skills.rest
AstorYH
AstorYHCOMMUNITY
Explore all skills by this author →
GitHub

data-triage

Analyze local CSV, TSV, JSON, JSONL, and log files with redacted summaries.

15|8|Updated Feb 9, 2026
Search Tags:#data validation#log analysis#data profiling#csv analysis#jsonl analysis#data triage
One-click install
npx skills add https://github.com/AstorYH/PASB --skill data-triage
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-triage
Source: https://github.com/AstorYH/PASB/tree/main/nanobot/skills/data-triage
Command: npx skills add https://github.com/AstorYH/PASB --skill data-triage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you quickly understand the contents and structure of unfamiliar local data files (like CSV, JSON, or logs) without needing to write custom parsing code.

Core Features & Use Cases

  • File Type Detection: Automatically identifies CSV, TSV, JSON, JSONL, and plain text files.
  • Data Profiling: Summarizes column types, missing values, and basic statistics for tabular data.
  • Log Analysis: Counts error/warning messages and hints at timestamp patterns in log files.
  • Safe-by-Default: Redacts potential PII and prioritizes statistics over raw data.
  • Use Case: You receive a large CSV file from a colleague. Use this Skill to get an immediate overview of its columns, data types, and potential issues before diving deeper.

Quick Start

Use the data-triage skill to analyze the file located at /path/to/your/data.csv.

Frequently Asked Questions about data-triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze a large CSV file and profile its columns without writing code?▼

To analyze a large CSV file, you can use this Skill to automatically profile columns, detect schema issues, count missing values, and summarize statistics locally without writing custom parsing code.

What is the best way to summarize JSONL files and identify data anomalies?▼

The best way to summarize JSONL files is using data profiling techniques that detect file types, count unique values, and identify anomalies automatically while operating locally on your machine.

Can I analyze local plain-text log files and detect error patterns safely?▼

Yes, you can analyze plain-text log files locally to count error and warning messages, identify timestamp patterns, and generate safe summaries that redact potential PII by default.

Does this data profiling approach work with TSV files and detect schema issues?▼

Yes, data profiling works with TSV files by automatically detecting the format, summarizing column types, identifying missing values, and flagging potential schema issues before deeper analysis.

How do I get an overview of unfamiliar data files without uploading them?▼

You can get an overview of unfamiliar data files by running local analysis that profiles columns, identifies anomalies, and generates statistics safely without uploading your data to external servers.

Related Skills

Explore More Data & Analytics Skills→
cas-bigdatalabcas-bigdatalab
541

text_fragment_remover

Remove specified text fragments from CSV, TSV, JSON, and JSONL fields using pandas.

Official
Intermediate
RUSHYOPRUSHYOP

xlsx

Clean, transform, and convert .xlsx, .xlsm, .csv, and .tsv spreadsheets.

Community
Intermediate
MichaelYang-lyxMichaelYang-lyx
110

chart-embedded-export

Extract classification distributions, clean text, and compute cross-tabulated statistics for analysis reports.

Community
Advanced
GiorgioRicciardielloGiorgioRicciardiello

eda

Automate exploratory data analysis with automatic PII redaction and themed plots.

Community
Intermediate