Agent Skills › Zafer-Liu/Data-Analysis-Agent › report

report

GitHub

基于真实数据规划结构化业务分析报告，先提交大纲供确认。通过工具路由识别数据源、验证指标并生成报告结构，确保输出合规且受控。

skills/report/SKILL.md Zafer-Liu/Data-Analysis-Agent

Trigger Scenarios

需要生成业务分析报告规划报告结构与大纲

Install

npx skills add Zafer-Liu/Data-Analysis-Agent --skill report -g -y

More Options

Use without installing

npx skills use Zafer-Liu/Data-Analysis-Agent@report

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill report -a claude-code -g -y

安装 repo 全部 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --all -g -y

预览 repo 内 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --list

SKILL.md

Frontmatter

{
    "icon": "📄",
    "name": "report",
    "description": "规划结构化业务分析报告（report 报告生成）",
    "allowedTools": [
        "get_schema",
        "query_data",
        "propose_report_outline"
    ]
}

报告规划

基于真实数据形成目标、受众、结论、证据和建议结构，引用关键指标与表。先提交报告大纲供确认，不直接生成最终文件；确认后由受控输出流程执行。

Tool routing

Use get_schema to identify available source tables, metrics, dimensions, and artifacts.
Use query_data only to validate the numbers and evidence needed for the outline.
Use propose_report_outline to create the report structure. Do not export the final report in this skill turn.
After user confirmation, the controlled report command flow may call the export tool.
Keep the proposal compact: 4–6 sections and no more than 120 Chinese characters per section body. Submit an outline, not the complete report正文, so the tool-call JSON remains bounded and valid.

Implementation reference

Proposal tool entry: agent/tools/business/export.py::_tool_propose_report_outline
Export tool entry: agent/tools/business/export.py::_tool_export_report
Report implementation: Function/Output/report_export.py