Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    agentx multi agent data analyst

    1

    Multi-agent data intelligence for dataset profiling, verified statistical analysis, and document extraction.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    agentx multi agent data analyst

    agentx multi agent data analyst

    Example session with this skill installed

    Analyze sales_data.csv. What was the average 'total_revenue' in Q3, and are there any missing values in the 'customer_id' column?

    • Read your context and instructions
    • Compiled the agentx multi agent
    • Generated the data export

    The analysis of sales_data.csv is complete. I have calculated the requested metrics for the Q3 period (July-September) and performed a quality check on the customer identifiers.

    Data Analysis Report: Sales Q3

    Answer: $12,450.32

    • Field: total_revenue
    • Method: Arithmetic mean
    • Valid records: 1,240
    • Filters: Date range between 2023-07-01 and 2023-09-30
    • Missing values: 12 records with null revenue were excluded from the mean calculation.

    Interpretation: The average revenue per transaction remained stable compared to Q2, despite a higher volume of sales.

    Data Quality Check

    • Column: customer_id
    • Missing Values: 45 missing entries (3.6% of Q3 records).

    Observation: Missing IDs are primarily associated with "Guest Checkout" transactions. No duplicates were detected in the existing ID set.

    Next steps

    1. Generate a line chart showing the weekly revenue trend for Q3.
    2. Filter the 45 records with missing customer_id to see if they correlate with specific product categories.
    3. Compare these results against the Q4 forecast data.

    sales_data.csv

    CSV · data export

    Generated

    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

    Analyzing raw datasets or complex documents often leads to hallucinations or incorrect column mapping. This skill provides a multi-agent workflow for verifying calculations, inspecting data quality, and extracting grounded insights from structured and unstructured files.

    What it does

    • Multi-format ingestion processes CSV, Excel, Parquet, JSON, PDF, DOCX, and image-based documents.
    • Data profiling inspects schemas, missing values, correlations, and categorical distributions automatically.
    • Verified calculations computes descriptive statistics and groupings while explicitly reporting the valid sample size and filters used.
    • Visual intelligence generates Matplotlib charts including histograms, scatter plots, and heatmaps to reveal trends.
    • Document extraction performs OCR and text analysis on scanned files, preserving page boundaries and identifying tables.
    • Automated reporting structures findings into executive summaries with objectives, methods, and recommendations.

    How it works

    1. Source Inspection identifies file types and validates the integrity of the data or document structure.
    2. Column Mapping aligns natural-language questions to exact dataset headers, resolving synonyms or ambiguous fields.
    3. Execution & Critique runs statistical operations or extraction scripts and verifies the results against the raw source.
    4. Synthesis assembles the verified data into a structured response or a full-length Markdown report.

    Frameworks & tools

    This skill utilizes Python for data processing, Matplotlib for visualization, and specialized libraries for PDF/DOCX extraction and OCR.

    Why this beats prompting it yourself

    Generic prompts often guess at data types or hallucinate numeric totals. This skill enforces a strict multi-step verification process that requires the agent to check sample sizes and handle missing values before presenting an answer.

    Use cases

    • Sales analysis to calculate growth trends and categorical performance from CRM exports.
    • Legal review to extract specific clauses, dates, and entities from a batch of PDF contracts.
    • Technical audits to profile JSON/XML logs for outliers and missing data patterns.
    • Academic research to summarize PowerPoint presentations or complex Word documents with source-grounded evidence.

    Known limitations

    Requires a host environment with Python execution and file access. Visualizations and OCR depend on the availability of libraries like Matplotlib and specific document parsers in the runtime.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    Requires Python execution environment. Performance depends on installed libraries for OCR and charting. Cannot join files without clear keys.

    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 buying a skill.

    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 3 days ago

    Software
    Python
    Optional
    pandasMatplotlibExcel/Parquet support

    AgentX works with compatible AI agents that support skill instructions and file/data analysis. Python is optional and is required only for running the included helper scripts. Additional file formats depend on the tools and libraries available in your AI environment. No API keys or credentials are r

    Permissions

    Terminal / Shell
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that may hallucinate numbers, this skill uses a multi-agent critique loop to verify column mapping and sample sizes against the raw data before delivering results.

    The skill is designed for any AI agent platform that supports Python execution and file system access, as it relies on these to perform its deep data profiling and OCR tasks.

    Yes, the skill features a 'Document Extraction' module that uses OCR to process scanned PDFs and images, identifying tables and text while maintaining page-level grounding.

    The skill supports a wide range of structured and unstructured formats, including CSV, Excel, Parquet, JSON, PDF, DOCX, and common image formats.

    Upon purchase, you receive the complete multi-agent skill configuration, including the logic for data profiling, the visualization suite for generating Matplotlib charts, and the automated reporting templates.

    New in Research & Analysis