Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever…
Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table…
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics…
Run destructive tenant-data operator subcommands via the atlas-operator binary — proactive enable/disable, seed prompts/workspace, ops wipe, backfill-crm-leads, smoke-crm, teardown-verify-accounts, gate-export. Use when asked to wipe, seed, backfill, smoke-test, tear down, or export gate decisions from…
Publish or bump an @useatlas/ npm package. Use when bumping a version in packages/types, schemas, sdk, react, plugin-sdk, or webhook-publisher, when pushing release tags, or when Deploy Validation scaffolds fail on npm install after a version change.
Create, generate, verify, or deploy Apache Flink streaming SQL jobs from a natural-language description — windowed aggregations (tumbling/hopping/session), running totals, top-N, deduplication, filters, and interval/temporal joins, plus Kafka topic->topic pipelines. Use whenever the user wants a Flink/streaming job…