← 返回 Skills 市场
data-analysis
作者
ModestyRichards
· GitHub ↗
· v1.0.0
· MIT-0
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install modesty-data-analysis
功能描述
Analyze, visualize, and explain data using SQL, Python, or spreadsheets to deliver decision-ready reports, cohort and funnel analyses, and hypothesis tests.
安全使用建议
This skill is a coherent, instruction-only package of analysis methodology and templates. Before using it: (1) understand that to run real queries or spreadsheets you'll need to grant the agent access to your data sources — prefer short-lived, scoped credentials or connector tokens rather than long-lived admin keys; (2) do not paste sensitive production credentials into prompts; (3) review outputs (especially anything recommending actions) before approving changes; (4) if the agent will access PII or regulated data, enforce least privilege, masking, and logging; and (5) if you are uncomfortable with autonomous invocation, restrict or require explicit approval when the agent requests external data access.
功能分析
Type: OpenClaw Skill
Name: modesty-data-analysis
Version: 1.0.0
The skill bundle is a purely instructional framework designed to guide an AI agent in performing high-quality data analysis. It contains no executable code, scripts, or external network dependencies. The instructions in SKILL.md and the supporting reference files (e.g., pitfalls.md, techniques.md) focus entirely on analytical methodology, statistical rigor, and decision-oriented reporting, with no evidence of malicious intent or prompt-injection attacks.
能力标签
能力评估
Purpose & Capability
The name and description (SQL/Python/spreadsheet-based analysis, reports, cohorts, funnels, hypothesis tests) match the SKILL.md and accompanying docs. The skill is a methodology-and-templates pack rather than an integration that would need credentials or binaries, so the lack of required env vars or install steps is consistent.
Instruction Scope
SKILL.md contains procedural guidance, checklists, templates, and analytic best practices. It does not instruct the agent to read arbitrary system files, reach out to hidden endpoints, or exfiltrate data. It only references the included guidance files and methodological steps for analysis.
Install Mechanism
There is no install spec and no code to execute — the skill is instruction-only and therefore does not write code or binaries to disk. This is low-risk and coherent with its purpose.
Credentials
The skill declares no required environment variables or credentials, which is reasonable because it's a guidance/template skill. However, real-world use of the skill (querying databases, spreadsheets, BI tools) will normally require the agent or user to provide credentials or connectors at runtime; those are not requested by this skill itself. Users should be aware that granting the agent access to data sources is an operational step outside the skill.
Persistence & Privilege
The skill is not 'always' enabled and does not request persistent system-wide configuration or modify other skills. Default autonomous invocation (model-invocable) is allowed, which is standard and not problematic here by itself.
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 modesty-data-analysis - 安装完成后，直接呼叫该 Skill 的名称或使用
/modesty-data-analysis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
- Added metric contracts, chart guidance, and decision brief templates for more reliable analysis.
- Expanded documentation on methodology-first analysis, statistical rigor, and output standards.
- Included reference files for KPI definitions, chart selection, pitfalls, and analytical techniques.
- Clarified security, privacy, and external endpoint handling.
- Added table for related skills and installation guidance.
元数据
常见问题
data-analysis 是什么？
Analyze, visualize, and explain data using SQL, Python, or spreadsheets to deliver decision-ready reports, cohort and funnel analyses, and hypothesis tests. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。
如何安装 data-analysis？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install modesty-data-analysis」即可一键安装，无需额外配置。
data-analysis 是免费的吗？
是的，data-analysis 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
data-analysis 支持哪些平台？
data-analysis 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 data-analysis？
由 ModestyRichards（@modestyrichards）开发并维护，当前版本 v1.0.0。
推荐 Skills