Token导航 LogoToken导航

Agent Skill · 研究检索

tcs-expense-claim(tcs 费用报销)

tcs-expense-claim 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

tcs-expense-claim 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 33,045。

总安装 2,423周安装 103GitHub Stars 1下载 849核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:tcs-expense-claim(tcs 费用报销)
来源仓库:https://github.com/insanelyqurious/tcs-expense-claim
安装命令:
openclaw skills install tcs-expense-claim
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install tcs-expense-claim

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

商务旅行费用报销全流程处理器,支持收据与发票图像识别。自动归类消费项目并生成合规报销单据,减少人工录入。适用于频繁出差的企业员工与财务人员快速核销费用。上传图片需确保清晰可读,避免模糊或遮挡关键信息。tcs-expense-claim 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install tcs-expense-claim;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

tcs-expense-claim 怎么安装?

在终端执行 openclaw skills install tcs-expense-claim。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

tcs-expense-claim 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

tcs-expense-claim 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

tcs-expense-claim 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

tcs-expense-claim 用的人多吗?

公开数据是累计安装 2,423 次,近一周安装 103 次,下载 849 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

tcs-expense-claim 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
tcs-expense-claim

tcs 费用报销 · 本页

2,4231需要联网MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
expense-claim
description
>

Expense Claim Skill

Automates the full workflow of turning a pile of receipt images and PDFs into clean, submission-ready expense claim packages — sorted by date and category, with currency conversions and a summary table.


Workflow Overview

Run these five phases in order. Never skip a phase.

Phase 1 → Ingest & Parse all uploaded files
Phase 2 → Classify each bill (date, vendor, category, currency, amount)
Phase 3 → Generate per-day per-category PDFs
Phase 4 → Generate the expense spreadsheet (XLSX)
Phase 5 → Output summary tables for manual form entry

Phase 1 — Ingest & Parse

  1. List every file in /mnt/user-data/uploads/
  2. For each file:

- Images (.png, .jpg, .jpeg): read visually — extract date, vendor, amount, currency, bill number, and any GST/VAT breakdown - PDFs (.pdf): use pypdf to extract text; if text is sparse, treat as scanned and read visually

  1. Ask the user if any files are missing or unreadable before proceeding

Phase 2 — Classify

Map every bill to this schema:

date        : DD-Mon-YY   (e.g. 13-Feb-26)
vendor      : string
location    : city / airport / country
category    : one of the TCS categories below
currency    : INR | USD | EUR | GBP | SGD | AED | ...
amount_orig : float (as printed on bill)
bill_no     : string (from receipt; use "attached" if none)
notes       : brief description of items

TCS Expense Categories (map every bill to one)

TCS CategoryWhat goes here
Travel Expenses – ConveyanceUber, Ola, Lyft, taxis, local cabs, airport transfers
Ticket Expenses – Air TicketsAirline tickets, excess baggage fees (keep SEPARATE per bill)
Ticket Expenses – Train TicketsRail bookings
Ticket Expenses – Bus TicketsBus / coach bookings
Hotel AccommodationHotel folios, checkout invoices (NOT room dining — that's Meal)
Travel Expenses – MealAll food, beverages, airport snacks, restaurant bills, delivery (Zomato/Swiggy), cafe receipts
Client Entertainment – TravelMeals/entertainment where clients were present
Car ExpensesFuel, parking, tolls
Communication ExpensesSIM cards, roaming, internet dongles
Conference and Training CoursesRegistration fees, course materials

Special Rules

  • Room dining at a hotel → Meal (NOT Hotel Accommodation)
  • Zomato/Swiggy orders: bundle restaurant bill + platform fee + delivery fee

into ONE line item with the combined total

  • Delta / airline excess baggage → Air Tickets (separate PDF per bill)
  • Airport retail (water, snacks, chocolates) → Meal
  • Sweets / gifts (e.g. Kantis, mithai shops) → Meal (flag with note:

*"verify if gift policy applies"*)

  • Multiple bills same day same category → merged into one PDF

Phase 3 — Generate PDFs

Read /mnt/skills/public/pdf/SKILL.md before running this phase.

Naming convention:

DD_Mon_YYYY_<TCS_Category_Underscored>.pdf

Examples:

13_Feb_2026_Travel_Expenses_Conveyance.pdf
13_Feb_2026_Travel_Expenses_Meal.pdf
13_Feb_2026_Ticket_Expenses_Air_Tickets.pdf
20_Feb_2026_Hotel_Accommodation.pdf

Script to use: scripts/build_pdfs.py

  • Converts images → PDF pages using img2pdf + Pillow
  • Merges existing PDFs using pypdf
  • Outputs to /mnt/user-data/outputs/bills_by_category/

Run: python3 scripts/build_pdfs.py

Present all generated PDFs to the user using present_files.


Phase 4 — Generate XLSX Summary

Read /mnt/skills/public/xlsx/SKILL.md before running this phase.

Script to use: scripts/build_xlsx.py

The spreadsheet has two sheets:

Sheet 1: "All Expenses"

Columns: #, Date, Vendor, Location, Category, Currency, Amount (Original), Amount (INR equiv.), Notes

Color coding:

  • Blue fill → Travel / Conveyance / Air Tickets
  • Green fill → Food & Meal
  • Orange fill → Accommodation
  • Purple fill → Other

Sheet 2: "Summary"

Rows = TCS categories; Columns = Category, # Items, Original Amounts, INR Equiv. Plus a Grand Total row with all-in USD equivalent.

Currency conversion — use rates from references/fx_rates.md or fetch live rates if web search is available. Always show the rate used and its date.

Output to /mnt/user-data/outputs/expense_claim.xlsx


Phase 5 — Summary Tables for Manual Entry

Always output three tables in chat so the user can fill their expense portal directly:

Table A: Conveyance entries

Bill Date | From Location | To Location | Bill No | Currency | Amount | Remarks

Table B: Meal entries

Bill Date | Name of Hotel/Restaurant | Bill No | Currency | Amount | Remarks

Table C: Hotel entries

Bill Date | From Date | To Date | Bill No | Currency | Amount | Remarks

Table D: Air Ticket entries

Bill Date | Bill No | Currency | Amount | Remarks

Table E: Day-wise spend summary

Date | Conveyance | Air Ticket | Hotel | Meal (local currency) | Day Total (USD) — Include a GRAND TOTAL row at the bottom.


Currency Conversion Rules

See references/fx_rates.md for standard rates.

  • Always convert everything to INR for Indian domestic claims
  • Always convert everything to USD for international / global summary
  • Show the exchange rate used in every table and in the XLSX notes
  • If the trip spans multiple currencies, show original + converted in the XLSX
  • Flag any bill where the currency on the receipt doesn't match the card

currency (possible forex fee)


Output Checklist

Before finishing, confirm all of these exist:

  • [ ] One PDF per day per category in /mnt/user-data/outputs/bills_by_category/
  • [ ] expense_claim.xlsx with both sheets
  • [ ] Table A–E printed in chat
  • [ ] Grand total in USD stated clearly
  • [ ] Any flagged items noted (gift policy, missing bills, illegible receipts)

Error Handling

ProblemAction
Can't read a receiptNote it, ask user to confirm amount manually
Date missing from billInfer from surrounding bills or ask user
Currency ambiguousDefault to country of purchase; flag for user
Bill number not on receiptUse "attached"
Multiple receipts same vendor same dayMerge into one line, note qty

Reference Files

  • references/fx_rates.md — Standard FX rates for common travel corridors
  • references/tcs_categories.md — Full TCS category eligibility rules
  • scripts/build_pdfs.py — PDF generation script
  • scripts/build_xlsx.py — Excel generation script

平台分布

OpenClaw

93.19%
按下载量换算791

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills