Use when you have PR review comments to address and want to evaluate each comment's validity before deciding to fix, reply, or skip
Use when creating new pipeline templates (YAML + seed files) for DataGenFlow. Guides through block selection, YAML authoring, seed file creation, and validation. Use for any task involving lib/templates/ directory, adding new template use cases, or creating seed files that match pipeline variables.
Use when creating new blocks for DataGenFlow pipeline system or modifying existing blocks to ensure consistency with established patterns
Use when testing pipelines end-to-end - running single-seed dry runs, batch generation, result analysis, and iterating on prompt quality. Use after creating a pipeline template, when validating output quality, or when improving generation results. Not for debugging crashes (use debugging-pipelines instead).
Use when creating data generation pipelines with DataGenFlow's extensibility system — user_templates, user_blocks, docker-compose setup, and dgf CLI. Use for any task involving generating synthetic data, building custom pipelines, or extending DataGenFlow from an external project without modifying its source.
Use when writing Playwright end-to-end tests for DataGenFlow UI. Covers test file creation, database cleanup, navigation, file uploads, confirmation modals, and job monitoring. Use for new UI features, extending existing test suites (pipelines, generator, review, settings), or verifying UI flows after frontend changes.
Use when setting up LLM or embedding models in DataGenFlow via Settings page or API. Guides through provider-specific configuration for OpenAI, Anthropic, Gemini, and Ollama. Use for first-time setup, adding new providers, troubleshooting connection failures, or migrating from .env fallback to proper model configs.
Use after completing implementation to review code quality, user impact, test coverage, and documentation before creating a PR