菜单
Multi-step structured analysis with visible progress tracking — enables create_plan and update_plan tools
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Sequence cleaning steps in a chain — trim/case/replace, null handling, deduplication, and type casting — in the right order. Use when raw ingested data needs cleaning before joins or aggregation.
Place Assert and Schema Validation nodes as gates that halt a chain when data is wrong, so bad data never reaches the output. Use when the pipeline must guarantee correctness before exporting or loading downstream.
Choose the right sink format, compression, and destination for a chain's output, and decide between exporting a file vs creating a table. Use at the end of a pipeline when deciding how to persist results.
Best practices for loading files into a chain — single file, folder globs, type detection, and union of many files. Use when the pipeline starts from CSV/Parquet/JSON/Excel files or a folder of files.
Decide between Merge (stack rows / UNION) and Join (match on a key) when a chain has multiple inputs, and set keys and join type correctly. Use when a pipeline combines two or more upstream tables.
Descompone un objetivo de procesamiento en un flujo de nodos Chains (source → transform → sink). Use when the user wants to build a data pipeline / chain, or describes an end-to-end "load X, clean it, summarize, export" goal.
| name | Análisis con Plan de Pasos |
| description | Multi-step structured analysis with visible progress tracking — enables create_plan and update_plan tools |
| keywords | complex, detailed, comprehensive, thorough, plan, structured, completo, detallado, exhaustivo, paso a paso, planificar, análisis completo, profundo |
| next | null |
Esta skill activa las herramientas de planificación (create_plan y update_plan) para análisis complejos que requieren múltiples pasos. El usuario puede ver el progreso en tiempo real.
create_plan PRIMERO con el objetivo y todos los pasos antes de ejecutar nadaupdate_plan después de CADA paso (done/failed/skipped)ask_user si hay ambigüedad genuina que bloquea el progresofinal_answer cuando todos los pasos estén completosPara un análisis completo típico:
Máximo 10 pasos — si necesitas más, agrupa pasos relacionados.
update_plan — el usuario ve el progreso en vivofailed con una nota y continuar con alternativatool_hint en cada paso para que el usuario sepa qué herramienta se usará