cash-flow-snapshot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Cash Flow Snapshot

现金流快照

Produces a 30/60/90-day cash flow forecast with percentage-variance confidence bands and named risk flags. Delivers a two-part output: a concise chat summary and a downloadable XLSX workbook.

Quick start

"Will I make payroll next month?"

Claude pulls AR/AP and fixed costs from connected sources, calculates expected inflows and outflows across 30, 60, and 90-day windows, applies confidence bands based on each customer's historical payment variance, and flags specific risks by name.

生成带有百分比方差置信区间和命名风险标记的30/60/90天现金流预测。提供两部分输出内容：简洁的聊天摘要和可下载的XLSX工作簿。

快速入门

“下个月我能发工资吗？”

Claude从已连接的数据源提取AR/AP和固定成本数据，计算30、60、90天周期内的预期流入和流出资金，基于每位客户的历史付款方差应用置信区间，并按名称标记特定风险。

Workflow

工作流程

Step 1 — Identify available data sources

步骤1 — 识别可用数据源

Check which connectors are live. Try in this order:

QuickBooks — primary source for AR aging, AP, and fixed costs
PayPal — transaction history and settlement timing
Stripe — charge and payout history
Square — sales and payout history
CSV upload — fallback if no connector is connected

If no connector is live and no file is attached, ask the user to either connect a source or upload a CSV (income/expense tabular data, any reasonable format). Note which sources were used in the output — this affects confidence band width.

检查哪些连接器处于可用状态，按以下顺序尝试：

QuickBooks — 获取AR账龄、AP及固定成本的主要数据源
PayPal — 交易历史和结算时间数据
Stripe — 收费和付款历史数据
Square — 销售和付款历史数据
CSV上传 — 若没有连接器可用则作为备选方案

若没有可用的连接器且未附加文件，请用户连接数据源或上传CSV文件（收入/支出表格数据，支持任何合理格式）。在输出中注明使用的数据源——这会影响置信区间的宽度。

Step 2 — Pull the data

步骤2 — 提取数据

From QuickBooks:

AR aging report: customer name, invoice amount, invoice date, due date, days outstanding
AP: vendor name, amount due, due date
Recurring fixed costs: rent, payroll, subscriptions (look for recurring transactions)

From PayPal / Stripe / Square:

Settlement history: transaction date, amount, settlement date
Use settlement lag (transaction date → payout date) to compute each source's average and variance payment delay

From CSV upload:

Parse as income/expense tabular data
Required columns (flexible naming): date, amount, type (income or expense), description
If columns are ambiguous, show the header row and ask the user to confirm mapping

从QuickBooks提取：

AR账龄报告：客户名称、发票金额、发票日期、到期日、逾期天数
AP数据：供应商名称、应付金额、到期日
recurring固定成本：租金、工资、订阅费用（查找重复交易记录）

从PayPal / Stripe / Square提取：

结算历史：交易日期、金额、结算日期
使用结算延迟（交易日期→付款日期）计算每个数据源的平均付款延迟时间及方差

从CSV上传提取：

解析为收入/支出表格数据
必填列（命名灵活）：日期、金额、类型（收入或支出）、描述
若列含义不明确，显示表头行并请用户确认映射关系

Step 3 — Compute historical payment timing

步骤3 — 计算历史付款时间

For each AR customer (or income source from CSV), calculate:

Mean payment lag — average days from invoice/transaction date to receipt
Payment variance — standard deviation of payment lag across last 6–12 payments
Use variance to set confidence band width (see Step 4)

If fewer than 3 payments exist for a customer, use the population mean as the point estimate and apply a ±30% variance band as the default. When running on CSV data with sufficient history (≥3 payments per source), compute the band from the actual payment variance — do not assume ±30%.

针对每位AR客户（或CSV中的收入来源），计算：

平均付款延迟 — 从发票/交易日期到收款的平均天数
付款方差 — 过去6-12次付款的付款延迟标准差
使用方差设置置信区间宽度（见步骤4）

若某客户的付款记录少于3条，则使用总体均值作为点估计值，并默认应用±30%的方差区间。当CSV数据有足够历史记录（每个来源≥3次付款）时，根据实际付款方差计算区间——不默认使用±30%。

Step 4 — Build the 30/60/90-day forecast

步骤4 — 构建30/60/90天预测

Produce three time windows: 0–30 days, 31–60 days, 61–90 days.

For each window, compute:

Line	Method
Expected inflows	AR due in window, adjusted for mean payment lag
Expected outflows	AP due in window + fixed costs falling in window
Net cash position	Inflows − Outflows
Confidence band	± weighted average payment variance as a % of expected inflows

Confidence band formula:

band_pct = weighted_avg_stddev_days / avg_payment_lag_days
low  = net_cash × (1 − band_pct)
high = net_cash × (1 + band_pct)

Round band_pct to one decimal place. Cap at ±50% — higher variance means the data is too thin to model; flag it instead (see Step 5).

生成三个时间周期：0-30天、31-60天、61-90天。

针对每个周期，计算：

项目	计算方法
预期流入	周期内到期的AR金额，根据平均付款延迟调整
预期流出	周期内到期的AP金额 + 周期内产生的固定成本
净现金头寸	流入金额 − 流出金额
置信区间	± 加权平均付款方差占预期流入的百分比

置信区间公式：

band_pct = weighted_avg_stddev_days / avg_payment_lag_days
low  = net_cash × (1 − band_pct)
high = net_cash × (1 + band_pct)

将band_pct四舍五入至一位小数。上限为±50%——更高的方差意味着数据量不足无法建模，需标记为风险（见步骤5）。

Step 5 — Flag named risks

步骤5 — 标记命名风险

Scan for conditions that push the low-band estimate negative or create a liquidity crunch. For each risk found, produce a one-line flag:

Late-payer risk: "Customer X historically pays 18 days late; that shifts their $8,400 invoice out of the 30-day window into day 48."
Payroll crunch: "Payroll ($22,000) hits April 15. Low-band cash on hand April 14: $19,200. Shortfall risk: $2,800."
Thin data warning: "Only 2 payments on record for Customer Y — confidence band set to default ±30%."
No-connector warning: "Running on CSV data only — no real-time AP or recurring cost data. Confidence bands are wider than normal."

Limit to the top 5 risks by severity (largest dollar impact first).

扫描导致区间下限估计为负值或出现流动性短缺的情况。针对发现的每个风险，生成一行标记：

延迟付款风险：“客户X历史付款平均延迟18天；这将使其8400美元的发票从30天周期推迟至第48天。”
工资发放短缺风险：“工资（22000美元）将于4月15日发放。4月14日的区间下限现金余额为19200美元。短缺风险：2800美元。”
数据量不足警告：“客户Y仅有2条付款记录——置信区间设置为默认±30%。”
无连接器警告：“仅基于CSV数据运行——无实时AP或重复成本数据。置信区间比正常情况更宽。”

按影响严重程度（美元金额从大到小）限制最多显示5个风险。

Step 6 — Deliver outputs

步骤6 — 交付输出

Chat summary (always):

Cash Flow Snapshot — [date range]
Source(s): [connectors used]

            Expected    Low       High
30-day net: $X,XXX     $X,XXX    $X,XXX
60-day net: $X,XXX     $X,XXX    $X,XXX
90-day net: $X,XXX     $X,XXX    $X,XXX

⚠ Risks flagged: [count]
  • [risk 1]
  • [risk 2]
  ...

XLSX workbook (always): Read

xlsx/SKILL.md

before generating. Produce a workbook with three sheets:

Summary — the 30/60/90 forecast table with confidence bands. Beneath each window row, expand inline sub-rows showing the individual transactions that make up its inflows (green) and outflows (red). This makes the estimates auditable without leaving the Summary sheet.
Detail — all transactions grouped by window, sorted by date within each group. Include a running net column (cumulative inflows minus outflows within the window) and a subtotal row at the bottom of each window showing total inflows, total outflows, and net. Grey out past transactions in a separate section at the bottom for reference. Ensure all three windows have rows even if one is empty — show a "No transactions in this window" placeholder row.
Risks — the flagged risks with dollar impact and affected window.

Save as

cash-flow-snapshot-[YYYY-MM-DD].xlsx

聊天摘要（必选）：

现金流快照 — [日期范围]
数据源：[使用的连接器]

            预期值    区间下限  区间上限
30天净现金：$X,XXX     $X,XXX    $X,XXX
60天净现金：$X,XXX     $X,XXX    $X,XXX
90天净现金：$X,XXX     $X,XXX    $X,XXX

⚠ 标记的风险数量：[数量]
  • [风险1]
  • [风险2]
  ...

XLSX工作簿（必选）：生成前请阅读

xlsx/SKILL.md

。生成包含三个工作表的工作簿：

摘要 — 带有置信区间的30/60/90天预测表格。在每个周期行下方展开内嵌子行，显示构成该周期流入（绿色）和流出（红色）的具体交易记录。无需离开摘要工作表即可核查估算依据。
明细 — 所有交易按周期分组，每个周期内按日期排序。包含累计净现金列（周期内累计流入减去流出），每个周期底部显示小计行，包含总流入、总流出和净现金。在底部单独区域灰化显示过往交易记录供参考。即使某周期为空，也要确保三个周期都有行——显示“此周期无交易记录”占位行。
风险 — 标记的风险及其美元影响和受影响的周期。

保存为

cash-flow-snapshot-[YYYY-MM-DD].xlsx

。

Approval gates

审批环节

No destructive actions — this skill is read-only. No approval gate required before generating the forecast.

Remind the user after delivery:

"This forecast is based on [sources listed]. It is not a substitute for accounting advice — verify with your bookkeeper before making financing decisions."

无破坏性操作——此技能为只读模式。生成预测前无需审批环节。

交付后提醒用户：

“本预测基于[列出的数据源]。不能替代会计建议——做出融资决策前请与簿记员核实。”

Reference files

参考文件

File	Load when
`reference/gotchas.md`	When a connector returns unexpected data or variance is extreme
`reference/examples/worked-example.md`	When modeling the output format for a new data shape

文件	加载时机
`reference/gotchas.md`	当连接器返回意外数据或方差异常时
`reference/examples/worked-example.md`	针对新数据形状建模输出格式时