lobsterbrew

Lobster Brew helps your OpenClaw discover coffee roasters, compare coffees, build personalized carts, and hand off a secure Shopify checkout link for you to complete the purchase.

3,891 stars

Best use case

lobsterbrew is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Lobster Brew helps your OpenClaw discover coffee roasters, compare coffees, build personalized carts, and hand off a secure Shopify checkout link for you to complete the purchase.

Teams using lobsterbrew should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/buy-coffee/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/abuiles/buy-coffee/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/buy-coffee/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How lobsterbrew Compares

Feature / AgentlobsterbrewStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Lobster Brew helps your OpenClaw discover coffee roasters, compare coffees, build personalized carts, and hand off a secure Shopify checkout link for you to complete the purchase.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# LobsterBrew Skill

Version: 1.2.0
Base URL: lobsterbrew.com

Lobster Brew helps your OpenClaw discover coffee roasters, compare coffees, build personalized carts, and hand off a secure Shopify checkout link for you to complete the purchase.

Use it when the owner wants to buy coffee, subscriptions, and brewing gear. Use it to discover merchants, inspect active offers, resolve merchant Shopify Storefront MCP endpoints, and prepare carts for owner checkout.

## What this skill does

- Uses this service as the directory and routing layer
- Uses each merchant's Shopify Storefront MCP endpoint for live catalog, cart, and checkout work
- Keeps the owner in control of payment by handing off Shopify checkout instead of completing payment directly
- Uses the installed skill file as the authoritative instruction source

## Versioning

- Treat `Version` in this file as the local skill version
- Do not re-fetch remote instructions during normal use
- Runtime requests to `lobsterbrew.com` are for directory data only
- If Lobster Brew returns a version header or version field that differs from this file, note that the local skill may be stale without changing behavior automatically

## Discovery

1. Start with `GET lobsterbrew.com/countries.md` to see supported countries
2. Choose a country that matches the owner's location when possible
3. Fetch `GET lobsterbrew.com/countries/{country_code}.md`
4. Use `GET lobsterbrew.com/offers/{country_code}.md` to prioritize active offers
5. Choose a merchant before using Shopify Storefront MCP

## Merchant connect

1. GET `lobsterbrew.com/merchants/{slug}/connect.md`
2. Read the returned merchant MCP URL
3. Connect to that merchant's Shopify Storefront MCP
4. Use that merchant MCP for:
   - catalog search
   - product details and availability
   - policy questions
   - cart retrieval
   - cart updates
   - checkout URL generation

Do not infer merchant MCP URLs yourself when a connect response is available.

Prefer the `.md` endpoints for agent consumption. Use the JSON endpoints only when a structured machine response is required.

Treat merchant MCP data as the source of truth for products, pricing, availability, cart state, and checkout URLs.

## Subscription products

When the merchant MCP exposes subscription choices, inspect subscription fields before updating the cart.

1. Check for:
   - `requiresSellingPlan` or `requires_selling_plan`
   - variant-level selling plan requirements
   - `sellingPlanGroups`
   - `sellingPlanAllocations`
   - available `sellingPlanId` values
2. If a subscription is optional, present both one-time and subscription choices.
3. If a selling plan is required, do not attempt a normal cart add without a `sellingPlanId`.
4. Ask the owner to choose a cadence unless a clear preference already exists in local memory.
5. Highlight subscription savings when `priceAdjustments`, `price`, or `compareAtPrice` show the subscription is cheaper than the one-time purchase.
6. Try the merchant MCP cart and checkout flow first.
7. If the merchant MCP cannot apply the required selling plan, tell the owner that this merchant flow is not supported yet.

## Cart rule

When updating carts, attach private cart attribute only if the merchant MCP supports cart attributes cleanly:

- `lb_source__ = lobsterbrew`

Otherwise omit the attribute instead of assuming support.

## Final handoff

When you finish, return a structured summary with:

- `merchant`
- `product`
- `variant`
- `purchase_type`
- `selling_plan_name`
- `selling_plan_id`
- `cadence`
- `savings_summary`
- `checkout_url`
- `resolution_path`

Use `resolution_path = mcp_cart` when merchant MCP created the cart.
Use `resolution_path = unsupported_subscription_flow` when a required selling plan could not be applied through the merchant MCP.

Say clearly when:

- the item is subscription-only
- the available cadences are every 1, 2, or 4 weeks, monthly, or similar
- the subscription saves money versus one-time purchase
- the merchant MCP could not attach the required selling plan and the flow is not supported yet

## Safety

- This skill is for merchant discovery and Shopify Storefront MCP routing, not product truth storage
- Keep preferences and prior purchases in your own local memory
- Do not attempt payment completion
- Return checkout URL to owner for approval and payment
- Do not infer merchant MCP URLs yourself when a connect response is available

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation