Data analysis, machine learning, LLM apps, and prompt design (9.2K skills)
Helps startup leaders make strategic data decisions: assess permission to train AI on customer data, choose data architecture, evaluate customer data as a business asset, and sequence hiring around the decisions the business needs to make.
Evaluate a Claude Managed Agent against a written rubric, a set of checkable criteria, and guide improvements within a fixed attempt limit. After a version passes, prepare separate evaluation cases to check performance beyond the examples used for revision.
Scope a Claude Managed Agent through six questions about its job, trigger, inputs, actions, success criteria, and recurrence. Produce a validated build sheet with configuration components, deferred features, and an evaluation plan, without requiring an API key.
Coordinate AI agents acting as company executives through shared question and response formats. The skill defines limits on repeated calls, independent analysis, peer checks, conflict reporting, and decision records to support cross-functional reviews and board meetings.
Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.
Creates charts from numerical data using the chart tool and Chart.js v4. Supports bars, lines, pies, scatter plots, and other formats to show comparisons, trends, proportions, and relationships, with options for dataset colors and mixed charts.
Analyze reviews, surveys, and other user feedback by user group. Summarize satisfaction scores, recurring complaints, positive themes, and the goals users want to achieve, then recommend product improvements based on frequency, severity, and business impact.
Design a product metrics dashboard with clearly defined measures, data sources, charts, targets, and alert thresholds. The skill produces a Markdown specification that also covers dashboard layout, review schedules, and responsibilities for responding to alerts.
Analyze users grouped by signup period or another shared characteristic to compare retention and feature adoption over time. Produce charts, highlight unusual changes, and recommend follow-up research or experiments to investigate the patterns.
Turn everyday questions into SQL queries, the commands used to retrieve and summarize database records. Uses your database structure and platform to produce queries with explanations, performance notes, and optional validation scripts.
Analyze A/B test results to decide whether to launch a change, extend testing, stop, or investigate further. Check sample size, statistical significance, uncertainty ranges, and effects on other important metrics, then summarize the recommendation and next steps.
Generate text and images through a reverse-engineered Gemini Web API, an interface reconstructed from the web service. Use reference images for descriptions or variations, and continue conversations across requests with saved sessions.
Retune a collection of skills for a new model using archived runs and controlled comparisons. Establish normal measurement variation, register success criteria before editing, and make targeted changes until measured behavior meets the criteria or a specific limitation is reported.
Manage the AI models offered through OpenWork, including model additions, removals, aliases, and pricing discounts. Validate configuration consistency and trigger the GitHub workflow that refreshes models from models.dev, then report its merge or failure result.
Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.
Build Python applications that collect live cryptocurrency prices, trades, and order books with Cryptofeed. Covers consistent data formats across exchanges, price comparisons, and writing incoming data to storage systems for monitoring and analysis.
Develop applications with the Claude API using examples from Anthropic's official cookbooks. Explore document summarization, image analysis, document retrieval, external tool calls, and prompt caching through practical Python code and implementation guidance.
Read market details and public order prices directly from Polymarket. Match outcomes such as Yes or No to their token identifiers, then use the best buying and selling prices to calculate a midpoint.
Convert queries, schema definitions, and stored procedures from database dialects such as Oracle and Teradata into BigQuery GoogleSQL. Coordinate single-query or batch translation, configure conversion rules, and inspect errors and behavioral differences in the results.
Create, deploy, and troubleshoot custom functions in BigQuery for calculations, data processing, and API calls. Choose among SQL, JavaScript, Python, and externally hosted functions, with guidance on dependencies, permissions, and validation.
Design a Google Cloud system for data analysis or machine learning with AI agents. Turn requirements into product choices, an architecture diagram, infrastructure configuration, deployment instructions, and validation steps, with user reviews between phases.
Design hybrid search on AlloyDB by combining meaning-based search, keywords, and SQL filters. Turn requirements into architecture diagrams, database setup scripts, deployment guidance, and validation plans for search applications on Google Cloud.
Design AI agent analytics workflows across distributed tables and documents. Combine Knowledge Catalog for metadata, meaning information about data and its usage rules, with managed Spark processing to produce architecture diagrams, deployment guidance, and validation plans.
Design an enterprise search system that answers questions using retrieved company content, an approach called RAG. Gather requirements and produce architecture diagrams, deployment guidance, and validation plans using GKE, AlloyDB, and open models.