Rockfish-Data
OrganizationA tackle box of Claude skills for the Rockfish synthetic data SDK.
Categories
Indexed Skills (7)
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, stateful, or derived columns, state machines, timeseries with seasonality, entity relationships (foreign keys, composite keys, parent/child fan-out, self-references), or realistic PII-like values (names, emails, addresses, SSNs) via NamedEntityProvider. Also generates OpenTelemetry telemetry from a service call graph — distributed-trace span trees with correlated RED metrics and logs derived from the same spans. Trigger on phrases like "generate synthetic data", "fake data from a schema", "create a test dataset", "GenerateFromDataSchema", "OpenTelemetry / span / trace / call-graph data", or mentions of entity/foreign-key/state-machine data.
inject-incidents
Inject synthetic incidents (instantaneous spike, sustained magnitude change, data outage, value ramp) into a time-series dataset and evaluate analytics agents with `rockfish.agentfuel` — incident math and ground-truth generation run locally, no remote service. Covers the whole agentfuel toolkit; typed incident configs with boolean SQL test cases verified via DataFusion, Claude-backed natural-language prompts, variations, and answer grading, plus the pandas-based suite generators (analytics aggregation questions, scenario Q&A templates, stateful event/state analysis). Trigger on phrases like "inject an incident", "incident injection", "inject an anomaly", "add a spike to this series", "simulate an outage", "scenario injection", "evaluate my analytics agent", "generate a test suite from my data", "ground-truth test cases from an anomaly", "event/state questions from an event log", "agentfuel", or mentions of `rockfish.agentfuel` or the removed `rockfish.labs.scenarios`, which this skill replaces.
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`.
snowflake-analyst
Explore, analyze, and load data in Snowflake the way you would local CSV files — list databases/schemas/tables like listing directories, inspect a table's columns, preview or sample rows, profile column statistics, and import generated/local data into a table. Use when a user wants to look at, understand, summarize, pull from, or write to a Snowflake table, warehouse, or database. Trigger on phrases like "what's in my Snowflake", "list the tables", "describe this table", "sample/preview a Snowflake table", "profile the columns", "run a query against Snowflake", "how big is this table", "export a Snowflake table to CSV", or "load/import/upload/write data into Snowflake". Built to stay cheap on large tables — computation is pushed to the warehouse and only small results cross the network.
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`.
snowflake-analyst
Explore, analyze, and load data in Snowflake the way you would local CSV files — list databases/schemas/tables like listing directories, inspect a table's columns, preview or sample rows, profile column statistics, and import generated/local data into a table. Use when a user wants to look at, understand, summarize, pull from, or write to a Snowflake table, warehouse, or database. Trigger on phrases like "what's in my Snowflake", "list the tables", "describe this table", "sample/preview a Snowflake table", "profile the columns", "run a query against Snowflake", "how big is this table", "export a Snowflake table to CSV", or "load/import/upload/write data into Snowflake". Built to stay cheap on large tables — computation is pushed to the warehouse and only small results cross the network.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.