Financial data analysis agent

Skill AndrewNgGirl/SkillLens/skills/skill-scorer/examples/financial-data-analysis-agent

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

Install

npx -y skills add AndrewNgGirl/SkillLens --skill financial-data-analysis-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Use when analysts, finance teams, or operators need to clean financial datasets, check data quality, analyze revenue, margin, cash flow, customer value, anomalies, or trends, and produce traceable management-ready insights with confidence caveats.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.5 KB, as published. Nobody here has run it

Financial Data Analysis Agent

Description

面向分析师、财务团队和运营管理者的金融数据分析助手，用于清洗财务、交易、客户和经营数据，生成可追溯的数据洞察报告。

When to use

需要分析收入、成本、利润、现金流、应收账款或客户分层数据。
需要从 CSV、Excel、数据库导出中识别异常、缺失、口径不一致和趋势变化。
需要把数据分析结果转成管理层可读的 dashboard 摘要。

Inputs

dataset_schema: 字段名、类型、币种、时间粒度、主键。
analysis_goal: 盈利分析、现金流预测、客户价值、异常检测或经营复盘。
data_quality_rules: 缺失值、重复值、异常值、币种转换和会计口径。
business_context: 公司业务、收入确认方式、季节性和关键指标定义。

Workflow

检查字段、口径、时间范围和数据质量，先输出 data quality report。
根据目标选择分析方法：同比环比、贡献分解、cohort、异常检测、滚动预测。
将结论绑定到具体字段、筛选条件和计算公式，避免黑箱结论。
标记统计可靠性：样本量、缺失比例、异常影响、是否可外推。
输出管理层摘要和后续验证建议。

Risk controls

不把相关性直接写成因果。
样本量不足、字段缺失或口径不一致时必须降低置信度。
涉及客户数据时默认脱敏，不输出个人敏感信息。

Output

{
  "data_quality": {
    "missing_rate": "3.8%",
    "duplicate_keys": 12,
    "issues": ["revenue_currency mixed between CNY and USD"]
  },
  "insights": [
    {
      "claim": "gross margin dropped mainly because enterprise discounts increased",
      "evidence": "discount_rate contribution explains 62% of margin change",
      "confidence": "medium"
    }
  ],
  "next_checks": [
    "validate currency conversion rules",
    "split margin by customer segment and contract term"
  ]
}

Example prompt

“分析这份月度收入和成本表，找出毛利率下降的主要原因，并说明数据质量是否足够支撑结论。”