agentleFS
wwumitwwumit/skills-tools/skills/excel2insights-pro/SKILL.md

excel2insights-pro

Skill0 starsChanged 3 months agoMITView on GitHub

Excel2Insights Pro — 交互式数据分析和可视化仪表板。 Automatically analyzes structured data (CSV/XLSX/TSV) and generates an interactive HTML dashboard with Plotly charts, data quality insights, and customizable branding.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a brand.json file to customize your dashboard:

    line 145
  2. Distinctive:

    All processing is local — no data leaves the machine

    line 248
  3. Distinctive:

    No user data is collected or transmitted

    line 250

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

免责声明

本工具仅供学习和研究参考,不构成任何投资建议。投资有风险,入市需谨慎。 本工具为数据分析辅助工具,提供的分析结果仅供参考, 不构成任何投资建议,不构成投资建议,不构成任何法律建议,不构成法律建议。 用户应结合实际情况自行判断并承担相关责任。

📊 Excel2Insights Pro



Overview

Excel2Insights Pro transforms structured data files into interactive, brandable HTML dashboards with a single command. It combines automated statistical analysis, data quality checks, and Plotly interactive visualizations into a polished, self-contained report.

What makes it Pro

FeatureFree VersionPro Version
ChartsStatic PNG (matplotlib)Interactive Plotly (zoom, hover, pan)
OutputMarkdown reportBranded HTML dashboard
CustomizationNoneBrand colors, logo, fonts
Data QualityBasic statsVisual quality panel
InsightsRaw numbersTagged insights with scores
Pipeline5 separate commandsOne-command auto-pipeline

Workflow

Quick Start (30 seconds)

# One-command: load → analyze → chart → dashboard
python3 scripts/auto-pipeline.py --file data.csv
# Opens: output/<dataset>_dashboard.html

Custom Brand Dashboard

# 1. Generate brand template
python3 scripts/dashboard-generator.py --init-brand brand.json

# 2. Edit brand.json (colors, logo, company name)

# 3. Run with branding
python3 scripts/auto-pipeline.py --file data.csv --brand-json brand.json

Custom Chart Selection

python3 scripts/auto-pipeline.py --file data.csv \
  --charts histogram,bar,heatmap,scatter,pairplot \
  --brand-json brand.json

Available Scripts

ScriptDescriptionUsage
scripts/excel-reader.pyLoad & inspect file metadata--file DATA
scripts/data-analyzer.pyFull statistical analysis--file DATA --output analysis.json
scripts/chart-generator.pyInteractive Plotly charts--file DATA --charts TYPES --output DIR
scripts/dashboard-generator.pyHTML dashboard + brand--analysis JSON --charts DIR --output DASHBOARD
scripts/auto-pipeline.pyOne-command full pipeline--file DATA [--brand-json BRAND]

Script Details

excel-reader.py

  • --file PATH — Path to Excel/CSV/TSV file
  • --sheet NAME — Sheet name (XLSX only)
  • --encoding ENC — File encoding (default: utf-8)

data-analyzer.py

  • --file PATH — Path to data file
  • --output PATH — Output JSON path
  • --correlation — Include correlation matrix
  • --outliers — Enable outlier detection

chart-generator.py (Pro: Plotly interactive)

  • --file PATH — Path to data file
  • --charts TYPES — Comma-separated: histogram,boxplot,bar,line,pie,heatmap,scatter,pairplot
  • --columns COLS — Specific columns to visualize
  • --output DIR — Output directory

Generated charts are interactive HTML files with:

  • 🔍 Zoom & pan controls
  • 🖱️ Hover tooltips with values
  • 📏 Auto-scaling axes
  • 💾 SVG/PNG export (via Plotly toolbar)

dashboard-generator.py (Pro exclusive)

  • --analysis JSON — Analysis results JSON (required)
  • --charts DIR — Charts directory
  • --output PATH — Output dashboard HTML path
  • --brand-json PATH — Brand configuration file
  • --init-brand PATH — Generate brand template
  • --file DATA — Original data file (for stats)

auto-pipeline.py (Pro exclusive)

  • --file PATH — Data file (required)
  • --charts TYPES — Chart types (default: histogram,bar,heatmap,scatter)
  • --output DIR — Output directory
  • --format FORMAT — html / markdown / both
  • --brand-json PATH — Brand configuration

Brand Customization

Create a brand.json file to customize your dashboard:

{
  "company_name": "Your Company",
  "logo_url": "",
  "primary_color": "#1a73e8",
  "secondary_color": "#34a853",
  "accent_color": "#ea4335",
  "font_family": "'Inter', sans-serif",
  "show_footer": true,
  "footer_text": "Generated by Excel2Insights Pro | Your Company"
}

Generate a template: python3 scripts/dashboard-generator.py --init-brand brand.json


Examples

Example 1: Quick Dashboard

python3 scripts/auto-pipeline.py --file sales_data.csv
# Output: output/sales_data_dashboard.html
# → Interactive dashboard with histogram, bar, and correlation charts

Example 2: Full Analysis with Branding

python3 scripts/auto-pipeline.py --file survey_2024.xlsx \
  --charts histogram,bar,boxplot,heatmap,scatter \
  --brand-json brand.json
# Output: output/survey_2024_dashboard.html
# → Branded dashboard with 5 chart types

Example 3: Manual Step-by-Step

# Step 1: Analyze
python3 scripts/data-analyzer.py --file data.csv \
  --output analysis.json --correlation --outliers

# Step 2: Generate charts
python3 scripts/chart-generator.py --file data.csv \
  --charts histogram,bar,heatmap,scatter --output charts/

# Step 3: Build dashboard
python3 scripts/dashboard-generator.py \
  --file data.csv --analysis analysis.json \
  --charts charts/ --output dashboard.html \
  --brand-json brand.json

Output Format

The dashboard is a self-contained HTML file that includes:

<!-- Summary Cards → overview stats -->
<!-- Data Quality → missing values, column profile -->
<!-- Interactive Charts → Plotly with zoom/hover/pan -->
<!-- Key Insights → tagged findings with severity -->

Open it directly in any browser — no server required.


Legal

Disclaimer

This tool provides data analysis and visualization. It does not make business decisions. Users are responsible for interpreting results and making informed decisions.

License

MIT License. See LICENSE file for details.


Security & Constraints

Declared Capabilities

ScriptPurposeInputOutputNetworkFilesystem
excel-reader.pyLoad & preview fileFile pathstdoutNoRead only
data-analyzer.pyStatistical analysisFile path / JSONstdout / JSONNoRead + write output
chart-generator.pyInteractive Plotly chartsFile path / columnsHTML filesNoWrite charts
dashboard-generator.pyHTML dashboard + brandJSON + chartsHTML fileNoWrite dashboard
auto-pipeline.pyFull pipeline orchestratorFile pathDashboardNoWrite all outputs

Explicitly Denied

  • ❌ No network access (HTTP, socket, API calls)
  • ❌ No arbitrary code execution via exec()/eval()
  • ❌ No dynamic imports from external sources
  • ❌ No system commands via subprocess/shell
  • ❌ No telemetry, analytics, or usage reporting
  • ❌ No external script fetching
  • ❌ No auto-update mechanisms

Data Privacy

  • All processing is local — no data leaves the machine
  • Output files are saved to the working directory
  • No user data is collected or transmitted

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.