From ai-analyst
Switches active dataset: validates target in data_sources.yaml with fuzzy matching, checks manifest.yaml, updates active.yaml pointer and history, confirms with summary of tables, date range, connection. Triggered by /switch-dataset or phrases like 'switch to dataset'.
npx claudepluginhub ai-analyst-lab/ai-analyst-plugin --plugin ai-analystThis skill uses the workspace's default tool permissions.
Change the active dataset. Updates the active pointer, validates the target dataset exists, and confirms with a summary of what's now active.
Guides connection of CSV files, DuckDB, MotherDuck, PostgreSQL, BigQuery, and Snowflake datasets with credential setup, validation, schema profiling, and knowledge brain integration.
Create and manage Hugging Face Hub datasets: initialize repos, configure prompts/metadata, stream row updates, and query/transform data with DuckDB SQL.
Creates, manages, queries Arize datasets and examples via ax CLI: CRUD ops, append examples, export data, file-based creation for test/eval sets.
Share bugs, ideas, or general feedback.
Change the active dataset. Updates the active pointer, validates the target dataset exists, and confirms with a summary of what's now active.
Invoke as /switch-dataset {name} when the user wants to analyze a different dataset than the currently active one.
data_sources.yaml to check if {name} exists as a registered source<workspace>/knowledge/datasets/{name}/manifest.yaml exists/connect-data to set it up."<workspace>/knowledge/active.yamlactive_dataset to {name}switch_history (cap at 20 entries, FIFO)<workspace>/knowledge/active.yamlRead the target dataset's manifest.yaml and display:
Switched to: {display_name}
Tables: {table_count}
Date range: {date_range}
Connection: {connection.type} ({connection.database}.{connection.schema})
Last analysis: {last_used or "none"}
Metrics defined: {count from metrics/index.yaml or 0}