What makes Yaohx Expense Tracker notable?

1.1K downloads. Trust evidence available

How should Yaohx Expense Tracker be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Yaohx Expense Tracker

个人记账助手。当用户发送消费信息（文本或支付截图）时自动识别并记录到本地消费数据库；支持按月归档、分类统计、查看消费记录、生成月度消费报告。触发词：记账、账单、消费记录、花了多少钱、月度总结、消费报告、看看本月消费等。This skill should be used when the user mentions... Skill: Yaohx Expense Tracker Owner: yaohx-star Summary: 个人记账助手。当用户发送消费信息（文本或支付截图）时自动识别并记录到本地消费数据库；支持按月归档、分类统计、查看消费记录、生成月度消费报告。触发词：记账、账单、消费记录、花了多少钱、月度总结、消费报告、看看本月消费等。This skill should be used when the user mentions... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-07-11T14:24:48.513Z | auto - Major refactor for skill structure and documentation to clarify usage and workflow. - Updated and greatly expanded SKILL.md:

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.3release · observed Jul 11, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1735rtand3mccspdcq16nv2g1887kma:yaohx-expense-tracker

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yaohx-star-yaohx-expense-tracker/snapshot"

Documentation

CLAWHUB

35,756 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: yaohx-expense-tracker
description: "个人记账助手。当用户发送消费信息（文本或支付截图）时自动识别并记录到本地消费数据库；支持按月归档、分类统计、查看消费记录、生成月度消费报告。触发词：记账、账单、消费记录、花了多少钱、月度总结、消费报告、看看本月消费等。This skill should be used when the user mentions recording an expense, checking spending, or requesting a consumption report."
agent_created: true
---

# 记账助手 (Expense Tracker)

## 概述

一个纯本地处理的个人记账技能。支持文本输入和支付截图两种方式记录消费，按月归档到本地 JSON 文件，支持消费分类管理、记录查询、月度报告生成。所有数据存储和处理均在本地完成，不依赖任何云端 API。

## 数据存储位置

所有数据文件存放在工作区根目录下（即当前工作目录）：

| 文件/目录 | 说明 |
|---|---|
| `categories.json` | 消费分类定义文件 |
| `expenses/` | 消费记录目录 |
| `expenses/expenses-YYYYMM.json` | 按月份的消费记录文件 |

数据格式详见 `references/data_schema.md`。

## 触发场景

1. **文本记账**：用户发送消费描述，如 "午餐花了25元"、"打车15块"
2. **图片记账**：用户发送微信支付/支付宝截图，直接识图后记录
3. **手动记录**：用户说"记账"并提供详细信息
4. **查看记录**：用户说"看看本月消费"、"本月花了多少"
5. **月度报告**：用户说"生成本月消费报告"、"月度总结"
6. **删除记录**：用户说"删除刚才那条记录"、"删掉某笔消费"

## 工作流程

### 初始化（首次使用时执行）

当用户首次使用记账功能时，先执行初始化：

```bash
python scripts/init_db.py
```

此脚本在工作区根目录创建：
- `categories.json`（含默认分类）
- `expenses/` 目录
- 当前月份的 `expenses/expenses-YYYYMM.json` 空文件

### 流程 A：处理文本账单

1. 从用户消息中提取关键信息：日期、时间、金额、商家、消费类别、支付方式、备注
2. 如果用户未提供日期/时间，默认使用当前日期和时间
3. 根据商家名称和备注，自动匹配消费分类（匹配规则见下方）
4. 调用脚本写入记录
5. 回复用户确认记录成功，展示本次消费摘要和本月累计

**关键：调用脚本时使用独立参数，绝不传递 JSON 字符串**

正确调用方式：

```bash
python scripts/record_expense.py --amount 25 --merchant "兰州拉面" --category "餐饮" --date 2026-07-09 --time 1230 --payment "微信" --note "午餐"
```

参数说明：
- `--amount`：金额（数字，必填）
- `--merchant`：商家名称（必填）
- `--category`：消费分类（可选，不传则自动匹配）
- `--date`：日期，格式 YYYY-MM-DD（可选，默认今天）
- `--time`：时间，格式 HHMM（可选，默认当前时间）
- `--payment`：支付方式（可选，如 微信/支付宝/现金/银行卡）
- `--note`：备注（可选）

### 流程 B：处理图片账单（支付截图）

**根据模型能力选择路径：**

#### 路径 B1：多模态模型（能直接识图）

如果你是多模态模型，可以直接观察图片：

1. 用户发送支付截图后，直接观察图片，提取以下信息：
   - 金额（必填）
   - 商家/收款方名称
   - 支付方式（微信/支付宝等）
   - 交易时间（如图片中可见）
   - 备注/商品说明
2. 将提取结果展示给用户确认（如有不确定的信息请用户补充）
3. 用户确认后，使用独立参数调用 `record_expense.py` 写入记录
4. 回复确认

#### 路径 B2：非多模态模型（无法识图，使用本地 OCR）

如果你无法直接观察图片（非多模态模型），使用本地 OCR 脚本提取文字：

1. 获取用户发送的截图文件路径
2. 调用 OCR 脚本提取文字和结构化信息：

```bash
python scripts/ocr_image.py --image "截图文件路径"
```

脚本使用 rapidocr-onnxruntime 进行本地 OCR：

3. OCR 脚本输出 JSON 格式结果：

```json
{
  "success": true,
  "raw_text": "微信支付 ¥25.00 向兰州拉面付款...",
  "structured": {
    "amount": 25.00,
    "merchant": "兰州拉面",
    "date": "2026-07-09",
    "time": "1230",
    "payment": "微信",
    "note": null
  },
  "method": "rapidocr"
}
```

4. 读取 `structured` 中的字段，如果关键信息（金额、商家）已提取到，展示给用户确认后调用 `record_expense.py` 写入记录
5. 如果 `structured` 中部分字段为 null，根据 `raw_text` 上下文自行推断补充，或请用户手动补充缺失信息
6. 如果 OCR 脚本返回 `"success": false`，说明 OCR 不可用，此时**必须**请用户手动输入消费信息（金额、商家等），不要直接报错终止

OCR 不可用时输出示例：
```json
{
  "success": false,
  "error": "rapidocr-onnxruntime not installed",
  "install_hint": "pip install rapidocr-onnxruntime",
  "fallback_instruction": "OCR is not available. Please ask the user to manually input the expense details."
}
```

**OCR 依赖安装（非多模态模型必须安装）：**

如需使用图片记账功能，运行：
```bash
python -m pip install rapidocr-onnxruntime
```

如果未安装 rapidocr，OCR 脚本会返回 `fallback

_meta.json

{
  "ownerId": "kn74k9gxerd67wztxke01p3js188715p",
  "slug": "yaohx-expense-tracker",
  "version": "1.0.3",
  "publishedAt": 1783779888513
}

skill-card.md

## Description:

Yaohx Expense Tracker helps an agent record local personal expenses from text or payment screenshots, query monthly spending, manage categories, delete records, and generate monthly spending reports.

This skill is ready for commercial/non-commercial use.

## Publisher:

[yaohx-star](https://clawhub.ai/user/yaohx-star)

### License/Terms of Use:

MIT-0

## Use Case:

External users can use this skill with an agent to maintain a local personal expense ledger, capture spending from natural-language notes or payment screenshots, and review monthly spending summaries.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Deleting financial records can remove a user's source-of-truth expense data if the wrong record is selected.

Mitigation: Ask the user to confirm the exact record identifier and visible expense details before running a deletion workflow.

Risk: The optional OCR path recommends installing an unpinned dependency.

Mitigation: Install OCR dependencies only in a controlled environment with pinned, trusted package versions.

Risk: The release evidence warns that expected supporting scripts may be missing from the installed package.

Mitigation: Verify the installed package includes the required scripts before relying on recording, OCR, listing, reporting, or deletion workflows.

## Reference(s):

- [Server-resolved GitHub source repository](https://github.com/yaohx-star/yaohx-expense-tracker)
- [ClawHub skill page](https://clawhub.ai/yaohx-star/skills/yaohx-expense-tracker)
- [Publisher profile](https://clawhub.ai/user/yaohx-star)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Plain text or Markdown with shell command examples and JSON-shaped script outputs]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create or update local categories and monthly expense JSON files when the supporting scripts are present.]

## Skill Version(s):

1.0.3 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular