More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Data Cleaning Guardrails

    1

    A hard-gated cleaning workflow that never guesses, never silently deletes rows, and always validates before handing data back.

    Free

    Security scanned
    Data Cleaning Guardrails

    Data Cleaning Guardrails

    Example session with this skill installed

    Clean this messy CSV I exported from our CRM — some emails are missing and one column looks shifted.

    • Read your context and instructions
    • Compiled the data cleaning guardrails

    The agent profiles the file first (rows, columns, 3-row sample), then outputs a diagnostic report: encoding check, missing counts per column, shifted-column suspicion.

    Diagnostic Report

    • Missing values: email 12% (14 rows), phone 3%
    • Column shift suspected: "contact" column contains mixed zip codes
    • Duplicates: 6 exact duplicate rows

    Proposed Plan

    • Problem: 12% emails missing -> Plan: offer drop / impute / skip -> Impact: 14 rows
    • Problem: 6 duplicate rows -> Plan: keep first occurrence -> Impact: 6 rows
    • Problem: shifted contact column -> Plan: flag, no auto-fix -> Impact: 1 column

    Expected result after cleaning: 860 rows x 18 columns.

    The agent then STOPS and waits for explicit confirmation — nothing is modified until you say yes. After cleaning it runs four validation layers (domain / statistical / sampling / shape) and an anomaly checklist (row-count drift > 20%, vanished categories, impossible values, missing rate > 10%) before calling it done.

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

    About this skill

    Most agents clean data too eagerly: regex-guessing mojibake, auto-dropping rows, and reporting "done" without validation. This skill installs a diagnose -> propose -> confirm workflow with hard gates:

    • No cleaning before the user confirms the plan
    • Never guess repairs for corrupted fields — flag them instead
    • Never auto-delete rows with missing values — present options
    • Four-layer validation (domain / statistical / sampling / shape) before any "done"

    Pure instruction skill — no dependencies, no scripts to run, works in any agent that follows SKILL.md.

    Requires user confirmation at multiple stages. Will not automatically repair undecidable encoding corruption or delete rows without explicit approval.

    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 3 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files

    File Scopes

    *.csv
    *.xlsx

    Instruction-only: the agent reads the user's data files, proposes a cleaning plan, and writes cleaned output only after explicit user confirmation. No scripts, no network access.

    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that might silently delete rows or guess values, this skill enforces a 'diagnose-propose-validate' workflow, requiring explicit user approval before any destructive changes are applied to your dataset.

    The skill is optimized for tabular data formats including CSV, Excel (.xlsx), and plain text files, making it ideal for CRM exports, database dumps, and scientific datasets.

    The package contains a single SKILL.md file — the complete hard-gated cleaning workflow: the diagnose checklist, the repair decision table (fix / offer candidates / flag), the four-layer validation rules, and the anomaly-detection triggers. It is lightweight by design: the intelligence lives in the instructions, not in bundled scripts.

    This skill is designed for agents with access to Python environments or data processing libraries, as it utilizes specific diagnostic scripts to ensure row count integrity and anomaly detection.

    No, the skill is intentionally designed with 'hard gates' that stop the process to seek human confirmation for any undecidable encoding or structural flaws, ensuring you maintain full control over your data.

    No specific framework required. It works in any agent that follows the SKILL.md standard — Claude Code, Codex CLI, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline and others. No dependencies, no scripts, no environment setup, no API key.

    New in Workflow Automation