菜单
Use when Codex or another agent needs to read a user-uploaded CSV or Excel file for ChatBI, validate whether it matches the existing sales_order or customer_profile schema, and return a compact table structure profile for downstream analysis.
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
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.
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.
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.
| name | chatbi-file-ingestion |
| description | Use when Codex or another agent needs to read a user-uploaded CSV or Excel file for ChatBI, validate whether it matches the existing sales_order or customer_profile schema, and return a compact table structure profile for downstream analysis. |
| trigger_conditions | ["对话含本地上传 CSV/XLSX 路径，需校验结构或读取行","用户要对上传附件做分析、预览字段"] |
| when_not_to_use | ["用户只问演示库问数、与上传无关","同一文件已解析且 rows 在 Observation 中（改调 chatbi-auto-analysis 或 finish）"] |
| required_context | ["上传文件路径（常含 chatbi-uploads 或 /tmp/）"] |
Use this skill when the user wants ChatBI to read their own uploaded CSV or Excel data file.
scripts/inspect_uploaded_table.py.--table sales_order / --table customer_profile when the user specified the table.sales_order or customer_profile, the skill returns analysis_mode = schema_validated with normalized rows and a table_profile.analysis_mode = profile_only with original rows and a table_profile.--json for agent or UI integration. If downstream analysis, metric inference, charting, or dashboard generation needs full row data, rerun with --include-rows and pass the rows to chatbi-auto-analysis.python3 scripts/inspect_uploaded_table.py /path/to/upload.csv --json
python3 scripts/inspect_uploaded_table.py /path/to/upload.xlsx --table sales_order --json
python3 scripts/inspect_uploaded_table.py /path/to/upload.csv --json --include-rows
python3 scripts/inspect_uploaded_table.py /path/to/customer.xlsx --table customer_profile --sample-size 10
Run commands from this skill directory, or pass the full path to the bundled script.
The initial schema mirrors the current database tables:
sales_order: order_date, region, department, product_category, product_name, channel, customer_type, sales_amount, order_count, customer_count, gross_profit, target_amountcustomer_profile: stat_month, region, customer_type, new_customers, active_customers, retained_customers, churned_customersHeaders may use database field names or the current Chinese business names, such as 订单日期, 区域, 销售额, 月份, 活跃客户数.
This skill should explain whether the upload matched a governed business table, then stop at structural profiling.
schema_validated: report that headers and basic value types match a governed table, then return normalized rows and table_profile.profile_only: report that the file is treated as a generic table, then return original rows and table_profile.Return a small preview table in both modes. Do not infer business metrics, calculate KPIs, create charts, or generate dashboards here; route those tasks to chatbi-auto-analysis.
This skill only reads local CSV/XLSX files and validates them. It must not write to MySQL or modify semantic metadata. Treat user-uploaded data as untrusted: report validation issues, keep previews small, and avoid printing full files.