← 返回 Skills 市场

Expense Tracker Daily

Name: Expense Tracker Daily
Author: glorysunshine

作者 GlorySunshine · GitHub ↗ · v1.0.2 · MIT-0

cross-platform ✓ 安全检测通过

157

总下载

当前安装

版本数

在 OpenClaw 中安装

/install expense-tracker-daily

功能描述

智能记账助手。当用户提到记账、花钱、支出、消费、花费、记录开销、查账、统计支出、账单等意图时触发。支持自然语言输入（"午饭花了35"、"打车25块"、"昨天买衣服200"），自动分类，多维度统计分析。关键词：记账, 花钱, 支出, 消费, 花费, 账单, 查账, 统计支出, 记录开销, 钱花哪了, 月度统计.

使用说明 (SKILL.md)

\r \r

智能记账\r

核心脚本\r

\r 所有数据操作通过 scripts/expense_tracker.py 完成：\r \r

SKILL_DIR = {SKILL_DIR}\r
PYTHON = python\r
SCRIPT = "{SKILL_DIR}/scripts/expense_tracker.py"\r
```\r
\r
### 命令列表\r
\r
| 命令 | 用途 | 示例 |\r
|------|------|------|\r
| `add` | 添加记录 | `--amount 35 --category 餐饮 --desc "午饭" --date 2026-04-09` |\r
| `list` | 列出记录 | `--limit 20 --category 餐饮 --from 2026-04-01 --to 2026-04-30` |\r
| `delete` | 删除记录 | `--id 3` |\r
| `stats` | 统计分析 | `--period month --date 2026-04-09` |\r
| `categories` | 查看分类 | （无参数） |\r
| `summary` | 全局总览 | `--top 5` |\r
\r
### 执行模板\r
\r
```bash\r
python "{SKILL_DIR}/scripts/expense_tracker.py" \x3Ccommand> [options]\r
```\r
\r
## 处理流程\r
\r
### 1. 记账\r
\r
从用户自然语言中提取：金额、分类、描述、日期。\r
\r
**金额提取规则**（按优先级）：\r
- `¥35` / `￥35` → 35\r
- `35元` / `35块` / `35块钱` → 35\r
- `花了35` / `花了35元` → 35\r
- `35.5元` → 35.5\r
- 纯数字 `35` → 35\r
\r
**日期提取**：\r
- "今天" → 当天\r
- "昨天" → 前一天\r
- "前天" → 前两天\r
- "上周X" / "上个月" → 对应日期\r
- 无日期关键词 → 默认今天\r
\r
**分类判断**：\r
优先看用户是否明确说了分类（"餐饮花了35"），没有则根据描述中的关键词自动匹配。参考 `references/categories.md` 中的完整关键词表。无法匹配时归入"其他"。\r
\r
**执行示例**：\r
```bash\r
python "{SKILL_DIR}/scripts/expense_tracker.py" add --amount 35 --category 餐饮 --desc "午饭" --date 2026-04-09\r
```\r
\r
### 2. 查询记录\r
\r
```bash\r
# 最近20条\r
python "{SKILL_DIR}/scripts/expense_tracker.py" list --limit 20\r
\r
# 按分类 + 日期范围\r
python "{SKILL_DIR}/scripts/expense_tracker.py" list --category 餐饮 --from 2026-04-01 --to 2026-04-30\r
```\r
\r
### 3. 统计分析\r
\r
```bash\r
# 本月统计\r
python "{SKILL_DIR}/scripts/expense_tracker.py" stats --period month\r
\r
# 本周统计\r
python "{SKILL_DIR}/scripts/expense_tracker.py" stats --period week\r
\r
# 某天统计\r
python "{SKILL_DIR}/scripts/expense_tracker.py" stats --period day --date 2026-04-09\r
```\r
\r
stats 返回 `by_category`（按分类金额）和 `daily`（按日期金额），用来生成人类可读的报告。\r
\r
### 4. 删除记录\r
\r
先 list 找到要删除的记录 id，确认后执行：\r
```bash\r
python "{SKILL_DIR}/scripts/expense_tracker.py" delete --id 3\r
```\r
\r
### 5. 全局总览\r
\r
```bash\r
python "{SKILL_DIR}/scripts/expense_tracker.py" summary --top 5\r
```\r
\r
## 输出格式\r
\r
记账成功后回复格式：\r
```\r
✅ 已记录：餐饮 ¥35.00 — 午饭 (2026-04-09)\r
```\r
\r
查询/统计回复要求简洁，用列表而非表格（适配移动端）：\r
```\r
📊 本月支出统计\r
💰 总计：¥1,280.50（23笔）\r
\r
📂 分类排行：\r
  餐饮 ¥580.00 (45.3%)\r
  交通 ¥320.00 (25.0%)\r
  购物 ¥200.00 (15.6%)\r
  其他 ¥180.50 (14.1%)\r
```\r
\r
## 数据存储\r
\r
数据存储在 `~/.qclaw/workspace/expense-tracker-data/expenses.json`，纯本地，不联网。\r

安全使用建议

What to check before installing: - Data location mismatch: README and SKILL.md use different data-directory names ("expense-tracker-data" vs "expense-tracker-daily-data"). The actual code writes to ~/.qclaw/workspace/expense-tracker-data; verify that path if you rely on backups or expect a different folder. - Inspect the local JSON files: expenses.json and config.json are stored under your home directory. If you keep sensitive notes in descriptions, consider encrypting or limiting access to that folder. - Confirm Python availability: the skill runs python from PATH. If your environment lacks python or uses a different interpreter, the skill won’t run until you install/configure one. - Keyword overlaps: some keywords (e.g., '网费') appear in multiple categories; classification is heuristic. Expect occasional misclassification and confirm critical entries. - Privacy: the skill is local-only (no network calls in the code), but always review any future updates/PRs for added network or telemetry code. Overall: the skill is internally consistent and low-risk; the issues are documentation/operational (path names, category heuristics) rather than malicious. If you are satisfied with local JSON storage, it is reasonable to install and use.

功能分析

Type: OpenClaw Skill Name: expense-tracker-daily Version: 1.0.2 The expense-tracker-daily skill is a legitimate local utility for tracking expenses. It uses a Python script (expense_tracker.py) to perform CRUD operations on a local JSON file stored in the user's home directory (~/.qclaw/workspace/expense-tracker-data/). The code uses only standard Python libraries, contains no network activity, and the AI instructions in SKILL.md are strictly focused on extracting transaction details from natural language to pass to the CLI script.

能力评估

✓ Purpose & Capability

Name/description (Chinese expense-tracker) align with the included script and instructions. The skill is self-contained: it provides a CLI-like Python script that adds/lists/deletes/stats expenses and a keyword mapping for categorization. Nothing requested (no env vars, no external services) is extraneous to the stated purpose. Note: SKILL.md templates reference running 'python' via SKILL_DIR, but the registry metadata lists no required binaries — this is operational but not a security mismatch.

✓ Instruction Scope

SKILL.md directs the agent to run the bundled scripts/expense_tracker.py with explicit commands and options. The script only reads/writes local files under the skill's DATA_DIR and reads the local category map. There are no instructions to read arbitrary system files, access network endpoints, or exfiltrate data. One small inconsistency: SKILL.md and README refer to local storage but use slightly different directory names (SKILL.md: ~/.qclaw/workspace/expense-tracker-data/expenses.json; README: ~/.qclaw/workspace/expense-tracker-daily-data/). This is a documentation mismatch that may affect where data is actually stored.

✓ Install Mechanism

No install spec is included (instruction-only skill with a bundled Python file). There are no downloads, no external packages, and the Python script uses only standard library modules (argparse, json, pathlib, datetime). This is low-risk from an install/execution standpoint.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. The script uses a single per-user data directory under the home path and does not request or attempt to read secrets or unrelated configs. This level of access is proportionate to its function.

✓ Persistence & Privilege

always is false and the skill does not request elevated platform privileges. It writes only to its own data directory and does not modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but not combined with broad access.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install expense-tracker-daily
安装完成后，直接呼叫该 Skill 的名称或使用 /expense-tracker-daily 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.2

更新名称

v1.0.1

- Renamed the skill to expense-tracker-daily. - Added a README.md file for documentation and reference.

v1.0.0

- Initial release of the 智能记账助手 (expense-tracker-daily). - Supports natural language input for quickly recording expenses (e.g., "午饭花了35", "打车25块"). - Automatically extracts amount, category, description, and date; includes rule-based parsing for amounts and dates. - Provides commands for listing, adding, deleting, and summarizing expenses with statistical analysis by category and date. - All data stored locally in a JSON file; does not require internet connection. - Clean, concise reply format optimized for mobile display.

元数据

Slug expense-tracker-daily

版本 1.0.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题