KPI Sheet Analyst — Metrics Without Fiction

    1

    Analyze KPI sheets and CSVs into trends, anomalies, and next questions — confirm before overwriting source data.

    $24

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    KPI Sheet Analyst — Metrics Without Fiction

    Example session with this skill installed

    Analyze this weekly KPI CSV and flag anomalies.

    • Read your context and instructions
    • Compiled the kpi sheet analyst

    Summary

    Profiled the weekly KPI CSV and separated facts from inferences without inventing gaps.

    KPIGrainTrendNote
    Signupsweek+12% WoWFact from sheet
    ActivationweekflatDefinition unclear
    Churnweekspike week 3Possible weekend filter gap

    Profile: 14 weeks, 2 null weeks in churn, no duplicate dates.
    Inferences (labeled): activation flat may be segment mix — needs definition confirm.
    Questions: timezone of week start; paid vs free filter; owner of churn definition.

    Do not invent missing week values as zeros.

    Next steps

    1. Confirm definitions with stakeholder
    2. Re-run after filter fix
    3. Only then add formula columns

    Confirm before overwriting the source sheet.

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

    About this skill

    KPI Sheet Analyst turns spreadsheets and CSVs into honest metric readouts.

    • Confirm KPI definitions, grain, and filters first
    • Profile nulls, duplicates, and date ranges
    • Separate computed facts from inferences
    • Never invent missing KPI values
    • Confirm before overwriting source sheets or adding formulas

    You get SKILL.md plus a KPI framework reference and test prompts for live UAT.

    Requires CSV/pasted data. No direct live-sync to BI tools or cloud DBs. User must confirm all data modifications.

    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 24 days ago

    Permissions

    Read Files
    Listed27 days ago

    What's inside

    Frequently Asked Questions

    Unlike generic prompts that might guess your data's meaning, this skill enforces a 'Definition Check' phase to verify time grains and metric logic before any analysis occurs, preventing hallucinated insights.

    The skill is compatible with CSV files, spreadsheet exports, and pasted tables, and it integrates seamlessly with developer-focused AI tools like Cursor, Claude Code, Codex CLI, and Gemini CLI.

    To maintain strict data integrity, the agent will never overwrite your source data; instead, it proposes new columns or formulas and waits for your explicit approval before generating an updated file.

    The purchase includes the skill definition and workflow logic designed for your AI agent, along with a set of guidelines to help you get the most accurate trend and anomaly reports.

    Currently, the skill requires manual exports or pasted data; it does not support live-syncing or direct API connections to live BI platforms like Tableau or Looker.

    New in Research & Analysis