finance-tools
Skill0 starsChanged 3 months agoMITView on GitHub
财务分析工具集 v1.1.0。7个子命令覆盖财务分析全流程。 自动识别CSV中的金额、日期、类别列。 纯Python标准库，无外部依赖。
In this repository12 other files it gives its agents.
- bundle-lintSkill
- csv-toolsSkill
- dependency-scanSkill
- excel2insights-proSkill
- excel2insightsSkill
- expert2skillSkill
- fitness-dailySkill
- malware-scanSkill
- runtime-probeSkill
- skill-complianceSkill
- study-abroad-assistantSkill
- sum2slides-proSkill
The file
Files
⚠️ 免责声明：本工具为辅助性参考工具，不构成投资建议，不构成法律建议。市场有风险，投资需谨慎；据此操作，风险自担。正式合规意见请咨询具备资质的律师。最终决策与责任由使用者自行承担。 仅供学习研究参考；> 仅供参考，不构成任何操作依据；市场有风险，投资需谨慎，据此操作风险自担。
💰 Finance Tools v1.1.0
Overview
自动识别CSV中的金额列(amount/收入/支出)、日期列(date/日期)、类别列(category/类型)，无需手动指定列名。7个子命令覆盖从基础分析到预测的全流程。
Usage
analyze — 收支分析（扩展版）
python3 scripts/finance_tools.py analyze --file transactions.csv
# 📊 财务分析 — transactions.csv
# 总交易数: 1,200
# 收入合计: 485,230.00
# 支出合计: 312,450.00
# 净额: 172,780.00
# 收支比: 1.55x
# P25: 120.00 | P75: 850.00
#
# 月度净额:
# 2026-01: 145,000.00ratios — 财务比率（扩充版）
python3 scripts/finance_tools.py ratios --file financials.csv
# 📈 财务比率分析 — financials.csv
# revenue: 1,250,000.00 cost: 875,000.00
# 毛利率: 30.00%
# ROE(净资产收益率): 18.50%
# ROI(投资回报率): 12.30%trend — 月度趋势（含移动平均）
python3 scripts/finance_tools.py trend --file income.csv --ma 3
# 📈 月度趋势分析 — income.csv
# 月份 金额 环比 同比 MA-3
# 2026-01 98,500.00 — — 98,500.00
# 2026-02 102,300.00 +3.9% — 100,400.00category — 分类汇总 (NEW)
python3 scripts/finance_tools.py category --file transactions.csv
# 📂 分类汇总 — transactions.csv
# ████████████████ 工资 350,000.00 (72.1%)
# ██████ 餐饮 45,200.00 ( 9.3%)budget — 预算对比 (NEW)
python3 scripts/finance_tools.py budget --file actual.csv --budget-file budget.csv
# 📋 预算 vs 实际
# 类别 实际 预算 差异 执行率
# 工资 350,000 360,000 -10,000 97.2%yoy — 同比环比 (NEW)
python3 scripts/finance_tools.py yoy --file revenue.csv
# 📊 同比/环比增长分析
# 月份 金额 环比(MoM) 同比(YoY)
# 2026-01 98,500 — —
# 2026-02 102,300 +3.9% +5.2%forecast — 趋势预测 (NEW)
python3 scripts/finance_tools.py forecast --file revenue.csv --periods 6
# 🔮 趋势预测 — revenue.csv
# 模型: 线性增长 (斜率=+2,350.00/月, R²=0.923)
# 2026-07: 112,000.00 (+3.2% 预测增长)列名自动识别
| 角色 | 匹配关键词 |
| 金额 | amount, 金额, revenue, 收入, expense, 支出, cost, 成本, profit, 利润, actual, budget |
| 日期 | date, 日期, time, 时间, month, 月份, period, 期间 |
| 类别 | category, 类别, type, 类型, name, 名称, department, project |
Use Cases
- 个人理财: analyze 月度汇总 + category 分类 + forecast 支出预测
- 小企业: ratios 财务比率 + yoy 同比 + budget 预算管理
- 团队预算: budget 执行率 + trend 趋势 + forecast 预测
Security
- ✅ 纯本地运行，无网络请求
- ✅ 只读输入文件
- ❌ 无任意代码执行
- ❌ 无系统命令执行
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.