← Back to Skills Marketplace
tujinsama

Auto Data Analysis Claw

by Ricky · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
159
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install auto-data-analysis-claw
Description
自动化财务与业务数据分析,深度挖掘数据价值,生成专业报表。激活场景:用户提供财务报表(利润表、资产负债表、现金流量表)、业务数据(销售数据、运营数据、客户数据、成本数据),或要求进行数据分析、数据挖掘、报表生成、KPI计算、趋势分析、差异分析、同比环比分析、多维分析、数据清洗。触发关键词:分析数据、财务分析、业务...
README (SKILL.md)

自动化数据分析虾 🦐

对财务、业务数据进行深度挖掘,自动完成复杂业务逻辑处理,产出专业报表。

工作流程

1. 理解需求

明确以下要素(缺少则向用户确认):

  • 数据来源:文件路径/格式(CSV、Excel)或描述数据结构
  • 分析目标:用户最关心什么?(盈利?增长?效率?风险?)
  • 时间范围:分析哪个周期?
  • 对比基准:与上期比?与预算比?与行业比?

2. 数据加载与质量评估

使用 scripts/analyze.py profile 检查数据:

python3 scripts/analyze.py profile {文件路径}

关注:行数、字段类型、空值率、数值范围是否合理。发现异常数据立即告知用户。

3. 数据清洗

python3 scripts/analyze.py clean {文件路径} -o {输出路径}
  • 空值处理:数值列用中位数填充,分类列用众数填充
  • 全空列自动删除
  • 清洗后向用户确认数据量变化

4. 核心分析(根据场景选择)

通用分析

# 差异分析(环比、同比、分组对比)
python3 scripts/analyze.py variance {文件} --value {数值列} --period {时间列} --group {分组列}

# 趋势分析
python3 scripts/analyze.py trend {文件} --date {日期列} --value {数值列} --freq M

# 相关性分析
python3 scripts/analyze.py correlate {文件} --columns {列1} {列2} ...

KPI 计算

准备配置 JSON,然后执行:

python3 scripts/analyze.py kpi {文件} --config {kpi_config.json}

配置格式:

{"kpis": [
  {"name": "总收入", "formula": "sum(revenue)"},
  {"name": "平均毛利率", "formula": "mean(gross_margin_pct)"},
  {"name": "订单数", "formula": "count(order_id)"}
]}

5. 深度分析参考

根据分析场景加载对应参考资料:

  • 财务数据:阅读 references/financial-metrics.md(指标体系与公式)
  • 业务数据:阅读 references/business-analysis-patterns.md(分析场景与方法论)
  • 生成报表时:阅读 references/report-templates.md(结构与格式规范)

6. 生成报表

使用 scripts/report_generator.py 生成专业报表:

准备报表配置 JSON,然后执行:

python3 scripts/report_generator.py {report_config.json} -o {输出路径} --format markdown

配置格式:

{
  "title": "2025年度财务分析报告",
  "metadata": {"period": "2025-01 至 2025-12", "author": "数据分析虾"},
  "sections": [
    {"title": "执行摘要", "content": "核心发现概要...", "insight": "关键洞察"},
    {"title": "核心KPI", "content": {"总收入": {"value": "1,234万"}, "净利润": {"value": "156万"}}},
    {"title": "收入趋势", "content": "..."}
  ]
}

支持输出 Markdown 和 HTML 两种格式。

分析原则

  1. 先概览再深挖:先了解数据全貌,再针对重点展开
  2. 结论驱动:每个分析模块结束时总结 1-3 条结论
  3. 数据说话:用具体数字支撑观点,避免空泛描述
  4. 标注异常:发现偏离预期的数据点,主动提示风险
  5. 可操作性:最终输出应包含明确的行动建议

注意事项

  • pandas、numpy 是必需依赖,运行前确认已安装
  • 大数据集(超 100MB)建议先采样分析再全量处理
  • 敏感财务数据注意脱敏提示
  • 预测类分析需明确告知用户置信区间和局限性
Usage Guidance
This skill appears to do what it says: run the included Python scripts on files you provide and produce reports. Before running, (1) ensure pandas/numpy are installed; (2) review the scripts if you have sensitive data — they will read any file path you give them and write outputs to the provided output path; (3) run it in a sandbox or with non-sensitive sample data first; (4) avoid supplying secrets or system config files as input. If you need networked uploads or automated remote reporting, verify the code explicitly adds no outbound network calls before relying on it.
Capability Assessment
Purpose & Capability
Name/description match the included scripts and reference docs. The skill is a local data-analysis + report-generation tool; required libraries (pandas, numpy) are appropriate and no unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md confines runtime actions to loading user-provided CSV/Excel files, cleaning, analysis, and generating reports via the included Python scripts. It does not instruct reading system-wide configs, environment secrets, or sending data to external endpoints.
Install Mechanism
No install spec or remote downloads; code is included in the package and runs locally. The only runtime dependency callouts (pandas, numpy) are reasonable for the task.
Credentials
No environment variables, credentials, or config paths are requested. The skill reads files supplied by the user (CSV/Excel/config JSON) — which is expected for this use case.
Persistence & Privilege
always is false; the skill does not request persistent system-wide privileges or modify other skills. It writes outputs only to user-specified paths.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install auto-data-analysis-claw
  3. After installation, invoke the skill by name or use /auto-data-analysis-claw
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
初始发布:自动化财务与业务数据分析
Metadata
Slug auto-data-analysis-claw
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Auto Data Analysis Claw?

自动化财务与业务数据分析,深度挖掘数据价值,生成专业报表。激活场景:用户提供财务报表(利润表、资产负债表、现金流量表)、业务数据(销售数据、运营数据、客户数据、成本数据),或要求进行数据分析、数据挖掘、报表生成、KPI计算、趋势分析、差异分析、同比环比分析、多维分析、数据清洗。触发关键词:分析数据、财务分析、业务... It is an AI Agent Skill for Claude Code / OpenClaw, with 159 downloads so far.

How do I install Auto Data Analysis Claw?

Run "/install auto-data-analysis-claw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Auto Data Analysis Claw free?

Yes, Auto Data Analysis Claw is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Auto Data Analysis Claw support?

Auto Data Analysis Claw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Auto Data Analysis Claw?

It is built and maintained by Ricky (@tujinsama); the current version is v1.0.0.

💬 Comments