Loading...
Loading...
Found 207 Skills
Generates a Jupyter notebook that evaluates a fine-tuned SageMaker model using LLM-as-a-Judge. Use when the user says "evaluate my model", "how did my model perform", "compare models", or after a training job completes. Supports built-in and custom evaluation metrics, evaluation dataset setup, and judge model selection.
Generates a Jupyter notebook that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.
Use this skill when the user needs to look up or verify Goldsky blockchain dataset names, chain prefixes, dataset types, or versions. Triggers on questions like 'what\'s the dataset name for X?', 'what prefix does Goldsky use for chain Y?', 'what version should I use for Z?', or 'what datasets are available for Solana/Stellar/Arbitrum/etc?'. Also use for chain-specific dataset questions (e.g., polygon vs matic prefix, stellarnet balance datasets, solana token transfer dataset names). Do NOT trigger for questions about CLI commands, pipeline setup, or general Goldsky architecture unless the core question is about finding the right dataset name or chain prefix.
Build and deploy new Goldsky Turbo pipelines from scratch. Triggers on: 'build a pipeline', 'index X on Y chain', 'set up a pipeline', 'track transfers to postgres', or any request describing data to move from a chain/contract to a destination (postgres, clickhouse, kafka, s3, webhook). Covers the full workflow: requirements → dataset selection → YAML generation → validation → deploy. Not for debugging (use /turbo-doctor) or syntax lookups (use /turbo-pipelines).
Implements Syncfusion WinUI Cartesian Charts (SfCartesianChart) for data visualization in WinUI applications. Use this when working with column, line, bar, area, or financial charts (OHLC, Candle). This skill covers axis configuration, legends, tooltips, zooming/panning, data labels, and high-performance fast series for large datasets.
Implement and configure Syncfusion MultiColumnComboBox control in Windows Forms - an advanced combobox with multiple columns in dropdown and virtual data binding for large datasets. Use when creating dropdown lists with multiple data fields, DataSource binding, DisplayMember/ValueMember configuration, or column headers in dropdown. Covers filtered dropdown lists and replacing standard ComboBox with multi-column alternatives.
Instrument, trace, evaluate, and monitor LLM applications and AI agents with LangSmith. Use when setting up observability for LLM pipelines, running offline or online evaluations, managing prompts in the Prompt Hub, creating datasets for regression testing, or deploying agent servers. Triggers on: langsmith, langchain tracing, llm tracing, llm observability, llm evaluation, trace llm calls, @traceable, wrap_openai, langsmith evaluate, langsmith dataset, langsmith feedback, langsmith prompt hub, langsmith project, llm monitoring, llm debugging, llm quality, openevals, langsmith cli, langsmith experiment, annotate llm, llm judge.
Use when the user needs ML pipelines, statistical analysis, data preprocessing, feature engineering, model selection, experiment tracking, or data visualization. Triggers: dataset exploration, model training, feature engineering, hyperparameter tuning, experiment tracking setup, statistical hypothesis testing, visualization creation.
Guided, interactive exploration of statistical data via SDMX providers (Eurostat, OECD, ECB, World Bank, ISTAT, and others) using the opensdmx CLI. Use this skill whenever the user asks ANY question about statistics or data that could be answered with SDMX data — even if they don't mention SDMX, Eurostat, or any provider by name. Topics include demographics, economy, employment, births, deaths, population, prices, trade, health, agriculture, GDP, inflation, unemployment, fertility rates, migration, energy, education, poverty, housing, and any other statistical topic. Also use it when the user mentions a specific dataflow ID they want to explore. Trigger this skill even for implicit questions like "how many births were there in Italy last year?" or "I need EU unemployment data by age group" — these clearly need SDMX data even if the user doesn't say so. The skill guides the user step by step: discovers relevant datasets, proposes the most meaningful candidates, explores the schema using real constraints (not codelists), explains the dataset structure, and invites the user to make informed filter choices before fetching any data.
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
Runs metrics queries against Axiom MetricsDB via scripts. Discovers available metrics, tags, and tag values. Use when asked to query metrics, explore metric datasets, check metric values, or investigate OTel metrics data.
Writes Pest feature tests for Laravel HTTP controllers using repeatable controller-test patterns across web/session and API/JSON flows. Activates when creating or updating controller tests, nested resource route tests at any depth, CRUD action tests (create, destroy, edit, index, show, store, update), authorization and route-binding scope checks, validation datasets, transport-specific response assertions, and database persistence assertions.