Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Weekly Deals

    1

    Transform Gmail and Outlook promotional emails into a structured weekly savings calendar with verified offer tracking.

    Free

    1 useSecurity scanned
    Weekly Deals

    Weekly Deals

    Example session with this skill installed

    Scan my Gmail promotions from the last 7 days and generate a weekly savings calendar. Use JEV for classification.

    • Read your context and instructions
    • Compiled the weekly deals

    I have scanned your Gmail promotions for the past 7 days. 42 messages were ingested, resulting in 12 unique offers after deduplication.

    Weekly Savings Calendar

    CategoryMerchantOfferDeadlineStatus
    FoodWhole Foods20% off prepared salads2023-11-15Verified
    TravelDelta Air Lines$50 off domestic flights2023-12-01Needs Confirmation
    ShoppingNike15% off member rewardUnknownVerified
    ServicesWag!First walk free2023-11-20Verified

    Notes on Extraction:

    • The Delta offer is marked

    Needs Confirmation because the redemption code is likely contained within an image asset that could not be parsed.

    • The Nike offer did not state a specific expiration date in the body text; it is listed with an

    Unknown deadline to avoid incorrect assumptions.

    • 3 duplicate reminders for the Whole Foods sale were collapsed into a single entry.

    Next steps

    • Run weekly-deals mark <offer-id> --status used to clear items from your list.
    • Check the generated calendar.html in your workspace for the full interactive view.
    • To see the raw data for unverified items, run weekly-deals pending.

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

    About this skill

    Manual tracking of promotional emails is a time-sink that often results in missed deadlines and clutter. DealWeek automates the extraction of coupons, discounts, and travel offers from Gmail and Outlook, turning a messy inbox into a structured savings calendar.

    What it does

    • Inbox Processing scans Gmail or Outlook for promotional content using JEV classification to filter out noise.
    • Fact Extraction pulls promo codes, redemption deadlines, and material restrictions into structured data.
    • Duplicate Grouping identifies repeated marketing campaigns to prevent calendar clutter while preserving unique offers.
    • Savings Validation flags offers that require a minimum spend above the user's typical habits or have conflicting terms.
    • Calendar Generation renders a self-contained HTML or JSON weekly view organized by category and expiration status.

    How it works

    1. Status Check runs weekly-deals status to verify Python environment, mail permissions, and JEV API configuration.
    2. Mail Ingest fetches messages from authorized providers and exports them as .eml files for normalization.
    3. Scan and Dedupe processes the local files to classify content and group repeating promotions using the configured budget.
    4. Calendar Render generates the final savings report or HTML calendar to review upcoming deadlines and verified offers.

    Frameworks & tools

    Built for Python 3.11+. Interfaces with Gmail API and Microsoft Graph/Outlook connectors. Uses JEV for classification and deduplication, with local storage for normalized email bodies and extraction drafts.

    Why this beats prompting it yourself

    Generic prompts often hallucinate deadlines or ignore fine-print restrictions hidden in footnotes. This tool uses deterministic validation to ensure every extracted claim is backed by a verbatim quote from the source text.

    Use cases

    • Grocery Budgeting by extracting weekly food and dining offers into a meal planner.
    • Travel Tracking to monitor expiration dates for airline and hotel promo codes.
    • Subscription Management by flagging "needs confirmation" terms for recurring services.

    Known limitations

    Requires Python 3.11+. Does not support Outlook .msg files directly. Cannot read terms embedded in images if has_unparsed_visuals is flagged. Extraction is primarily optimized for food and dining.

    Requires Python 3.11+. No support for .msg files. Visual-only terms in images are not extracted. Coverage is marked partial if mail fetch is interrupted.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Typesafe
    Sunsetcreamery
    Evil
    Googleapis
    Python

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    api.typesafe.ai
    cdn.sunsetcreamery.example
    sunsetcreamery.example
    evil.example
    www.googleapis.com
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the extraction of promo codes and deadlines from your Gmail or Outlook inbox, organizing them into a structured, noise-free savings calendar so you never miss a discount.

    The skill requires a Python 3.11+ environment and authenticated access to the Gmail API or Microsoft Graph; it is designed to integrate with AI agents capable of executing local Python scripts.

    Unlike basic prompts, this skill uses deterministic validation to cross-reference extracted dates and terms against the source text, significantly reducing the risk of hallucinated deadlines.

    Currently, the skill is optimized for food, dining, and travel promotions; it cannot process offers embedded purely in images or read Outlook .msg files directly.

    The purchase includes the full Python source code for the skill, JEV classification configurations, and the documentation needed to connect your mail providers and generate the calendar reports.

    New in Workflow Automation