expense-report — Invoice → Categorized Excel
Extract invoice information from images or text, classify expenses, and generate
a professional Excel report with subtotals per category.
When to Use
- User has invoice photos / scanned receipts to process
- User describes expenses in text and wants them organized
- User needs a categorized reimbursement report (报销单)
- User mentions 发票报销, 报销汇总, 发票整理, expense report
Expense Categories
| Category |
Keywords / Examples |
| 业务招待 |
客户餐费, 商务宴请, 礼品, 招待 |
| 差旅-交通 |
机票, 火车票, 高铁, 出租车, 打车, 网约车, 加油, 过路费, 停车费 |
| 差旅-住宿 |
酒店, 住宿, 宾馆 |
| 差旅-餐饮 |
出差期间餐费, 工作餐 |
| 办公用品 |
文具, 打印, 办公耗材, 办公设备 |
| 通讯费 |
话费, 流量, 网费, 宽带 |
| 其他 |
不属于以上类别的费用 |
Workflow (MANDATORY)
Step 1: Collect Invoice Data
Accept input in any of these forms:
- Images: Read invoice photos using the Read tool. Extract: date, vendor, amount, item type, notes.
- Text descriptions: Parse the user's text for the same fields.
- Mixed: Multiple images + supplementary text.
For each invoice, extract these fields:
{
"date": "2026-04-15",
"vendor": "海底捞(国贸店)",
"item": "客户餐费",
"amount": 486.00,
"category": "业务招待",
"note": "与XX公司李总晚餐"
}
Step 2: Classify
Assign each invoice to a category from the table above. Rules:
- If the user explicitly states the category, use it.
- If the item/vendor clearly matches a category keyword, auto-assign.
- For ambiguous items (e.g., "餐费" could be 业务招待 or 差旅-餐饮):
- If the note mentions a client/customer → 业务招待
- If the context is a business trip → 差旅-餐饮
- If unclear, ask the user.
Step 3: Confirm with User
Before generating, show the extracted data as a table:
| # | 日期 | 商户 | 项目 | 金额 | 分类 | 备注 |
|---|------|------|------|------|------|------|
| 1 | 2026-04-15 | 海底捞 | 客户餐费 | 486.00 | 业务招待 | 与XX公司李总 |
| 2 | 2026-04-14 | 滴滴出行 | 打车 | 45.50 | 差旅-交通 | 机场→酒店 |
Use AskUserQuestion to ask: "以上信息是否正确? 需要修改或补充吗?"
Step 4: Generate Excel
Write the confirmed data to a temp JSON file, then run:
python expense-report-skill/scripts/generate_report.py \
--input /tmp/invoices.json \
--output "发票报销汇总-YYYYMMDD.xlsx"
JSON format (array of objects):
[
{"date": "2026-04-15", "vendor": "海底捞", "item": "客户餐费", "amount": 486.0, "category": "业务招待", "note": "与XX公司李总"},
{"date": "2026-04-14", "vendor": "滴滴出行", "item": "打车", "amount": 45.5, "category": "差旅-交通", "note": "机场→酒店"}
]
Step 5: Deliver
Tell the user:
- Output file path
- Total amount and breakdown by category
- Remind them to review the "分类汇总" sheet for the summary
Output Format
The Excel file contains two sheets:
- 发票报销汇总 — Full detail, grouped by category with subtotals
- 分类汇总 — Summary table: category, count, subtotal
Style: Lovstudio warm-academic (terracotta headers #CC785C, warm cream accents).
Edge Cases
- Blurry/unreadable image: Tell the user which fields couldn't be extracted; ask them to provide manually.
- Foreign currency: Note the currency; convert to CNY if user provides rate, otherwise keep original with note.
- Duplicate invoices: Flag potential duplicates (same date + vendor + amount) before generating.
- No date on invoice: Use the date the user provides, or mark as "日期不详".
1---2name: sgc-expense-report3description: Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), travel-meals, office supplies, communication, and other. Use when the user mentions "发票报销", "expense report", "报销单", "发票整理", "invoice", "报销汇总", "发票分类", "reimbursement", or has invoice images to process.4license: MIT5---67# expense-report — Invoice → Categorized Excel89Extract invoice information from images or text, classify expenses, and generate10a professional Excel report with subtotals per category.1112## When to Use1314- User has invoice photos / scanned receipts to process15- User describes expenses in text and wants them organized16- User needs a categorized reimbursement report (报销单)17- User mentions 发票报销, 报销汇总, 发票整理, expense report1819## Expense Categories2021| Category | Keywords / Examples |22|----------|-------------------|23| 业务招待 | 客户餐费, 商务宴请, 礼品, 招待 |24| 差旅-交通 | 机票, 火车票, 高铁, 出租车, 打车, 网约车, 加油, 过路费, 停车费 |25| 差旅-住宿 | 酒店, 住宿, 宾馆 |26| 差旅-餐饮 | 出差期间餐费, 工作餐 |27| 办公用品 | 文具, 打印, 办公耗材, 办公设备 |28| 通讯费 | 话费, 流量, 网费, 宽带 |29| 其他 | 不属于以上类别的费用 |3031## Workflow (MANDATORY)3233### Step 1: Collect Invoice Data3435Accept input in any of these forms:3637- **Images**: Read invoice photos using the Read tool. Extract: date, vendor, amount, item type, notes.38- **Text descriptions**: Parse the user's text for the same fields.39- **Mixed**: Multiple images + supplementary text.4041For each invoice, extract these fields:4243```json44{45 "date": "2026-04-15",46 "vendor": "海底捞(国贸店)",47 "item": "客户餐费",48 "amount": 486.00,49 "category": "业务招待",50 "note": "与XX公司李总晚餐"51}52```5354### Step 2: Classify5556Assign each invoice to a category from the table above. Rules:57581. If the user explicitly states the category, use it.592. If the item/vendor clearly matches a category keyword, auto-assign.603. For ambiguous items (e.g., "餐费" could be 业务招待 or 差旅-餐饮):61 - If the note mentions a client/customer → 业务招待62 - If the context is a business trip → 差旅-餐饮63 - If unclear, ask the user.6465### Step 3: Confirm with User6667Before generating, show the extracted data as a table:6869```70| # | 日期 | 商户 | 项目 | 金额 | 分类 | 备注 |71|---|------|------|------|------|------|------|72| 1 | 2026-04-15 | 海底捞 | 客户餐费 | 486.00 | 业务招待 | 与XX公司李总 |73| 2 | 2026-04-14 | 滴滴出行 | 打车 | 45.50 | 差旅-交通 | 机场→酒店 |74```7576Use `AskUserQuestion` to ask: "以上信息是否正确? 需要修改或补充吗?"7778### Step 4: Generate Excel7980Write the confirmed data to a temp JSON file, then run:8182```bash83python expense-report-skill/scripts/generate_report.py \84 --input /tmp/invoices.json \85 --output "发票报销汇总-YYYYMMDD.xlsx"86```8788**JSON format** (array of objects):8990```json91[92 {"date": "2026-04-15", "vendor": "海底捞", "item": "客户餐费", "amount": 486.0, "category": "业务招待", "note": "与XX公司李总"},93 {"date": "2026-04-14", "vendor": "滴滴出行", "item": "打车", "amount": 45.5, "category": "差旅-交通", "note": "机场→酒店"}94]95```9697### Step 5: Deliver9899Tell the user:100- Output file path101- Total amount and breakdown by category102- Remind them to review the "分类汇总" sheet for the summary103104## Output Format105106The Excel file contains two sheets:1071081. **发票报销汇总** — Full detail, grouped by category with subtotals1092. **分类汇总** — Summary table: category, count, subtotal110111Style: Lovstudio warm-academic (terracotta headers #CC785C, warm cream accents).112113## Edge Cases114115- **Blurry/unreadable image**: Tell the user which fields couldn't be extracted; ask them to provide manually.116- **Foreign currency**: Note the currency; convert to CNY if user provides rate, otherwise keep original with note.117- **Duplicate invoices**: Flag potential duplicates (same date + vendor + amount) before generating.118- **No date on invoice**: Use the date the user provides, or mark as "日期不详".
lovstudio