A powerful AI skill that converts raw business data into plain-language executive summaries and actionable analytical reports.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install data-analysis-reporting
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install data-analysis-reporting using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
This skill acts as a sharp junior analyst for your AI agent, capable of processing diverse data formats like CSVs, SQLite databases, and tabular markdown. It bridges the gap between raw numbers and business decisions by providing context-aware insights, identifying trends, and flagging statistical confidence. By using these Openclaw Skills, developers can empower agents to handle complex business metrics without human intervention.
It is designed specifically for small business operators and analysts who need to turn noise into signal. The skill prioritizes data integrity by running comprehensive quality checks before analysis and ensures all findings are delivered in plain language, making it easier for decision-makers to act on the information provided.
To integrate this skill into your agent's workflow, include the skill definition and reference documents in your project directory.
# Navigate to your agent's skills folder
cd your-agent/skills
# Download the data-analysis-reporting skill
curl -O https://raw.githubusercontent.com/openclaw/skills/main/data-analysis-reporting/SKILL.md
Ensure your agent has access to the references for business metrics and data quality checks to enable full functionality of Openclaw Skills.
The skill uses a structured reporting schema to ensure clarity and professional presentation:
| Section | Description |
|---|---|
| Executive Summary | High-level findings answering the core question in plain language. |
| Data Quality Notes | Details on cleaning, row counts, and potential data gaps. |
| Key Findings | Fact, implication, and confidence level for each major insight. |
| Trend Analysis | Time-series patterns including direction, magnitude, and acceleration. |
| Watch Items | Emerging negative trends or thresholds that need monitoring. |
| Methodology | Explicit record of formulas and assumptions used for metrics. |
Loading
An AI-powered utility for generating satisfying, hyperrealistic material textures and macro photography visuals.

A powerful integration for managing torrent lifecycles and download statistics directly through the qBittorrent WebUI API.

A professional AI research engine that tracks trending topics, conducts deep-source verification, and generates fact-checked long-form content.

A portable skill for OpenClaw agents to search and play Netease Music on Sonos devices while preserving full metadata and album art.

A professional-grade quantitative signaling and thematic identification system for the A-share market.

A specialized skill for retrieving real-time NBA schedules and historical game results for any professional team.








































