More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ANSHora — Business Intelligence Analyst

    1

    Analyze business data, calculate reliable financial KPIs, uncover performance issues, and generate evidence-backed business recommendations.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    ANSHora — Business Intelligence Analyst

    Example session with this skill installed

    Analyze the included sample-business-data.csv file. Automatically identify the relevant revenue, cost, order ID, date, and category columns. Run the complete data quality audit and financial analysis. Show the all-rows and deduplicated KPIs, identify the main business performance drivers, and prepare an executive decision report. Clearly disclose assumptions and limitations.

    • Read your context and instructions
    • Compiled the anshora
    • Generated the data export

    Analysis of sales_data_q3.csv is complete. I have executed the deterministic audit and generated the financial breakdown.

    Executive Decision Report

    MetricAll RowsDeduplicated
    Data Health Score88/100-
    Total Revenue$452,300.50$448,100.00
    Total Gross Profit$185,443.20$183,721.00
    Weighted Margin %41.00%41.00%
    Average Order Value$1,256.39$1,244.72

    Data Quality & Trust Audit

    • Health Score: 88/100 (Status: High Trust)
    • Duplicate Exposure: 12 exact duplicate rows detected, totaling $4,200.50 in redundant revenue.
    • Outliers: 4 high-leverage transactions identified in 'Industrial' category for review.

    Segment Deep-Dive

    • Technology: 52% Revenue Share | 48.2% Weighted Margin.
    • Furniture: 28% Revenue Share | 31.5% Weighted Margin.
    • Office Supplies: 20% Revenue Share | 38.9% Weighted Margin.

    Root-Cause Investigation

    The 4.2% margin dip in Furniture is driven by

    Price Realization rather than cost inflation. Transaction logs show heavy discounting in the 'Seating' sub-category during the final two weeks of the quarter.

    Prioritized Recommendations

    1. Action: Cap discretionary discounts at 10% for the Seating category.
      • Owner: Sales Ops
      • Target Review: 2024-11-15

    Action: Audit the 4 identified outliers in Industrial to verify if these represent bulk contract pricing or entry errors.
    * Owner: Finance Lead

    Next steps

    • Would you like to simulate a what-if scenario for capping Furniture discounts?
    • Shall we perform a time-series breakdown to see if the margin dip is accelerating?

    sales_data_q3.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

    Business data is often messy, inconsistent, and prone to "hallucinated" insights when processed by standard LLMs. This skill eliminates guesswork by bridging a deterministic Python processing layer with expert financial reasoning to deliver audited, evidence-backed business intelligence.

    What it does

    • Data health auditing: Computes a 0-100 trust score based on missing values, duplicates, outliers, and type contamination.
    • KPI calculation: Derives weighted gross margins, revenue, COGS, and AOV using exact arithmetic rather than LLM estimation.
    • Root-cause decomposition: Analyzes whether performance shifts are driven by price realization, sales volume, or cost inflation.
    • Scenario simulation: Runs what-if models to project the impact of price changes or cost adjustments on the bottom line.
    • Executive reporting: Generates structured decision reports including prioritized recommendations and decision logs.

    How it works

    1. The user provides a CSV or tabular dataset and maps the relevant columns for revenue, cost, or dates.
    2. A local Python helper script profiles the data to generate a deterministic JSON summary of metrics and quality scores.
    3. The agent evaluates the results to perform segment deep-dives and identify profit leakage or margin gaps.
    4. The agent synthesizes findings into a 7-section executive report with specific business recommendations.

    Frameworks & tools

    This skill utilizes a Python-based deterministic layer (Standard Library) for calculation integrity and GitHub-flavored Markdown for structured reporting.

    Why this beats prompting it yourself

    Standard prompts often fail at weighted margin calculations and frequently hallucinate totals in large datasets. This skill uses a code-first execution model to ensure that every dollar reported is backed by exact row-level arithmetic and a documented audit trail.

    Use cases

    • Auditing transaction exports for duplicate revenue exposure and data contamination.
    • Investigating margin compression across different product categories or regions.
    • Simulating the profit impact of capping discounts for specific customer segments.
    • Generating weekly executive summaries from raw sales data for leadership teams.

    Known limitations

    Does not support direct processing of .xlsx or .xls files; users must export worksheets to CSV format. Multi-currency summation is blocked when distinct or ambiguous currency symbols are detected.

    Requires CSV/TSV format. Summation is blocked for mixed currencies. Outlier detection uses Tukey fences. Forecasting requires minimum 4 data points.

    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

    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

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    Standard LLMs often struggle with large-scale arithmetic, leading to 'hallucinated' totals. This skill uses a Python-based deterministic layer to perform exact calculations, ensuring your financial KPIs are mathematically accurate and audit-ready.

    You will receive the AI agent skill configuration, the required Python helper script for data profiling, and a structured template for generating executive decision reports. It includes everything needed to bridge your raw CSV data with the agent's reasoning engine.

    The skill is optimized for tabular CSV datasets. Before processing, you must export any Excel (.xlsx) workbooks to CSV format and ensure that your data uses a consistent currency, as multi-currency summation is currently blocked to prevent exchange rate errors.

    Setup involves importing the skill into your AI agent platform and hosting the provided Python script locally or in your sandbox environment. The agent will then guide you through mapping your CSV columns (like Revenue and COGS) to its internal financial model.

    Yes, the skill includes a data health auditing feature that computes a 0-100 trust score. It automatically identifies missing values, duplicates, and outliers, allowing you to clean your dataset before the agent performs any high-level analysis.

    New in Research & Analysis