merge messy spreadsheets

    1

    Merge messy spreadsheets using a four-pass deduplication cascade with fuzzy matching and full audit trails.

    $5

    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 CLIDeepSeekDeepSeekMuseMuse+22 more

    merge messy spreadsheets

    Example session with this skill installed

    Merge all the CSVs in the /exports folder. Use the 'Company Name' and 'Email' columns to find duplicates. I want to see the audit trail for any fuzzy matches it finds.

    • Read your context and instructions
    • Compiled the merge messy spreadsheets

    I've processed 5 files (850 total rows).

    • Exact/Normalized: 120 auto-merged.
    • Fuzzy Gate: 14 clusters found.
      [Table showing: "Intl Business Machines" vs "International Business Machines Corp", Score: 92]
      Approve these merges to generate your Unique and Merge Audit sheets?

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

    About this skill

    The problem

    Standard deduplication tools fail when rows aren't byte-identical, leaving you with messy data full of typos, abbreviations, and reordered names. Manually reviewing thousands of rows to catch "Jon Smith" vs "Jonathan Smith" is slow and prone to human error.

    What it does

    • Consolidates multiple .xlsx, .xlsm, and .csv files into a single unified schema while preserving source file and row metadata.
    • Executes a four-pass matching cascade: Exact, Normalized (diacritics/case), Fuzzy (typos/reordering), and Semantic (synonyms/paraphrases).
    • Implements mandatory approval gates for non-exact matches, ensuring you review and sign off on fuzzy or semantic clusters before merging.
    • Generates a comprehensive audit trail sheet documenting every merge decision, similarity score, and the pass that triggered the match.
    • Auto-selects the most complete row (fewest nulls) as the canonical record while logging all dropped duplicates.

    Frameworks & tools

    Python, Pandas for data orchestration, RapidFuzz for string similarity, and Sentence-Transformers for semantic embedding analysis.

    Why this beats prompting it yourself

    Writing a script to handle multi-pass deduplication is complex, especially when balancing recall and precision. This skill provides a tested architecture that handles edge cases like Unicode normalization and diacritic folding, while preventing data loss through structured audit logs that simple LLM prompts cannot reliably maintain.

    Use cases

    • Merging disparate CRM exports where contact names and company titles vary slightly.
    • Cleaning up inventory lists with inconsistent naming conventions and abbreviations.
    • Deduplicating survey responses or form submissions containing paraphrased text.
    • Consolidating legacy spreadsheets into a single source of truth for database migration.

    Known limitations

    This skill is designed for stacking and deduplicating rows. It does not perform relational joins or VLOOKUP-style operations between different datasets.

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

    Designed for row stacking and deduplication only. Does not support relational joins or VLOOKUP-style merging between datasets. Multi-sheet workbooks require user input to select the target sheet.

    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 months ago

    Permissions

    Terminal / Shell
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill supports .xlsx, .xlsm, and .csv formats. It is designed to work with any AI agent or platform that supports Python-based data processing environments and file system access.

    Unlike standard tools that require exact matches, this skill uses a four-pass cascade—including fuzzy and semantic matching—to catch typos, reordered names, and synonyms. It also includes mandatory approval gates and a full audit trail, ensuring you never lose data during the deduplication process.

    Your purchase includes the full skill package, a detailed configuration guide for setting up your matching thresholds, and documentation on how to interpret the generated audit trail sheets. All necessary library dependencies like Pandas and RapidFuzz are pre-defined for easy setup.

    While the process is highly automated, the skill includes 'approval gates' for fuzzy and semantic matches. This means the AI identifies potential duplicates and asks for your sign-off before merging, giving you final control over data integrity.

    This skill is specifically built for deduplication and schema consolidation—merging similar records into one. It is not intended for relational operations like VLOOKUPs, SQL-style joins, or connecting separate tables based on primary keys.

    New in Data & Databases