More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    csv insight report

    1

    Python 3.10+, pip install -r requirements.txt, one command to run.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    csv insight report

    csv insight report

    Example session with this skill installed

    Analyze sample_sales.csv. Is revenue significantly different across regions and product categories? Where are the strongest relationships? Give me charts and export the report as HTML.

    • Read your context and instructions
    • Compiled the csv insight report
    • Generated the data export

    I have analyzed sample_sales.csv. Data quality score:

    100 / 100 (Completeness 100 · Uniqueness 100 · Validity 100), 0 problems remaining after cleaning. Normality checks passed, so independent t-tests were auto-selected.

    Executive Summary

    DimensionGroupsMethodp-valueResult
    region -> revenueEast vs NorthIndependent t-test0.6504Not significant
    region -> profit_marginEast vs NorthIndependent t-test0.7340Not significant
    category -> revenueAppliances vs ElectronicsIndependent t-test0.0123Significant
    category -> unitsAppliances vs ElectronicsIndependent t-test0.0091Significant
    category -> profit_marginAppliances vs ElectronicsIndependent t-test<0.0001Significant

    Correlation Analysis (Pearson, |r| >= 0.3)

    Variable AVariable BrStrength
    revenueprofit_margin-0.66Moderate (negative)
    revenueunits0.48Weak (positive)

    Charts

    3 charts generated automatically: revenue by region (bar), revenue by category (box), correlation heatmap (Pearson).

    Deliverables

    • analysis_report.md — full report with quality score, cleaning audit and effect sizes
    • analysis_report.html — self-contained single file, charts embedded
    • analysis_report.pdf / .docx — via python export_report.py analysis_report.md pdf

    Business Findings

    Category drives performance — revenue, units and profit_margin all differ significantly between categories (p <= 0.0123); region does not.
    2.

    Higher revenue trades off margin — revenue and profit_margin are negatively correlated (r = -0.66): volume-driven sales dilute margins.
    3.

    Recommendation — focus pricing and inventory decisions at the category level; regional differences are statistical noise.

    Next step: run it on your own data — python agent.py your_file.csv --no-input, then export with export_report.py.

    sample_sales.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

    Upload a CSV, get back the report a data analyst would write: quality score -> cleaning audit -> hypothesis tests -> charts -> business findings, exported to Markdown / HTML / PDF / Word.

    • Runs without any API key. Deterministic statistical pipeline (scipy) with matplotlib charts; every stage falls back gracefully if the LLM is unavailable
    • Correct statistics, not vibes: normality test first, auto-selects t-test vs Mann-Whitney, reports effect sizes and plain-language conclusions
    • Encoding-proof: GBK/UTF-8/comma/tab auto-detected; never falls back to latin-1 mojibake
    • Guaranteed to finish: state-machine routing terminates in <=12 steps even when the LLM loops
    • Multi-format export with images embedded (single-file HTML/PDF/DOCX)

    Tested on Claude Code / Codex CLI. Python 3.10+, pip install -r requirements.txt, one command to run.

    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.

    Deterministic pipeline benchmark: 634 rows -> 0.53 s, 12,003 rows -> 0.85 s (fixed-seed synthetic data, reproducible via scripts/benchmark.py in the source repo). LLM mode adds model latency only.

    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 4 days ago

    Software
    Pythonpip

    No API key needed — the skill runs fully in deterministic mode. Optionally set OPENAI_API_KEY (plus OPENAI_BASE_URL / LLM_MODEL) in a .env next to the scripts to enable LLM-driven cleaning decisions and business insights. Charts are written to outputs/ and the report to analysis_report.md in your wo

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    *.csv
    outputs/**

    Runs `python agent.py <file.csv>` in the terminal: loads the CSV, computes quality score and statistics, writes charts to outputs/ and the report to analysis_report.md. Fully offline by default. If the buyer optionally configures an OpenAI-compatible key in .env, LLM mode makes network calls for cleaning decisions and business insights only.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    No. The pipeline runs fully without one — a key only adds LLM-written business insights.

    New in Research & Analysis