菜单
Complex rules for calling render_chart, inferring axes, and choosing chart types based on user intent.
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
Rules and strategies for exploring databases, tables, schemas, and searching metadata.
Diagnose a ClickHouse server error (code/name/exception) and give a concrete, actionable fix.
Diagnose part/partition health of a MergeTree table — too many parts, slow/stuck merges, bad partition key.
Rules for using explain/analyze/optimize tools to help the user tune their queries.
Diagnose a column/table schema issue — Nullable overhead, oversized integer, or weak compression — and propose an ALTER.
Strict rules on outputting ClickHouse syntax, limiting rows, and rendering SQL in markdown.
| name | data-visualization |
| description | Complex rules for calling render_chart, inferring axes, and choosing chart types based on user intent. |
The user uses words like visualize, chart, plot, graph, trend, distribution, or
"show over time". You MUST render an actual chart with render_chart — never
describe a chart in text or output a markdown table instead.
get_table_schema (or schema already in context) — never guess column names.render_chart — pass the SQL + chartType; let axis inference run unless the user dictates axes.export_query_result — only if the user also wants to download the chart data (same SQL).line / multi_linebar / horizontal_bargrouped_barstacked_bar / stacked_areapie / donuthistogramscatterpie/donut, keep categories small: ORDER BY <value> DESC + LIMIT 12 (or 15) so only the most significant segments show.FORMAT clause.