Back to Details

recap

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Financial Recap

财务回顾

Generate a narrative financial review for any time period.
生成任意时间段的叙述式财务复盘。

Workflow

工作流

  1. Determine the period. Parse 
    $ARGUMENTS
    for the time span:
    • "this week", "last week" → weekly
    • "this month", "january", "jan 2025", "2025-01" → monthly (default if no argument)
    • "this quarter", "Q1", "Q1 2025" → quarterly
    • "this year", "2025", "year in review" → yearly
    • Any explicit date range works too
  2. Fetch summary data. Call the 
    query
    MCP tool with 
    compare: "prior_period"
    :
    json
    { "period": "<detected_period>", "compare": "prior_period", "include": ["ratios", "anomalies", "accounts"] }
    (Use 
    start
    /
    end
    if a specific date range was requested.)
  3. Fetch year-ago comparison. For anything other than year-over-year, also fetch the same period from a year ago to account for seasonality:
    json
    { "start": "<same_period_last_year_start>", "end": "<same_period_last_year_end>", "include": ["ratios"] }
    For example, if reviewing February 2026, also fetch February 2025.
  4. Fetch recurring bills. Call the 
    query
    MCP tool:
    json
    { "recurring": true }
  5. Synthesize a narrative recap covering:
    • Headline numbers: total income, total expenses, net cash flow, savings rate
    • vs. prior period: changes from the immediately preceding period (last week, last month, etc.)
    • vs. same period last year: seasonal context — note whether changes are normal for this time of year or unusual (skip this section for year-over-year recaps)
    • Anomalies: unusual transactions or spending spikes
    • Recurring bills: new, changed, or cancelled subscriptions/bills
    • Key ratios: any ratios returned in the summary (e.g. expense-to-income)
    • Account balances: current balances and changes
  6. Tone: Stick to the facts. Report what happened without judgement — no "great job" or "you need to cut back." Just clear, plain-language observations. Skip categories with trivial amounts.
  1. 确定时间段。 解析 
    $ARGUMENTS
    获取时间范围：
    • "this week", "last week" → 周度
    • "this month", "january", "jan 2025", "2025-01" → 月度（无参数时默认）
    • "this quarter", "Q1", "Q1 2025" → 季度
    • "this year", "2025", "year in review" → 年度
    • 任何明确的日期范围也适用
  2. 获取汇总数据。 调用 
    query
    MCP 工具，参数为 
    compare: "prior_period"
    ：
    json
    { "period": "<detected_period>", "compare": "prior_period", "include": ["ratios", "anomalies", "accounts"] }
    （如果请求了特定日期范围，请使用 
    start
    /
    end
    参数。）
  3. 获取上年同期对比数据。 除同比回顾外的所有场景，还需获取上年同一时间段的数据以考量季节性因素：
    json
    { "start": "<same_period_last_year_start>", "end": "<same_period_last_year_end>", "include": ["ratios"] }
    例如，如果复盘2026年2月，同时获取2025年2月的数据。
  4. 获取定期账单。 调用 
    query
    MCP 工具：
    json
    { "recurring": true }
  5. 整合生成叙述式回顾，涵盖以下内容：
    • 核心数据：总收入、总支出、净现金流、储蓄率
    • 与上一周期对比：与紧邻的上一周期（上周、上月等）相比的变化
    • 与上年同期对比：季节性背景——说明变化是每年该时间段的正常情况还是异常情况（同比回顾可跳过此部分）
    • 异常项：不寻常的交易或支出激增
    • 定期账单：新增、变更或取消的订阅/账单
    • 关键比率：汇总返回的任意比率（例如支出收入比）
    • 账户余额：当前余额及变动情况
  6. 语气：基于事实陈述。客观汇报发生的情况，不做评判——不要出现“做得好”或者“你需要削减开支”这类表述。仅提供清晰、平实的观察结果。金额可忽略不计的类别直接跳过。