Online Shopping logo

Online Shopping

CommunityPopular
davidondrej
online-shopping

Research online purchases, prices, and shop trust. Use for buying advice, subscriptions, or shopping photos, links, and checkout screens.

Overview

Publisherdavidondrej
Repositoryskills
Skill nameonline-shopping
Stars
4.1K
Forks
599
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 davidondrej on GitHub. Read the source before you install it.

Installation

Install the Online Shopping 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.
  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/davidondrej/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/research-and-web/online-shopping .claude/skills/online-shopping
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Online Shopping 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 Online Shopping 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 Online Shopping 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.

Online Shopping Research

Auto-invoke for online purchases. Do not add disable-model-invocation or Codex allow_implicit_invocation: false.

Find a fair price, trusted places to buy, and legal checkout tax savings. Fable 5 is the preferred model for this skill.

Research only. Never place orders, create shop accounts, or enter payment, address, company, or VAT/tax details. Remind the user to enter them; never save those values in this skill or any file.

Keep every response concise and readable. Check it against How to answer before sending.

Setup

  • Read DEEPAPI_API_KEY and DEEPAPI_API_BASE_URL from the environment. If unset, try source ~/.deepapi/env; the default base URL is https://deepapi.co.
  • If the key is missing, stop and tell the user to get one at https://deepapi.co.
  • Never print, log, or expose the key.

DeepAPI

Use DeepAPI for all shopping research — not built-in search tools. Mix the endpoints however the task needs:

EndpointUse formaxCostUsd
POST /v1/search/webfind shops, prices, deals, reviews — run ~3 query variants"0.05"
POST /v1/scrape/websiteread the exact product page or listing the user is checking; verify an unknown shop"0.20"
POST /v1/research/deeppricing or market questions search cannot settle"0.10"
POST /v1/scrape/twitter/searchreal buyer complaints about a shop"0.03"

Every request: Authorization: Bearer $DEEPAPI_API_KEY, Content-Type: application/json, a unique Idempotency-Key per POST, and an explicit maxCostUsd.

bash
curl -sS -X POST "$DEEPAPI_API_BASE_URL/v1/search/web" \
  -H "Authorization: Bearer $DEEPAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: shop-$(uuidgen)" \
  -d '{"query": "Sony WH-1000XM5 price Germany", "maxResults": 5, "maxCostUsd": "0.05"}'

If status: running, poll GET /v1/requests/{requestId} after next.afterSecs. On HTTP 402, ask the user to top up at https://deepapi.co/credits.

VAT and sales tax

On checkout, subscription, or SaaS plan screens—especially Stripe or a VAT/GST/tax line—remind the user before paying:

  • If they have a company, buy as a business and enter its VAT ID (EU VAT number, Polish NIP, GSTIN, or local equivalent). For eligible EU B2B digital purchases, reverse charge can remove VAT from checkout.
  • Look for “purchasing as a business”, “VAT number”, “tax ID”, or “add billing details”. Currency changes do not remove VAT.
  • If tax is already $0 with a VAT ID, skip the reminder. If tax remains, check business status and VAT ID; do not promise removal without checking eligibility.
  • Never suggest a VPN, fake address, or borrowed card.

Treat tax as a possible legal saving; do not dismiss a valid business VAT option as “unavoidable tax”.

How to research

  1. Give first impressions before any research, whatever the price. In 1–2 sentences, react to the screenshot, link, or description: apparent value, seller reputation, or a rough price range. Make clear these are preliminary. For a checkout with VAT, include the company VAT ID reminder, unless tax is already $0.
  2. Identify the exact item and buying intent: what it is for, who it is for, and whether price, quality, or delivery matters most. Infer from context; ask one short question only if uncertainty would change the recommendation.
  3. Scale research to the price:
    • Obvious call: the screenshot or conversation is enough to judge; answer immediately, without searches or scrapes.
    • Cheap (roughly under $50): answer from existing knowledge. At most one quick web search if unsure; no scraping or deep research. Keep it especially brief.
    • Mid-range: a few searches; scrape the listing and one or two top competitors.
    • Expensive ($1,000+): deep research, several search variants, and scrapes of several shops and buyer reviews.

Use judgment within these limits. As needed for the price tier:

  • Infer the delivery country; ask if unclear. Find shops there or nearby with sensible shipping.
  • For branded merch, check the official store first. If none exists, suggest reputable print-on-demand shops and label the item unofficial.
  • Avoid scam and dropshipping shops. Verify unknown shops before recommending them. Watch for implausibly low prices, missing company info, fake urgency, and weeks-long shipping from a “local” shop.

How to answer

Draft, check, and revise against this format:

  • Fit on one screen: short sentences, plain English, readable Markdown.
  • Start with a bold verdict—good deal, fair, or overpriced—and the fair price range.
  • Use short bullets or a small table with the best 2–3 places to buy, links, and local-currency prices.
  • On checkout/subscription screens, add one short company VAT ID reminder when applicable.
  • Quote only prices actually found; clearly label preliminary estimates and say when results are thin.
  • Give conclusions without filler, hedging, or research narration. Report research costs only if asked.

Example:

markdown
**Verdict: Overpriced — fair price is €280–€330, this listing asks €449.**

| Buy from | Price |
|---|---|
| [amazon.de](https://www.amazon.de/...) | €289 |
| [mediamarkt.de](https://www.mediamarkt.de/...) | €299 |

Skip shiny-deals24.shop — €99 for this item is a classic scam price.

VAT: if you have a company, tick business and enter the VAT ID before paying.

Frequently asked questions

What does the Online Shopping AI skill do?

Research online purchases, prices, and shop trust. Use for buying advice, subscriptions, or shopping photos, links, and checkout screens.

Why use Online Shopping on TypingMind?

Because you install it once and use it with any model. Online Shopping 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 Online Shopping in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davidondrej/skills/tree/main/skills/research-and-web/online-shopping. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Online Shopping?

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 Online Shopping?

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

Is the Online Shopping AI skill free?

Yes. It is published on GitHub by davidondrej 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 👇