← Back to Skills Marketplace
openlark

Intelligent Data Analysis Assistant

by OpenLark · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
47
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install data-analyst-visualization
Description
LLM-powered intelligent data analysis assistant supporting natural language queries, SQL generation, visualization, and multi-turn conversation. Suitable for...
README (SKILL.md)

Intelligent Data Analysis Assistant

Talk to your data through natural language. No SQL or technical background required for data query, analysis, and visualization.

Workflow

User question → Parse intent → Generate SQL → Execute query → Analyze results → Visualize → Output conclusions

Core Capabilities

1. Natural Language → SQL

Chinese questions auto-converted to SQL:

User Question SQL
"Sales by region last month?" SELECT region, SUM(amount) FROM sales WHERE month='2026-04' GROUP BY region
"Which product has the highest return rate?" SELECT product, COUNT(*) FROM orders WHERE status='returned' GROUP BY product ORDER BY 2 DESC LIMIT 1
"Compare user growth vs same period last year" SELECT DATE_TRUNC('month', created_at), COUNT(*) FROM users WHERE created_at >= NOW() - INTERVAL '1 year' GROUP BY 1 ORDER BY 1

2. Data Visualization

Results output in two layers:

  • Layer 1: Inline Markdown summary (metrics table + ASCII trend + conclusions)
  • Layer 2: Standalone HTML page (Chart.js interactive charts), see references/visualization-template.md

3. Multi-turn Conversation

Mode Description
Refine "Only show East China" → append filter
Switch dimension "Group by month" → re-aggregate
Root cause "Why did it drop?" → drill down
Compare "vs last quarter?" → time comparison

4. File Data Reading

Supports Excel (.xlsx/.xls), JSON/JSONL, CSV file reading. See references/data-sources.md.

5. Database Connections

MySQL / PostgreSQL / Snowflake / SQLite / BigQuery / Redshift. See references/data-sources.md.

Output Format

Inline chat output:

📊 Results: {title}
─────────────────────────────
{metrics table}

📈 Trend:
{ASCII trend bars}

📋 Analysis:
1. ...

For charts, auto-generate HTML page → write to {domain}_chart.html → report path.

Notes

  • SQL limited to read-only SELECT
  • Privacy fields auto-masked
  • Large datasets prompt for LIMIT
  • Vague questions trigger clarifying questions
  • Uses mock data when no data source configured
  • File reading auto-outputs overview (row count, columns, types, first 5 rows)
Usage Guidance
Install only if you are comfortable letting the agent read the selected files or query the configured databases. Use read-only, least-privilege database accounts, avoid pasting long-lived production passwords directly into chat, review generated SQL before execution, and delete generated HTML chart files if they contain sensitive results.
Capability Assessment
Purpose & Capability
The skill is explicitly for natural-language SQL generation, file reading, database querying, and visualization; these capabilities fit the stated data-analysis purpose and include read-only SQL and masking constraints.
Instruction Scope
Runtime instructions are mostly scoped to SELECT-only analysis, table whitelisting, limits for large datasets, and clarifying questions, but credential handling guidance is minimal.
Install Mechanism
The package contains only markdown skill/reference files and no executable install scripts, declared dependencies, or hidden runtime code.
Credentials
Reading local data files, connecting to databases, and loading Chart.js from a CDN are proportionate for visualization work, but users should understand the local and network data exposure implications.
Persistence & Privilege
The skill clearly says it writes chart reports to a local HTML file, which is expected for this purpose, but users should treat those files as persistent copies of query results.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install data-analyst-visualization
  3. After installation, invoke the skill by name or use /data-analyst-visualization
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Data Analyst Visualization skill: - Enables natural language querying for automatic SQL generation and analysis. - Provides two-level results: concise Markdown summary and interactive HTML charts. - Supports Excel, JSON, CSV file data reading and overview. - Integrates with MySQL, PostgreSQL, Snowflake, SQLite, BigQuery, and Redshift databases. - Handles multi-turn conversations for in-depth drilldown, filtering, and comparison. - Ensures privacy by masking sensitive fields and clarifies vague queries automatically.
Metadata
Slug data-analyst-visualization
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Intelligent Data Analysis Assistant?

LLM-powered intelligent data analysis assistant supporting natural language queries, SQL generation, visualization, and multi-turn conversation. Suitable for... It is an AI Agent Skill for Claude Code / OpenClaw, with 47 downloads so far.

How do I install Intelligent Data Analysis Assistant?

Run "/install data-analyst-visualization" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Intelligent Data Analysis Assistant free?

Yes, Intelligent Data Analysis Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Intelligent Data Analysis Assistant support?

Intelligent Data Analysis Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Intelligent Data Analysis Assistant?

It is built and maintained by OpenLark (@openlark); the current version is v1.0.0.

💬 Comments