Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Daily Marketing Metrics CSV Builder — Tidy Report

    1

    Add each input with an optional source label, point the tool at a JSON column mapping, and choose how short dates get their year.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Daily Marketing Metrics CSV Builder — Tidy Report

    Daily Marketing Metrics CSV Builder — Tidy Report

    Example session with this skill installed

    Merge examples/north_funnel.csv and examples/south_funnel.csv with examples/columns.json, default year 2026, into examples/metrics.csv.

    • Read your context and instructions
    • Compiled the daily marketing metrics
    • Generated the data export

    The tool prints: OK rows=5 warnings=0 output=examples/metrics.csv

    date,label,line_cv,applications,attendances,closes,revenue,roas
    2026-04-01,north,1240,88,41,12,480000.00,2.40
    2026-04-01,south,610,44,20,5,210000.00,1.50
    2026-04-02,north,1305,92,45,15,612500.00,3.10
    2026-04-02,south,702,51,24,7,305000.00,2.00
    2026-04-03,north,980,70,33,9,360000.00,1.90

    metrics.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

    Daily marketing numbers often arrive as several CSV exports with inconsistent date and number formats: short dates with no year, currency marks, percent signs, and ratio marks like 2.4x. This small command-line tool cleans and merges them into one table.

    Add each input with an optional source label, point the tool at a JSON column mapping, and choose how short dates get their year. Count fields are written as integers; revenue and ratio keep two decimals. A clean run exits 0, a run with unparsable cells exits 1 with a warning, and a bad mapping or empty result exits 2. The tool only reads your inputs and writes the one CSV you name.

    The mapping file maps output fields (date, line_cv, applications, attendances, closes, revenue, roas) to zero-based source column indexes. The first line of every input is treated as a header and skipped; rows whose date does not match YYYY/M/D or M/D are skipped.

    Python 3.9+, standard library only. No network access. Includes a unit test file and example input CSVs with the expected output.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    The first line of every input is treated as a header and skipped. Rows whose date does not match YYYY/M/D or M/D are skipped. It does not reshape wide layouts, compute new metrics, or remove duplicate rows.

    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 days ago

    Software
    Python 3.9+

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    0 means rows were built and written with no unrecognized numbers (OK). 1 means rows were written, but one or more cells could not be parsed cleanly (WARN). 2 means a bad column mapping, an unreadable input, an unwritable output, or no dated rows (ERROR).

    Grouping separators, currency marks, percent signs and the x multiplier mark are removed before parsing. A leading minus, dash, triangle or a fully parenthesized value is read as negative. Dates in YYYY/M/D or M/D form are accepted; a short date uses --default-year, or the most common four-digit year in the data.

    A ZIP with the Python script, SKILL.md, README, example input CSVs with a column mapping file and the expected output CSV, a unit test file, and a LICENSE file.

    No. It reads your inputs and writes the one CSV you name. It never contacts a network and never changes the input files.

    Yes. Repeat --input for each CSV. A LABEL= prefix sets the source label; a bare path uses the file name without its extension. The output has one row per day and per label.

    It does not reshape wide layouts, compute new metrics, or remove duplicate rows. It normalizes and merges only the columns your mapping selects, and it skips the header line and any row whose date it cannot read.

    New in Workflow Automation