- Home
- Skills
- Data & Databases
- CSV Data Profiler
Works with the AI Agents you already use
CSV Data Profiler
Profile CSV/JSONL files for data quality, PII, and statistics while generating SQL schemas and HTML reports.
$1
CSV Data Profiler
Example session with this skill installed
Profile this user_exports.csv file, check for PII, and give me a Postgres CREATE TABLE statement for it.
- Read your context and instructions
- Compiled the csv data profiler
- Generated the data export
I have analyzed user_exports.csv using the data profiler. The file uses UTF-8 encoding and a comma delimiter. I detected 3,450 rows and identified several columns containing PII that should be masked or encrypted.
Data Profile Summary
| Column | Inferred Type | Nulls | Distinct | Notes |
|---|---|---|---|---|
user_id | UUID | 0 | 3,450 | Candidate Primary Key |
email | 0 | 3,448 | PII Detected, 2 duplicates | |
signup_date | Datetime | 12 | 2,890 | Format: YYYY-MM-DD HH:MM:SS |
account_balance | Float | 0 | 1,240 | Mean: 450.25, Max: 12500.00 |
phone_ext | Integer | 450 | 12 | Contains leading zeros |
Postgres Schema
CREATE TABLE user_exports (
user_id UUID PRIMARY KEY,
email VARCHAR(255) NOT NULL,
signup_date TIMESTAMP,
account_balance NUMERIC(12, 2),
phone_ext INTEGER
);
-- Index suggested for frequent lookups
CREATE INDEX idx_user_email ON user_exports(email);
Next steps
- Review the 2 duplicate entries in the
emailcolumn to prevent unique constraint violations. - Verify if the
phone_extnull values are expected or indicate an extraction error. - Apply the generated SQL to your staging environment to validate against your migration script.
user_exports.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Data integration often fails because you don't know what is actually inside the file. This skill profiles CSV, TSV, and JSON Lines files to catch data quality issues and schema mismatches before you start building.
What it does
- Format detection automatically identifies delimiters, encodings, and headers without manual configuration.
- Deep type inference identifies integers, floats, booleans, dates, UUIDs, emails, and URLs.
- Statistical analysis calculates min, max, mean, median, standard deviation, and percentiles for numeric data.
- Data quality auditing flags nulls, blanks, leading/trailing whitespace, and suspicious sentinel values like -999.
- Schema generation exports
CREATE TABLEstatements for SQL or JSON Schema files based on the analyzed data.
How it works
- Initial Scan: The tool probes the file to determine the structure and encoding.
- Profiling: It streams the data, using reservoir sampling for large files to keep statistics accurate while managing memory.
- Detection: It checks for PII, duplicate rows, and potential primary keys.
- Output Generation: You receive a summary report, SQL schema, or HTML visualization depending on the flags used.
Frameworks & tools
This tool uses a custom Python streaming processor. It operates without a pandas dependency to ensure it works in lightweight environments and handles large files via memory-efficient streaming.
Why this beats prompting it yourself
Generic LLMs often hallucinate data distributions or fail on large files due to context limits. This skill uses deterministic streaming logic to provide precise statistics and valid SQL schemas that you can actually run.
Use cases
- Pre-migration audits to find dirty data before loading a CSV into a production database.
- Schema bootstrapping to generate DDL for a new Postgres or Snowflake table from a flat file.
- PII discovery to identify sensitive fields like emails or card numbers that need masking.
Known limitations
Does not support Excel (.xlsx) files. SQL dialect support is focused on Postgres and standard SQL. Large file processing requires local Python execution.
Requires Python 3 environment. Does not support multi-sheet Excel files or nested JSON (only JSON Lines). Statistics on large files are based on reservoir sampling.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago