Search Discovery logo

Search Discovery

OrganizationPopular
anthropics
search-discovery

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Not needed when one search for the thing the customer named answers the request, or when the customer wants to learn what matters in a category first (purchase-research).

Overview

Publisheranthropics
Repositorycommerce-agents
Skill namesearch-discovery
Stars
3K
Forks
574
Bundled files
Instructions only
LicenseApache-2.0
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 anthropics on GitHub. Read the source before you install it.

Installation

Install the Search Discovery 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/anthropics/commerce-agents.git /tmp/commerce-agents
mkdir -p .claude/skills
cp -r /tmp/commerce-agents/shopping-agent/skills/search-discovery .claude/skills/search-discovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Search Discovery 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 Search Discovery 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 Search Discovery 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.

Search and discovery

Below, "item" means whatever this catalog sells: a product, a stay, a plan, or a seat.

Turn the need the customer described into a few options and a recommendation, in as few turns as the request allows.

Read the request and phrase the search

  • Take the budget, the recipient, dates, sizes, intended use, and dealbreakers out of the message and apply them; let the results show that you did instead of reading them back.
  • Search by default; a budget, a size, or a recipient you were not given narrows the shortlist and is asked about beside the results. Ask first only when the search cannot be run without the missing fact (a stay with no dates), and then ask that one question, with the likely answers as chips.
  • Apply what the profile you were given already holds (household, saved limits, what they own) without asking about it again.
  • Word the query in the catalog's vocabulary and leave the customer's phrasing behind.
  • Run one search per distinct thing the request names, all in the same round. Put a constraint the customer stated in a filter; put a guess about what they might also want in the query wording.

Shortlist and recommendation

  • Show three to six options in present_products with the one you recommend first. Each pick's reason is one clause naming the customer's own constraint it meets. When the options differ in a way that matters, name that trade-off in the text.
  • When the customer has narrowed to two to four finalists, use present_comparison on the dimensions they raised instead of another row of cards.
  • Answer a question the results do not cover with get_product_details, or with web_search where one is registered; when neither settles it, say it is unknown.
  • Before saying that several options fit under a figure, add up their prices. When the sum is over, give the sum, and offer no chip for a bundle the sum rules out.
  • Show an item the store cannot supply right now as unavailable, and introduce whatever you offer in its place as a stand-in.
  • Keep the text before the component to one to three sentences of guidance.

When the item is for someone else

  • Take the recipient's age, interests, and the budget from the request, the profile you were given, or a recall result about this recipient; a fact saved about a different person does not transfer. When none of the three says who the recipient is, ask the one question, or show a varied set and say their tastes are unknown.
  • Where a spread helps, include one dependable pick, one meant to delight, and one that costs less.
  • Surface the practicalities the attributes carry (sizing, batteries, noise, the age marking) where they matter for this recipient. Read an age marking against the recipient's age: leave a mismatched item off, or show it with the mismatch stated.

Frequently asked questions

What does the Search Discovery AI skill do?

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Not needed when one search for the thing the customer named answers the request, or when the customer wants to learn what matters in a category first (purchase-research).

Why use Search Discovery on TypingMind?

Because you install it once and use it with any model. Search Discovery 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 Search Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/commerce-agents/tree/main/shopping-agent/skills/search-discovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Search Discovery?

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 Search Discovery?

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

Is the Search Discovery AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 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 👇