convez.ai
PluginDados & AnalyticsIniciante
Ratnaditya-J

csvglow

Ratnaditya-J/csvglow

Dashboards visuais gerados automaticamente de dados tabulares em um clique

Ver no GitHub
InicialPluginScore · de 0 a 100

Transforma arquivos CSV/Excel em dashboards HTML interativos e auto-contidos, com detecção automática de gráficos, análises inteligentes, correlações e tabela de dados ordenável. Executa sem servidor, offline, com zero configuração.

Instalação

$npx convez-ai Ratnaditya-J/csvglow

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
14
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 8 meses
Versão
v0.1.0
Issues abertas
0
Contribuidores
1

Casos de uso

  • Explorar datasets rapidamente sem setup de ferramentas pesadas
  • Apresentar análises de dados em formatos executivos auto-contidos
  • Detectar padrões, correlações e outliers em dados tabulares de forma visual

Veredito

Ferramenta prática para visualização rápida de dados tabulares sem overhead de ambiente. Funciona como MCP server/skill e gera HTML auto-contido — ideal para prototipagem e compartilhamento, mas limitado em escala (100k+ rows) e customização.

README

A tradução para o português deste README ainda está na fila.

csvglow

csvglow MCP server

Generate beautiful, interactive HTML dashboards from CSV/Excel files. One command, zero config.

csvglow sales.csv

Opens a self-contained HTML dashboard in your browser with auto-detected charts, smart multi-column insights, correlations, and a sortable data table. Dark gradient theme. Copy any chart to your clipboard.

Install

pip install csvglow

Or via npx (no install needed):

npx csvglow data.csv

Usage

csvglow data.csv                    # CSV to dashboard, opens in browser
csvglow report.xlsx                 # Excel works too
csvglow data.csv -o dashboard.html  # Custom output path
csvglow data.csv --no-open          # Don't auto-open browser

What it generates

  • Smart findings — multi-column narrative analysis that cross-references metrics to surface contradictions, efficiency gaps, and top/underperformers
  • Histograms for every numeric column with mean, median, std, quartiles, and outlier counts
  • Bar charts for categorical columns
  • Cross analysis — automatic categorical x numeric crosstabs with overall mean lines
  • Time series line charts with area fill for date columns
  • Correlation heatmap between numeric columns
  • Scatter plots for highly correlated pairs (|r| > 0.7)
  • Sortable, filterable data table (first 1000 rows)
  • Copy button on each chart for pasting into slides

Output is a single self-contained HTML file. No server, no CDN, works offline.

MCP Server

csvglow works as an MCP tool in any MCP-compatible client. Once configured, ask your AI assistant to generate a dashboard from a file path.

Pick your client and add csvglow to its MCP config file:

ClientConfig file location
Cursor.cursor/mcp.json in your project root
Windsurf~/.windsurf/mcp.json

Add this to the config:

{
  "mcpServers": {
    "csvglow": {
      "command": "npx",
      "args": ["-y", "csvglow", "--mcp"]
    }
  }
}

Uses npx so there's nothing extra to install.

If you already have csvglow installed via pip, use "command": "csvglow" with "args": ["--mcp"] instead.

OpenClaw Skill

csvglow is available as an OpenClaw skill. Any OpenClaw-compatible client can discover and use it automatically — no manual config needed.

Supported formats

  • .csv / .tsv (auto-detected delimiter)
  • .xls
  • .xlsx (first sheet only — multi-sheet support coming soon)

Changelog

0.1.0

  • Initial release
  • Auto-detection of column types (numeric, categorical, datetime, identifier)
  • Smart findings: contradiction detection, efficiency analysis, top/underperformer identification across multiple columns
  • Histograms with stats sidebar, bar charts, cross-analysis crosstabs, time series, correlation heatmap, scatter plots
  • Sortable/filterable data table
  • Copy-to-clipboard for all charts
  • MCP server mode (csvglow --mcp)
  • OpenClaw skill support
  • Smart sampling for large files (100k+ rows)

Roadmap

  • Multi-sheet Excel support
  • Multi-file support with join keys
  • Light theme
  • Custom color palettes
  • PDF export

License

MIT

Ver o original no GitHub

Bom para

Relacionados