More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    McD Time Anchor (麦味时光锚点)

    1

    一句话点麦当劳:自动凑最优券、把每笔已核实支付沉淀成「时光锚点」,并推演平行宇宙里的另一种可能。

    Free

    1 useSecurity scanned

    McD Time Anchor (麦味时光锚点)

    Example session with this skill installed

    还是老样子,在公司楼下那家麦麦下单。

    • Read your context and instructions
    • Compiled the mcd time anchor

    已为你读取记忆档案。当前为午餐时段,为你锁定:麦当劳成都锦江区联升巷餐厅。

    极速单确认

    • 餐品:板烧鸡腿堡三件套(可乐去冰)
    • 价格:¥28.5 (原价 ¥34.5,已自动应用「超值午餐券」+「积分抵扣」)
    • 省钱:本次为你节省 ¥6.0

    回「好」下单,回「细说」看券怎么凑的。

    Next steps

    • 回复「好」获取官方支付链接。
    • 支付完成后告知我「付了」,我会将其记入你的时光锚点。
    • 询问「平行宇宙」查看如果不使用此优惠的累计支出对比。

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

    About this skill

    Ordering McDonald's shouldn't feel like a data entry task. This skill eliminates the friction of menu browsing by mapping your recurring orders to a persistent memory file and calculating the optimal coupon combinations via the mcd-mcp server. It automates the entire flow from store location to price optimization while maintaining a verifiable "Time Anchor" log of your actual purchases.

    What it does

    • Persistent Memory Management reads your profile.json to store "Usual" orders, favorite stores, and taste preferences like "no ice."
    • Price Optimization runs real-time calculations using calculate-price to find the cheapest coupon combinations for your specific order.
    • Geographic Awareness integrates with Amap or Baidu Maps to find the nearest open restaurant based on POI data or current weather conditions.
    • Order Verification performs post-payment reconciliation using query-order to ensure only confirmed transactions enter your history.
    • Scenario Projection uses historical "divergence" data to simulate alternative spending and flavor paths in a "Parallel Universe" mode.

    How it works

    1. Trigger the skill with natural phrases like "The usual" or "I'm hungry" to initiate store and meal detection.
    2. Review the minimalist confirmation prompt showing the optimized price vs. original price and the specific store location.
    3. Execute by saying "Yes" to receive a secure official McDonald's payment link, then notify the agent once paid to anchor the record.

    Frameworks & tools

    Built for the Model Context Protocol (MCP) using the mcd-mcp server. Supports Amap (高德) and Baidu Maps APIs for enhanced geolocation.

    Why this beats prompting it yourself

    Generic prompts cannot access live McDonald's inventory, real-time coupon stacks, or your specific order history. This skill bridges the gap between a LLM and the actual POS system, ensuring prices are accurate and preferences are remembered across sessions without repeating instructions.

    Use cases

    • One-word ordering for your daily office lunch using your "Usual" profile.
    • Budget optimization when you want the best deal on a specific set of items across available coupons.
    • Weather-based suggestions such as hot drinks on rainy days or ice cream during heatwaves.
    • Spending analysis to review total savings and order frequency over months of data.

    Known limitations

    Does not support third-party delivery platforms or payments outside the official McDonald's gateway. Geolocation accuracy depends on provided API keys.

    Requires mcd-mcp server and Bearer auth. Map features require Amap or Baidu keys. Only tracks confirmed payments in stats. Supports Chinese McDonald's infrastructure.

    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

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the entire McDonald's ordering process by syncing with the `mcd-mcp` server to apply the best available coupons, remember your specific customizations (like 'no ice'), and handle store selection based on your real-time location.

    The skill is built for the Model Context Protocol (MCP) and is compatible with any AI agent or platform that supports the `mcd-mcp` server, such as Claude Desktop or other MCP-integrated environments.

    You will receive the skill configuration files, access to the `mcd-mcp` server integration, and a schema for your `profile.json` to manage your persistent order preferences and history.

    To get started, you'll need to connect your `mcd-mcp` server credentials and optionally add an Amap or Baidu Maps API key if you want the skill to automatically detect the nearest restaurant based on your current location.

    New in Workflow Automation