Rockfish-Data
OrganizationA tackle box of Claude skills for the Rockfish synthetic data SDK.
Categories
Indexed Skills (2)
generate-from-schema
Generate synthetic datasets from a schema specification using the Rockfish SDK. Use when a user wants to create synthetic tabular or time-series data with specific structure — independent or derived columns, state machines, timeseries, entity relationships (including composite foreign keys), or realistic PII-like values (names, emails, addresses, SSNs) via NamedEntityProvider. Trigger on phrases like "generate synthetic data", "fake data from a schema", "create a test dataset", "GenerateFromDataSchema", or mentions of entity/foreign-key/state-machine data.
inject-scenarios
Inject synthetic scenarios (spike, outage, ramp, shift) into a time-series dataset using the Rockfish labs scenarios service. Use when a user wants to perturb a baseline time series for ML robustness testing, root-cause-analysis drills, or anomaly-detection evaluation — and optionally generate Q&A test cases from the perturbation. Trigger on phrases like "inject an anomaly", "add a spike to this series", "simulate an outage", "scenario injection", or mentions of `rockfish.labs.scenarios`.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.