메뉴
Auto-analysis middleware for uploaded tables. It profiles table rows, proposes metrics for user confirmation, executes accepted metrics with deterministic calculations, and emits frontend-ready analysis proposal/dashboard JSON for charts and dashboards.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when Codex or another agent needs to summarize the currently connected ChatBI business database, list queryable tables or views, explain what each table contains, show row counts, fields, semantic metrics, dimensions, aliases, or answer questions like 当前数据库有哪些表可以查, 数据库概览, 业务库结构, 表清单, schema 概述.
Use when Codex or another agent needs to answer Chinese natural-language data questions against the local ChatBI demo MySQL database, map business terms to governed metrics and dimensions, generate safe read-only SQL, execute metric queries, or return JSON/table results for sales, revenue, gross margin, target achievement, customer, retention, region, channel, product, and monthly trend analysis.
Use when Codex or another agent needs to add missing Chinese synonyms, aliases, or business phrasing to the local ChatBI semantic layer, especially when a natural-language query uses a new word that should map to an existing metric or dimension in alias_mapping. Supports safely inserting aliases for governed metrics and dimensions such as 销售额, 毛利, 目标完成率, 客户留存率, 区域, 时间, 部门, 产品类别, 产品名称, 渠道, and 客户类型.
BI chart recommendation for ChatBI and analytics workflows. Use when Codex needs to choose chart types and emit frontend-ready chart recommendation JSON from a user's analysis intent, Query Intent JSON, SQL result metadata, or tabular data, especially after natural language to SQL to data pipelines.
Use when the user asks for month-over-month (环比) comparison of business metrics such as sales, gross margin, order count, or customer count. Triggers on phrases like "环比", "上月对比", "月度对比", "和上个月比", "比上月", "月环比". Returns a comparison table with absolute change and percentage change, plus a grouped bar chart plan.
Dashboard auto-orchestration for ChatBI and analytics workflows. Use when Codex needs to generate a dashboard layout and frontend-ready dashboard JSON from multiple chart recommendations, Query Intent JSON objects, SQL result summaries, or BI analysis goals, especially when turning generated charts into a coherent dashboard.
| name | chatbi-auto-analysis |
| description | Auto-analysis middleware for uploaded tables. It profiles table rows, proposes metrics for user confirmation, executes accepted metrics with deterministic calculations, and emits frontend-ready analysis proposal/dashboard JSON for charts and dashboards. |
| trigger_conditions | ["chatbi-file-ingestion 已返回 rows，或对话含上传路径且需指标提案/采纳/看板","用户回复采纳、确认指标或要求上传表看板"] |
| when_not_to_use | ["尚无上传文件路径且无上一步 ingestion rows","演示库自然语言问数"] |
| required_context | ["上传路径或上一轮 file-ingestion 的 rows"] |
Use this skill after chatbi-file-ingestion has read an uploaded CSV/XLSX and returned rows.
charts, kpis, and dashboard_middleware so the frontend can render a full uploaded-file dashboard.PYTHONPATH=. .venv/bin/python skills/chatbi-auto-analysis/scripts/auto_analysis.py '{"question":"生成上传文件看板","rows":[...]}' --json
PYTHONPATH=. .venv/bin/python skills/chatbi-auto-analysis/scripts/auto_analysis.py '{"question":"采纳全部指标","mode":"execute","rows":[...]}' --json
need_confirmation or need_clarification with Markdown guidance.