newbee doc

    1

    Professional CSV data quality auditor for identifying missing values, duplicates, and type in

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    newbee doc

    Example session with this skill installed

    Audit this CSV sample
    id,date,value,note
    1,2023-01-01,10.5,Valid
    2,2023-01-02,N/A,Valid
    3,2023-01-02,12.0,Valid
    1,2023-01-01,10.5,Valid
    4,2023-01-04,ERROR,None

    • Read your context and instructions
    • Compiled the newbee doc

    I have completed the audit of the provided CSV sample (5 rows, 4 columns).

    CSV Data Quality Audit Report

    Audit Basis: Partial sample (5 rows)

    1. Summary Table

    CategoryStatusNotes
    Missing ValuesPASSNo empty cells detected.
    Duplicate RowsFAIL1 duplicate row found.
    Type ConsistencyWARNMixed types in 'value' column.
    Null EncodingsFAILFound 'N/A' and 'None'.
    Constant ColumnsWARN'note' column has low variance.

    2. Detailed Findings

    • Duplicate Rows: Row 4 is a duplicate of Row 1.
    • Type Mismatch (value): Column 'value' is primarily numeric, but contains 'ERROR' (Row 5).
    • Null Encodings:
      • Column 'value': 'N/A' detected (Row 2).
      • Column 'note': 'None' detected (Row 5).

    Constant/Low Variance: Column 'note' contains 'Valid' in 80% of rows; check if this column provides unique information.

    3. Incomplete Checks

    • Large Scale Patterns: Unable to verify patterns across full dataset as only 5 rows were provided.

    4. Privacy Notice

    • No PII (names, emails, phones) detected in this sample.

    Scope Reminder: This is an audit report only. No data has been cleaned or modified.

    Next steps

    1. Remove the duplicate entry at Row 4.
    2. Investigate the 'ERROR' string in the 'value' column at Row 5.
    3. Replace 'N/A' and 'None' strings with standard null values during your import process.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Dirty data ruins analysis. This skill audits CSV files to identify structural and content issues before you waste time on broken pipelines. It systematically scans for missing values, type mismatches, and duplicate records without modifying the source.

    What it does

    • Missing Value Detection scans every column to report null counts and percentages.
    • Duplicate Identification flags exact row duplicates within the provided dataset.
    • Type Consistency Check infers column types and isolates cells that deviate from the majority format.
    • Null Encoding Analysis finds stealthy missing values like N/A, ?, or NULL that bypass standard loaders.
    • Constant Column Flagging identifies columns with zero variance that offer no analytical value.

    How it works

    1. Analyze Coverage by checking if the input is a full file or a sample snippet to set audit scope.
    2. Execute Scans across five quality dimensions defined in the internal ruleset.
    3. Log Anomalies by specific column and row index for easy manual verification.
    4. Generate Report using a standardized Markdown template with PASS/WARN/FAIL statuses.

    Frameworks & tools

    This skill is framework-agnostic and processes raw CSV text or file uploads. It uses internal logic to simulate pandas-like profiling without requiring an execution environment.

    Why this beats prompting it yourself

    Generic prompts often miss non-standard null encodings (like nan vs None) or fail to check for constant columns. This skill follows a rigid audit checklist and output schema, ensuring no quality dimension is skipped and the report remains scannable.

    Use cases

    • Auditing raw data exports before importing them into a production SQL database.
    • Verifying third-party CSV samples during the vendor data evaluation phase.
    • Checking for PII leaks in datasets before sharing them with external teams.
    • Validating automated report exports for consistency and logic errors.

    Known limitations

    Does not perform data cleaning or transformations. Limited to CSV format only. Samples under 3 rows will return incomplete audit results.

    Cannot clean or transform data. Limited to CSV files. Samples under 3 rows trigger incomplete status. Does not support Excel or JSON.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listedtoday

    What's inside

    Frequently Asked Questions

    The auditor identifies structural and content errors such as hidden null values (e.g., 'N/A' or '?'), type inconsistencies, duplicate rows, and constant columns that offer no analytical value. This prevents you from running broken data pipelines or making decisions based on incomplete exports.

    This skill is framework-agnostic and works with any AI agent capable of processing text or file attachments. It operates on raw CSV data, meaning you don't need a specific Python or Pandas environment to generate a quality report.

    No, this skill is strictly an auditing tool; it identifies and logs anomalies without modifying your source file. This ensures you have a clean audit trail before you decide which manual or automated cleaning steps to take.

    Your purchase includes the full skill configuration, the internal logic for the five-point quality scan, and the standardized Markdown reporting template. You also receive any maintenance updates or logic improvements released for this version.

    While it can handle very large datasets, the audit is most effective when the agent can access the full context of the file. For extremely large files, we recommend providing a representative sample to ensure the agent's context window isn't exceeded while maintaining audit accuracy.

    New in Agents & Orchestration