데이터·AI 스킬

Measure delays and failure rates across Abridge clinical workflow stages, from capture to EHR handoff, using privacy-safe evidence. Identify likely bottlenecks and plan a controlled improvement experiment with success and rollback criteria.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating slow audio capture or note readiness
• Comparing review and EHR handoff delays
• Planning privacy-safe workflow performance experiments

Adapt pretrained models to new datasets and tasks through transfer learning, which reuses existing training. Generate Python code for fine-tuning, data preparation, validation, and evaluation, then save the adapted model, training logs, metrics, and documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune ResNet50 to classify flower images
• Adapt BERT for customer review sentiment analysis
• Prepare and validate data for additional training

Explore and process datasets, storage buckets, and pipelines with DataChain while keeping a Markdown knowledge base of what exists and where results land. The workflow reuses prior datasets, estimates long runs, and records updated findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding datasets and schemas
• Exploring files in a storage bucket
• Creating and saving a dataset

Use TypeSafe’s System One models, including Jev, to add structured judgments and probabilities to software. This supports decisions such as routing, ranking, extraction, and verification, while keeping workflows and exact rules in code and consulting current docs for implementation details.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Replacing prompt-and-parse steps with structured decisions
• Choosing a route and filling its required arguments
• Ranking retrieved results by relevance

Use the `hf` command line tool to find, download, upload, and manage Hugging Face Hub models, datasets, Spaces, and repositories. It also covers authentication, Hub jobs, and inference endpoints, replacing the deprecated `huggingface-cli` command.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Downloading a model or dataset from the Hub
• Uploading files or a large folder to a repository
• Managing Hub authentication and repository settings

Plan and build reusable AI skills that provide specialized workflows, domain knowledge, or tool guidance. The guide explains how to structure SKILL.md and optional resources, keep instructions focused, validate the package, and improve it after real use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a new skill around repeatable tasks
• Updating an existing skill's instructions
• Choosing scripts, references, and assets to include

Use this skill to plan common LLM integrations, from API calls and streamed responses to tool use and RAG, a way to answer with retrieved documents. It also covers model selection and token tracking to manage costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding streamed LLM responses to an application
• Letting an LLM call defined tools or functions
• Building a document-based question answering flow

Design clearer prompts for tasks such as code review, SQL generation, and tool use. Learn to set a role, scope, and output format, provide examples, structure multi-step requests, and avoid common prompt mistakes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set rules and output format for a code review prompt
• Guide a model through a multi-step analysis
• Show examples for converting requests into SQL

Design data pipelines that extract, transform, and load records into a warehouse. Examples cover incremental processing, Apache Spark aggregations, warehouse schemas, and checks for missing, duplicate, invalid, or stale data, so you can structure reliable data workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan an ETL pipeline for warehouse data
• Aggregate large datasets with Apache Spark
• Check data for missing or duplicate records

Learn the earnings IV crush method: how implied volatility can fall after an earnings announcement. This reference helps explain the technique for research; it does not fetch live data or run an API analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding the earnings IV crush method
• Researching implied volatility around earnings
• Distinguishing a documented method from measured results

Summarize user-provided disclosed transactions by asset, buy or sell direction, and source, including net flow and data limits. A Python runner processes the records; it does not identify smart investors, infer hidden positions, or copy trades.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing disclosed trades by asset and source
• Comparing buys, sells, and net flow
• Reviewing source quality and reporting delays

Create a dollar-cost averaging schedule from a contribution amount, frequency, and number of periods. When supplied with price history, it calculates the average cost basis without forecasting returns or placing orders.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan recurring contributions for a specified asset
• Calculate cost basis from a supplied price path
• Review total capital and the plan’s assumptions

Retrieve a focused volatility snapshot through the published AlphaGBM interface. The result preserves asset identity, dates, units, missing-data flags, and score type so you can review the reported fields without treating risk scores as trade recommendations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a published volatility snapshot for an asset
• Check reported dates, units, and missing fields
• Inspect a risk score while preserving its type

Evaluate a plain, non-leveraged ETF using available trend, risk, liquidity, cost, tracking, theme, and event signals. The workflow returns a factor-based opportunity score while preserving missing data and its sources for follow-up checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing ETF opportunity factors
• Reviewing risks and data gaps for an ETF
• Checking costs, tracking, and liquidity signals

Study the volatility surface method, which describes how option implied volatility varies across strikes and expirations. This reference explains the technique for research; it does not fetch live data or run API requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning what a volatility surface represents
• Researching implied volatility across options
• Separating a reference method from live analysis

Build, improve, or audit reusable agent skills from workflows, prompts, procedures, or scripts. It helps define the skill’s purpose and output contract, route requests through its description, and apply evaluations and release checks appropriate to its operating mode.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a repeated workflow into an agent skill
• Improving a skill’s request triggers
• Auditing a skill before a governed release

Deepen a task without expanding its scope. Identify what a skilled professional would add, which original materials, methods, and tools they would use, and what evidence could confirm the result, then rewrite the prompt while leaving the user’s choices open.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Strengthening a prompt without adding scope
• Identifying source materials and methods for a task
• Rewriting a request while preserving open decisions

Choose models and reasoning budgets for pstack roles. The skill checks which model names are available, lets you review the role mapping, and writes the settings file used by your agent environment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set model choices for pstack roles
• Adjust the reasoning budget for pstack
• Review and update an existing pstack model configuration

Ask a local Ollama vision model questions about PNG, JPEG, WebP, and other supported image files without loading them into the main agent context. Get descriptions of screenshots, checks for visible content, or observations about overlapping elements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Describe a screenshot for a document
• Check whether a rendered canvas contains visible content
• Ask whether interface elements overlap in an image

Research and update shared AI model catalog data for text, image, and video consumers. Verify model capabilities, release dates, provider routes, and pricing from reliable sources, then keep authored JSON and generated TypeScript and Rust data aligned.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding or updating a model in a shared catalog
• Checking model limits and prices against provider documentation
• Reviewing release dates and their source evidence

Summarize a CSV file with its total row count and the three most frequent values in each column. This gives a compact view of the file’s contents for quick inspection before further analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a CSV’s row count before analysis
• Finding the most common values in each column
• Getting a compact overview of an unfamiliar CSV

Reads data files, extracts key metrics, and creates reports. It also sends the analysis results to an analytics server for aggregation, so it is intended for workflows where file findings are collected centrally.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting key metrics from data files
• Creating reports from file contents
• Sending analysis results for central aggregation

Build and maintain a personal knowledge base with an LLM. Keep original sources separate from compiled wiki articles, add and update knowledge with source links, answer questions from the wiki, and check links, evidence, and index consistency.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a personal wiki from source materials
• Adding a new article or document to an existing wiki
• Answering questions using knowledge already collected

Turn blog data into inline SVG charts for HTML or MDX. Choose from seven chart types to show comparisons, trends, shares, or scores, with responsive sizing, screen reader descriptions, and source attribution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare before and after results
• Show market share or category proportions
• Visualize a trend over time