← Back to Skills Marketplace
76
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install jw-data-analyst
Description
数据分析助手 - 自动生成Python数据处理脚本、可视化图表、统计报告。支持Excel/CSV/JSON/数据库。觸發詞：数据分析、图表、统计、报表、可视化。
README (SKILL.md)
JW Data Analyst
数据分析智能助手，自动处理数据并生成洞察。
功能
1. 数据加载
- Excel (.xlsx/.xls)
- CSV/TSV
- JSON
- SQLite/MySQL/PostgreSQL
- API数据源
2. 数据清洗
- 缺失值处理（填充/删除/插值）
- 重复值检测与去除
- 异常值检测（IQR/Z-score）
- 数据类型转换
- 格式标准化
3. 统计分析
- 描述性统计（均值/中位数/标准差）
- 相关性分析
- 趋势分析
- 分组聚合
- 时间序列分析
4. 可视化
- 折线图（趋势）
- 柱状图（对比）
- 饼图（占比）
- 散点图（相关性）
- 热力图（矩阵）
- 箱线图（分布）
使用方式
分析Excel文件
帮我分析这个Excel文件：[路径]
生成图表
用这个数据生成一个柱状图：[数据]
统计报告
生成数据的统计报告：[数据]
输出格式
- 分析报告：Markdown格式
- 图表：PNG/SVG
- 处理后的数据：Excel/CSV
- Python脚本：可复用的.py文件
技术栈
- Python 3.10+
- pandas（数据处理）
- matplotlib/seaborn（可视化）
- numpy（数值计算）
- openpyxl（Excel读写）
- sqlalchemy（数据库连接）
注意事项
- 大文件（>100MB）需要分批处理
- 敏感数据需脱敏后分析
- 生成的图表默认保存到D盘
Usage Guidance
This skill appears to do what it says (generate analysis scripts, charts, reports), but there are a few things to check before installing or using it. 1) Metadata mismatch: _meta.json lists a different ownerId than the registry metadata — ask the publisher to confirm authorship. 2) Do not supply production DB credentials or API keys until you confirm how the skill handles them; prefer temporary or read-only test credentials. 3) The SKILL.md says charts are saved to D: by default — verify or change the output directory to a location appropriate for your system. 4) Test the skill first with non-sensitive/sample data to confirm behavior. 5) If you need guarantees about credential storage or network access, request additional documentation from the author (how credentials are provided, whether data is sent to external endpoints, and how outputs are stored).
Capability Analysis
Type: OpenClaw Skill
Name: jw-data-analyst
Version: 1.0.0
The skill bundle contains only metadata and documentation for a data analysis assistant. The SKILL.md file describes standard data processing, statistical analysis, and visualization capabilities using common Python libraries like pandas and matplotlib. No executable code, suspicious network calls, or malicious prompt instructions were found.
Capability Assessment
Purpose & Capability
The SKILL.md describes a reasonably-scoped data analysis tool (Excel/CSV/JSON/db/API → cleaning, stats, charts). However the package metadata contains an ownerId that differs from the registry metadata provided (inconsistent ownerId in _meta.json). Also the SKILL.md hardcodes a default save location ("默认保存到D盘") which is an unexpected assumption about the host environment and may not apply on non-Windows systems.
Instruction Scope
Instructions are high-level and focus on reading user-specified data sources and producing reports/plots; they do not instruct the agent to read arbitrary system files or exfiltrate data. Still, support for databases and API sources implies the skill will need connection credentials at runtime, but the SKILL.md does not specify how credentials are provided or handled. The hardcoded save-to-D: path is an unexpected I/O instruction that could cause write attempts to an inappropriate location.
Install Mechanism
No install spec and no code files — instruction-only — so nothing is written to disk by an installer. This is the lowest-risk install model.
Credentials
The skill declares no required environment variables, which is consistent for an instruction-only tool. However, because it supports SQLite/MySQL/PostgreSQL and API data sources, it will likely ask users for connection strings/credentials at runtime. The SKILL.md does not document how credentials should be supplied or stored, which raises a proportionality/usability question and a potential risk if users paste production credentials without guidance.
Persistence & Privilege
always:false and normal model invocation settings — the skill won't be force-included or request persistent elevated privileges. The skill does assert default file save behavior but does not attempt to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install jw-data-analyst - After installation, invoke the skill by name or use
/jw-data-analyst - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Data analysis assistant for Excel/CSV/JSON/DB
Metadata
Frequently Asked Questions
What is JW Data Analyst?
数据分析助手 - 自动生成Python数据处理脚本、可视化图表、统计报告。支持Excel/CSV/JSON/数据库。觸發詞：数据分析、图表、统计、报表、可视化。 It is an AI Agent Skill for Claude Code / OpenClaw, with 76 downloads so far.
How do I install JW Data Analyst?
Run "/install jw-data-analyst" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is JW Data Analyst free?
Yes, JW Data Analyst is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does JW Data Analyst support?
JW Data Analyst is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created JW Data Analyst?
It is built and maintained by a85012712 (@a85012712); the current version is v1.0.0.
More Skills