Uber Eats Order logo

Uber Eats Order

Organization
pockebot
uber-eats-order

Order food or groceries end-to-end in the Uber Eats consumer app. Use when the user asks to open Uber Eats, browse merchants, add items, customize options, apply promos, choose delivery or pickup, place an order, or track order progress.

Overview

Publisherpockebot
Repositoryopenpocket
Skill nameuber-eats-order
Stars
848
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by pockebot on GitHub. Read the source before you install it.

Installation

Install the Uber Eats Order AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pockebot/openpocket/tree/main/skills/uber-eats-order
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pockebot/openpocket.git /tmp/openpocket
mkdir -p .claude/skills
cp -r /tmp/openpocket/skills/uber-eats-order .claude/skills/uber-eats-order
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Uber Eats Order in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Uber Eats Order on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Uber Eats Order is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Uber Eats Order

Use this skill to complete Uber Eats ordering flows with high reliability and low spend risk.

This skill is aligned with Uber Eats official help flows:

  • place order path (View cart -> Go to checkout -> Place order)
  • cancellation behavior (free before merchant accepts; possible charges after acceptance)
  • post-order tracking and support entry points.

Preconditions

  • Confirm Uber Eats app is in foreground (com.ubercab.eats).
  • If app is not installed, install and open it first.
  • If login/sign-up is required, trigger request_human_auth(oauth).
  • If payment verification (card CVC, bank OTP, 3DS) appears, use request_human_auth(payment) and/or request_human_auth(sms-2fa).

Canonical Ordering Flow

Follow this baseline sequence unless the current screen requires a detour:

  1. Choose merchant.
  2. Add item(s) to cart.
  3. Tap View cart, then Go to checkout.
  4. Review delivery details and payment.
  5. Tap Place order.
  6. Track order status.

UI Anchors (Common)

Treat labels as variants; exact wording may differ by locale/A-B test.

  • Bottom tabs: Home, Search, Cart, Account.
  • Entry controls: Delivery / Pickup, ASAP / Schedule, address chip near top.
  • Item actions: Add to cart, Customize, Required, Optional, Add.
  • Cart/checkout actions: View cart, Go to checkout, Checkout, Place order.
  • Order status actions: Cancel order, Help, contact courier/support.

Execution Procedure

1) Set fulfillment context first

  • Confirm fulfillment mode with user intent: Delivery vs Pickup.
  • Confirm destination/address before selecting items.
  • If scheduling is requested, set Schedule before checkout.

2) Find the right merchant

  • Prefer Search tab for deterministic lookup by merchant/dish.
  • If user gave constraints (budget, ETA, cuisine, rating), apply them before opening merchant page.
  • Avoid random browsing loops; open one candidate merchant and proceed.

3) Add items with correct modifiers

  • Open item detail page and resolve all required modifier groups.
  • Only submit Add to cart after required options are complete.
  • For multi-quantity, prefer explicit quantity control in cart over repeated back-and-forth on menu cards.

4) Cart review before checkout

  • Open View cart and verify:
    • item list and quantities
    • required modifiers were applied
    • promo/coupon status (if user asked)
  • Then proceed via Go to checkout (or equivalent checkout CTA).

5) Checkout verification

Before final submit, verify all high-impact fields:

  • fulfillment mode (Delivery or Pickup)
  • delivery address / pickup store
  • time (ASAP vs scheduled)
  • payment method
  • tip amount (if visible)
  • final payable total (items + fees + taxes + tip)

If user asked for constraints (for example max total), enforce them here.

6) Final confirmation gate (mandatory)

  • If user explicitly requested immediate purchase (for example “place it now”), proceed to Place order.
  • Otherwise, pause at checkout and ask via request_user_decision before tapping Place order.
  • Never silently submit an order when user intent is ambiguous.

7) After placing the order

  • Stay on tracking screen and report key status:
    • accepted/preparing
    • courier matched / en route
    • ETA updates
  • Keep notification-sensitive actions minimal unless user asks for changes.

Safety Guardrails

  • Never add Uber One subscription or any upsell without explicit request.
  • Never change payment method to new credentials without human auth.
  • Never place duplicate orders to “retry” without explicit user confirmation.
  • If checkout total materially exceeds user expectation, stop and ask before placing.

Changes and Cancellation Handling

Use Uber’s policy-aware behavior:

  • Before merchant accepts:
    • cancellation is typically free; cancel and reorder if major edits are needed.
  • After merchant accepts:
    • cancellation may incur charges.
    • do not cancel automatically; ask user first unless explicitly instructed.
  • If item change is blocked after acceptance:
    • use in-app Help / support path and report constraints to user.

Tooling Guidance

  • Prefer tap_element when reliable UI candidates are present.
  • Use batch_actions for short, deterministic same-screen edits (for example quantity +/- and confirm).
  • Use swipe to browse long menus and cart sections.
  • Use launch_app to recover quickly from background/app switch issues.
  • If two similar taps fail to change state, switch target (row body vs button) instead of repeating.

Completion Report

When finishing, include:

  • whether order was placed or stopped at checkout
  • merchant name
  • fulfillment mode (Delivery or Pickup)
  • scheduled time or ASAP
  • final total observed
  • latest order status (if placed)
  • any unresolved blocker requiring user input

Frequently asked questions

What does the Uber Eats Order AI skill do?

Order food or groceries end-to-end in the Uber Eats consumer app. Use when the user asks to open Uber Eats, browse merchants, add items, customize options, apply promos, choose delivery or pickup, place an order, or track order progress.

Why use Uber Eats Order on TypingMind?

Because you install it once and use it with any model. Uber Eats Order is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Uber Eats Order in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pockebot/openpocket/tree/main/skills/uber-eats-order. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Uber Eats Order?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Uber Eats Order?

As many as you like. As long as a model supports skills, you can use Uber Eats Order with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Uber Eats Order AI skill free?

Yes. It is published on GitHub by pockebot under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇