← 返回 Skills 市场
Smart Ledger
作者
dyby99-gif
· GitHub ↗
· v1.0.0
299
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install smart-ledger
功能描述
智能收支追踪器 — 通过自然语言快速记账，自动分类，生成日/周/月报告和趋势分析。 支持中文自然语言输入("今天午饭花了35元")，数据本地JSON存储保护隐私。 适用于个人财务管理、预算追踪和消费分析场景。
安全使用建议
This package appears to be a local-only expense tracker and is coherent with its description. Before installing or running: 1) Confirm you have Python 3.9+ available (SKILL.md requires it). 2) Review the full scripts (especially the truncated sections provided) yourself to verify there are truly no network calls or unexpected subprocess usage. 3) Back up any existing data in ~/.openclaw/workspace/data/expenses/expenses.json before first run. 4) If you store sensitive financial details, consider encrypting the JSON or keeping backups offline. 5) Run the scripts in an isolated environment (local user account or sandbox) if you are uncertain about the origin of the package.
功能分析
Type: OpenClaw Skill
Name: smart-ledger
Version: 1.0.0
The OpenClaw AgentSkills skill bundle 'smart-ledger' is classified as benign. The code in `scripts/expense-tracker.py` and `scripts/report-generator.py` implements a local expense tracker with natural language parsing and reporting, storing data in `~/.openclaw/workspace/data/expenses/expenses.json`. There is no evidence of malicious intent, such as data exfiltration (no network calls), unauthorized execution, or persistence mechanisms. The `SKILL.md` provides clear usage instructions without any prompt injection attempts against the AI agent. The code also includes good security practices like atomic file writes and attempts to set strict file permissions for user data.
能力评估
Purpose & Capability
Name/description (natural-language expense tracking, local JSON storage, reports) match the provided code and SKILL.md. The code implements parsing, categorization, persistence, and reporting which align with the stated purpose. Minor metadata mismatch: the registry excerpt lists 'Required binaries: none' while SKILL.md declares 'python: >=3.9' — requiring Python is reasonable for this skill, but the registry metadata should reflect that.
Instruction Scope
Runtime instructions and the scripts operate on local files only (the data path is ~/.openclaw/workspace/data/expenses/expenses.json and assets/categories.json). The SKILL.md and code instruct reading/writing that file and editing local config; there are no instructions to read unrelated system files, access credentials, or transmit data externally. (Note: some file contents in the provided package listing were truncated; no evidence of network/endpoints was visible in the parts provided.)
Install Mechanism
No install spec included — instruction-only with bundled Python scripts and a JSON asset. Nothing is downloaded or executed from remote URLs. The scripts use only Python standard library features (json, pathlib, tempfile, etc.), so no external package install is required.
Credentials
The skill requests no environment variables or external credentials and stores data locally. This is proportionate to a personal expense tracker. It attempts to set restrictive file permissions for privacy (chmod), which is appropriate. There are no unrelated credential requests.
Persistence & Privilege
The skill does not set always:true and is user-invocable only. It persists its own data under a dedicated workspace path and does not modify system-level or other-skill configuration. Attempted file-permission tightening is scoped to its data directory.
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 smart-ledger - 安装完成后，直接呼叫该 Skill 的名称或使用
/smart-ledger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
v1.0.0
Smart-ledger 1.0.0 – Initial release
- Track expenses and income via natural language input (Chinese/English), e.g. “今天午饭花了35元”.
- Automatic classification of transactions (餐饮, 交通, 购物, etc.).
- Generate daily, weekly, monthly financial reports and trend analysis.
- Local JSON data storage to protect user privacy.
- CLI for adding, listing, summarizing, or deleting records; output supports both human-readable and JSON formats.
- Configurable categories and keyword mapping for custom classification and budget alerts.
元数据
常见问题
Smart Ledger 是什么？
智能收支追踪器 — 通过自然语言快速记账，自动分类，生成日/周/月报告和趋势分析。 支持中文自然语言输入("今天午饭花了35元")，数据本地JSON存储保护隐私。 适用于个人财务管理、预算追踪和消费分析场景。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 299 次。
如何安装 Smart Ledger？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install smart-ledger」即可一键安装，无需额外配置。
Smart Ledger 是免费的吗？
是的，Smart Ledger 完全免费（开源免费），可自由下载、安装和使用。
Smart Ledger 支持哪些平台？
Smart Ledger 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Smart Ledger？
由 dyby99-gif（@dyby99-gif）开发并维护，当前版本 v1.0.0。
推荐 Skills