Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From sdg-hub
Runs synthetic data generation via sdg_hub flows: detects environment, executes generation, and presents results with row counts and error details.
npx claudepluginhub red-hat-ai-innovation-team/sdg_hub --plugin sdg-hubHow this skill is triggered — by the user, by Claude, or both
Slash command
/sdg-hub:data-generationThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute synthetic data generation using sdg_hub flows. For approach selection, custom flow authoring, and block reference, consult the `synthetic-data-generation` skill.
Sets up sdg_hub for synthetic data generation: detects environment, installs if needed, collects API keys and model config.
Generates story-driven synthetic data for Databricks using Spark, Faker, and Pandas UDFs. Supports serverless execution, Parquet/JSON/CSV/Delta outputs, scales from thousands to millions of rows.
Generates synthetic test inputs for LLM pipeline evaluation using dimension-based tuples. Bootstrap eval datasets when real data is sparse or stress-test specific failure hypotheses.
Share bugs, ideas, or general feedback.
Execute synthetic data generation using sdg_hub flows. For approach selection, custom flow authoring, and block reference, consult the synthetic-data-generation skill.
"${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh"
library=missing or config=missing: invoke the setup-guide skill.library=installed, config=found)Proceed to Step 2.
If the user doesn't specify a flow, invoke the flow-browser skill to find one.
Recommend starting with --sample 2 for a dry run.
"${CLAUDE_PLUGIN_ROOT}/scripts/sdg_generate.sh" $ARGUMENTS
If generation failed, consult the synthetic-data-generation skill for troubleshooting.