a PNG chart, a CSV data table, and a summary of pooled effects and heterogeneity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Visualizing a meta-analysis of continuous outcomes
• Comparing intervention and control groups across studies
• Preparing a forest plot and results table from CSV data

Analyze genomic intervals with fast overlap queries, coverage tracks, reference sequence checks, and fragment workflows. The toolkit also converts genomic regions into discrete tokens for machine learning and provides Python bindings and command-line tools for notebooks, pipelines, and batch jobs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding overlaps between genomic region sets
• Generating WIG or BigWig coverage tracks
• Tokenizing genomic regions for machine learning

Create review-ready forest plots from meta-analysis or subgroup data in CSV or Excel files. Adjust odds ratio markers, confidence interval lines, colors, labels, and output format, with options to show pooled effects and subgroup results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a forest plot from meta-analysis data
• Styling odds ratio points and confidence intervals
• Displaying subgroup results in a plot

Creates a Radial Plot, also called a Galbraith Plot, from meta-analysis data in CSV format. The plot relates standardized effect sizes to precision, helping users inspect between-study heterogeneity, with a PNG image and data CSV as outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect heterogeneity across meta-analysis studies
• Create a Galbraith Plot from CSV data
• Identify studies outside the confidence band

Create and customize scientific and analytical plots in Python, from common charts to multi-panel figures and specialized plot types. Control figure elements with pyplot or the object-oriented interface, then export static files in PNG, PDF, or SVG formats.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Customizing plot labels, colors, legends, and layout in Python
• Building multi-panel figures for scientific analysis
• Creating heatmaps, contour plots, or other specialized charts