Menu
Coordinate crawler, parser, synthesizer, and reviewer agents for AI4S data production.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Designs and builds ETL/ELT data pipelines. Takes data sources, destination, transformation requirements. Generates pipeline code (Python/SQL), scheduling config, error handling, monitoring setup, and data quality checks. Outputs data-pipeline-spec.md + implementation files.
Review AI4S generated data for structure, scientific consistency, and hallucination risk.
Use MinerU to parse scientific PDFs into structured JSON for AI4S data generation.
Generate Sci-Evo style AI4S training data from structured paper content.
Based on SOC occupation classification
| name | pipeline-orchestration |
| description | Coordinate crawler, parser, synthesizer, and reviewer agents for AI4S data production. |
Use this skill when coordinating multiple agents across the AI4S data production pipeline.
Keep the pipeline explainable. Each generated task should have a clear input, expected output, assigned agent, and stopping condition.
