Analyze table or file structure, distributions, and data quality.
npx skills add https://github.com/ilove323/comlan-skills --skill explore-data-ilove323
Please help me install this Agent Skill. Skill: explore-data Source: https://github.com/ilove323/comlan-skills/tree/main/data/skills/explore-data Command: npx skills add https://github.com/ilove323/comlan-skills --skill explore-data-ilove323
Quickly understand the structure, quality, and key patterns of a new table or uploaded file so analysts can avoid wasted work and catch data issues early. It eliminates initial guesswork about schema, missingness, cardinality, distributions, duplicates, and suspicious placeholder values before deeper analysis.
Ask the assistant to explore the table orders or upload orders.csv to generate a full dataset overview, quality report, and recommended next-step analyses.
High-intent search queries and answers about installing and using this skill.
To profile a CSV file for data quality, you can analyze its structure to generate field-level statistics, missingness rates, cardinality, and basic distributions. This process surfaces high null rates, duplicates, and suspicious placeholder values.
Exploratory data analysis on database tables involves inferring schema and classifying fields into identifiers, dimensions, or metrics. It calculates table-level metrics like row counts and date ranges, alongside field-level statistics such as unique counts and numeric quantiles.
Yes, schema discovery can identify candidate foreign keys and hierarchical groupings in Parquet files. It classifies fields into dimensions, metrics, and timestamps while flagging data quality issues like unexpected values or future dates.
The best way to catch data quality issues in a new analytics table is to run sampling-aware profiling. This flags high null rates, placeholder values like N/A, duplicates, and negative numbers, while suggesting remediation steps and starter SQL.
Yes, exploratory data analysis works with JSON files and large database tables. It applies sampling-aware profiling for large tables to produce field-level statistics, missingness metrics, and suggested next-step analyses without scanning entire datasets.
Field analysis shows unexpected values and future dates because it actively flags data quality issues during schema discovery. It identifies suspicious placeholder values like 999999, negative numbers, and duplicates, then recommends appropriate remediation steps.
frumu-aiProfile datasets from warehouses and uploaded files to generate table and column metrics.
sun2443Profile unknown datasets to surface structure, quality issues, and analytical angles.
fuziix266Optimize SQL queries and design database schemas across PostgreSQL, MySQL, and SQL Server.
clawpod-appProfile datasets to assess shape, quality, and patterns.
