数据诊断

SkillAI & models

Lets your agent inspect data schemas, quality, and analysis readiness.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the 数据诊断 skill

About this capability

View data structure, quality, and analyzability (schema data overview profiling)

What this skill tells your AI

The instructions your AI receives, as published by zafer-liu/data-analysis-agent in skills/data/SKILL.md and read by ahel’s review.

先获取 schema 和必要样本，报告表规模、字段类型、缺失、重复、异常、时间范围和关键分布。区分事实、风险与建议，指出可直接分析的字段及需要用户确认的口径。

Use get_schema first to inspect tables, fields, row counts, and source structure.
Use get_table_detail when one table needs deeper field-level metadata.
Use profile_data for data quality, missingness, type, and distribution diagnostics.
Use query_data for small verification samples or targeted aggregates.
Use generate_chart only when a compact diagnostic chart materially helps explain the data.

Advanced