Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Ads Campaign Agent

    1

    Draft Google Ads and Meta campaign plans and analyze performance from exported reports.

    $59

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Ads Campaign Agent

    AI Ads Campaign Agent

    Example session with this skill installed

    Use AI Ads Campaign Agent to draft a 14-day Google Search campaign and Meta creative test for Riverside Cycle Repair, a fictional shop that serves customers within 6 km. We offer tune-ups and brake repairs, have six spare appointments per week, and can spend up to $700 across both channels. Count confirmed repair bookings as the primary conversion. Give me ready-to-review ad copy, a tracking QA checklist, and a test plan with a decision rule.

    • Read your context and instructions
    • Compiled the ai ads campaign

    Campaign draft

    Goal: Confirmed repair bookings.

    Area: 6 km around the shop.

    Pilot: 14 days, $700 proposed total. Search captures people looking for repairs now. Meta tests which creative brings people to the same booking page.

    CampaignStructure and targetingDraft allocation
    Google SearchTwo ad groups, Tune-ups and Brake Repair. Start with phrase and exact match for “bike tune-up near me” and “bicycle brake repair near me”. Send each group to its matching service page. Review negatives such as jobs, DIY, and wholesale against the keyword list.$420 total, $30/day average
    MetaOne local prospecting audience split between two creatives. Use the same placements, booking page, CTA and conversion event for both variants. Exclude customers with an existing booking if a suitable consented audience is available.$280 total, $140 per variant

    Search copy

    • Tune-ups — “Book a Bike Tune-Up” / “Get Your Bike Ride-Ready.” Description: “Get gears, brakes and tires checked. See available repair times and book online.”
    • Brake repair — “Local Bike Brake Repair” / “Book a Brake Check.” Description: “Squeaky brakes or weak stopping power? Book a workshop visit and choose an available time.”

    Meta creative: A opens with a short mechanic-led brake check. B opens with a real customer quote used with permission. Keep the caption and “Book Now” CTA identical. Hold variant B until the shop supplies an approved quote.

    Tracking check before launch

    1. Fire the primary event only after the booking system confirms the appointment and issues a booking ID. Track form starts separately.
    2. Make one test booking from each tagged channel URL. Confirm each booking appears once in the booking system and fires the intended conversion event in the platform's test tools. Refresh the confirmation page and verify it does not count twice. If Meta uses browser and server events, check that both carry the same event ID for deduplication.
    3. Confirm that a form abandon fires no booking event, a consent-denied test follows the site's consent rules, and analytics URLs and event payloads exclude names, emails and phone numbers. Record the attribution window and exclude test bookings from decision reporting.

    Meta test and decision rule

    Hypothesis: The mechanic explainer will generate confirmed bookings at a lower cost than the testimonial.

    Change: Creative only. Use a 50/50 traffic split where available and run up to 14 days with no mid-test creative swaps. Pause acquisition if the shop fills its six spare appointments in a week.

    For each arm, report spend, clicks, confirmed bookings and cost per confirmed booking (spend ÷ bookings). Check the result after the last cohort has had 72 hours to convert, or longer if measured booking lag warrants it. Treat a result as directional only if each arm has at least five confirmed bookings and one arm's cost is at least 20% lower. Otherwise report the test as inconclusive. With just 12 available appointments across two weeks, an inconclusive result is plausible.

    Launch gate: Confirm event deduplication, approved creative and available booking slots. The allocations above are draft estimates for this fictional example.

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

    About this skill

    Get a draft campaign structure, creative brief, conversion QA checklist and test matrix. The included Python helper pools a normalized CSV in one currency and calculates CTR, CPC, CVR, CPA and ROAS. Supports local exports and planning with no live ad account connection required.

    Cannot execute trades, publish ads, or authorize spend. Requires manual CSV exports for analysis. No multi-currency support in a single report.

    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 today

    Permissions

    Terminal / Shell
    Read Files
    Listedtoday

    What's inside

    Frequently Asked Questions

    This skill includes a structured campaign architect, a character-limit-aware creative generator, and a dedicated Python script (`metrics.py`) designed to process your CSV exports for accurate performance analysis.

    No, this agent operates as a strategic planning and diagnostic tool; it requires you to manually upload your performance CSVs and does not have the authorization to spend budget or modify live campaigns.

    The agent uses a built-in Python script for data processing to ensure all calculations—like ROAS and CVR shifts—are based on hard data rather than LLM probability, preventing the 'hallucinated metrics' common in standard prompting.

    While the agent generates platform-compliant copy, it also flags specific elements for manual review to ensure your creative meets the latest sensitive interest and industry-specific policy requirements.

    The skill is designed for any agentic environment that supports Python execution and CSV file uploads, making it compatible with most professional-grade AI agent platforms.

    Yes, the skill is optimized for both Google Search (handling match types and negative keywords) and Meta (handling audience prospecting and retargeting flows) within the same strategic workflow.

    New in Marketing & SEO