Agent skill

Product Shopping Search

by win4r in win4r/MuseAI-Skills

Guides an agent through product searches across a catalog, a browser agent and Facebook Marketplace, favoring low prices and citing each product it names.

No licenceAuto-check passedSales & Support

Install Product Shopping Search

skills CLI
$ npx skills add win4r/MuseAI-Skills --skill shopping -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install win4r/MuseAI-Skills shopping --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/win4r/MuseAI-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/opt/hatch/skills/shopping .claude/skills/shopping && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
shopping
GitHub stars
336
Used in
1 other repo
Token cost
~9.1k tokens
SKILL.md length
4,605 words
Files
4 (incl. references)
Skills in repo
25
Repo updated
First seen
Licence
None found

At a glance

Guides an agent through product searches across a catalog, a browser agent and Facebook Marketplace, favoring low prices and citing each product it names.

  • Works in 7 steps: Ensure you fully understand the user's… → Gather any relevant context that will be… → Use the relevant search tools to execute… → …
  • Finding and comparing products with prices and links
  • SKILL.md covers Product search tools, User Preferences, Required attributes and Workflows, plus 5 more sections
  • Calls jq

What it does

The skill sets one goal, which is to save you money by finding good products at low prices that fit your constraints. It names three search tools: `meta-catalog-search` for quick lookups across Meta's catalog, strongest for fashion, home decor and beauty; `browser.spawn_task` for slower but wide web searches, run alongside the others for home goods in particular; and `facebook-cli` for Marketplace listings.

After choosing products, the agent passes the result files and ordered selected IDs to `shopping.resolve_results`, which normalizes the picks, returns a path for an optional shopping widget and returns citation markers. Those markers must be used every time a product is named, including follow-up answers, comparisons and status notes, not only in the final roundup. Reference files cover search backends, browser checkout and Shopify UCP.

When your agent uses it

  • Finding and comparing products with prices and links
  • Searching Facebook Marketplace listings
  • Working from an Instagram or Marketplace link or a product photo

Example prompts

  • “Find a washable wool rug and compare the cheapest good options.”
  • “Search Facebook Marketplace for a used standing desk near me.”
  • “Here is an Instagram link to a jacket; find where I can buy it for less.”

Requirements

  • The meta-catalog-search, browser.spawn_task and facebook-cli tools
  • The shopping.resolve_results tool

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Ensure you fully understand the user's request, resolving every required attribute above before you search.
  2. Gather any relevant context that will be useful when writing product search queries. Use browser.search to discover trends, well-known…
  3. Use the relevant search tools to execute product search queries. Always call browser product search (unless the user explicitly asked for…
  4. Review the search results. Filter out any that don't match the user constraints, aren't high quality, or are outside the normal price…
  5. If you don't find enough relevant search results, adjust your queries (and potentially your product search tools) and repeat steps 3-4.
  6. A request gets one shopping-results presentation, and it comes after every product search for that request has finished. Until then, do…
  7. If the user continues the original query in follow-up turns, maintain the constraints of the original request. Drop constraints only when…

What it can do on your machine

Read from SKILL.md and the folder at commit 38bbb45. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Product Shopping Search loads about 9.1k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 4,605 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~9.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 4,605 words (~9,113 tokens).

“You should always aim to save the user money. Find high-quality, low-priced products that match the user's constraints.”

— opening of SKILL.md by win4r
name
shopping
metadata.includeInPrompt
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (references) in opt/hatch/skills/shopping of win4r/MuseAI-Skills.

  • SKILL.md
  • references/backends.md
  • references/browser-checkout.md
  • references/shopify-ucp.md

Open the folder on GitHubat commit 38bbb45

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in win4r/MuseAI-Skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Product Shopping Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Product Shopping Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Shopping Search this skillwin4r/MuseAI-Skills3361 repos~9.1kAutomated safety check: PassNone
Seedance Ecommerce Adbeshuaxian/higgsfield-seedance2-jineng950—~11kAutomated safety check: PassNone
Product Reel Generatorgooseworks-ai/goose-skills1.2k1 repos~2.3kAutomated safety check: NotesMIT
Social Media Monitornexscope-ai/eCommerce-Skills1.1k—~584Automated safety check: PassMIT
Seedance Ecommerce Adbeshuaxian/higgsfield-seedance2-jineng950—~1.7kAutomated safety check: PassNone
Bright Data MCPbrightdata/skills2641 repos~3.7kAutomated safety check: PassMIT

Similar skills

  • Seedance Ecommerce Ad

    beshuaxian/higgsfield-seedance2-jineng

    Generate e-commerce product advertisement video prompts for Seedance 2.0 on Higgsfield.

    950 GitHub stars~11k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Product Reel Generator

    gooseworks-ai/goose-skills

    Generates Instagram-ready product reels from any e-commerce product page URL.

    1.2k GitHub starsUsed in 1 repo~2.3k tokens
    Sales & SupportAuto-check: notes
  • Social Media Monitor

    nexscope-ai/eCommerce-Skills

    Monitor social media mentions, trends, and competitor activity for e-commerce brands.

    1.1k GitHub stars~584 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Seedance Ecommerce Ad

    beshuaxian/higgsfield-seedance2-jineng

    使用 Seedance 2.0(Higgsfield)为电子商务产品生成广告视频提示。在用户想要产品广告、电子商务视频、产品展示、开箱、产品演示、购物广告、时尚广告、美容广告、食品广告或任何用于在线销售的商业产品视频时使用。触发条件:产品广告、电子商务、产品展示、Amazon视频、Shopify广告、Instagram店铺、TikTok店铺、产品商业广告、时尚视频、美容广告、食品广告、产品演示、…

    950 GitHub stars~1.7k tokensUpdated 6 mo ago
    Media & CreativeAuto-check passed
  • Bright Data MCP

    brightdata/skills

    Bright Data MCP handles ALL web data operations. An agent skill from brightdata/skills.

    264 GitHub starsUsed in 1 repo~3.7k tokens
    Productivity & AutomationAuto-check passed
  • Ecommerce Content Marketing

    LeoYeAI/openclaw-master-skills

    E-commerce content marketing strategy planner. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub starsUsed in 1 repo~5.3k tokens
    Writing & ContentAuto-check passed

More from win4r/MuseAI-Skills

All 25 skills in this repo
  • Withings Health Data Reader

    win4r/MuseAI-Skills

    Reads Withings body measurements, daily activity, sleep sessions and workouts through a bundled withings command line tool and returns typed JSON records.

    336 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Travel and Event Booking

    win4r/MuseAI-Skills

    Handles direct flight, hotel, restaurant and event-ticket bookings and live availability checks, loading the right category reference before searching or booking.

    336 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed
  • HealthEx Health Records

    win4r/MuseAI-Skills

    Connects to HealthEx through OAuth and its MCP server so you can ask about medications, lab results, conditions and other health records.

    336 GitHub starsUsed in 1 repo~3.7k tokens
    Auto-check passed
  • Muse Feedback Filer

    win4r/MuseAI-Skills

    Tells the agent when to offer, and how to file, a feature request or bug report with the Muse team through a feature-request command line tool, only with your approval.

    336 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check: warnings
  • Duffel Flight Booking

    win4r/MuseAI-Skills

    Defines how an agent searches, books and manages flights through the Duffel CLI, and watches a booked fare when you ask for ongoing price monitoring.

    336 GitHub starsUsed in 1 repo~7k tokens
    Auto-check passed
  • Forget Personal Information

    win4r/MuseAI-Skills

    Removes a personal fact or past event from Muse's memory and from reminders, summaries and scheduled work that could bring it back, after you confirm a plan.

    336 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check: warnings

Works with

Categories

Questions about Product Shopping Search

What does Product Shopping Search do?

Guides an agent through product searches across a catalog, a browser agent and Facebook Marketplace, favoring low prices and citing each product it names. The skill sets one goal, which is to save you money by finding good products at low prices that fit your constraints.spawn_task` for slower but wide web searches, run alongside the others for home goods in particular; and `facebook-cli` for Marketplace listings.

When should I use Product Shopping Search?

Product Shopping Search fits situations like: finding and comparing products with prices and links; searching Facebook Marketplace listings; working from an Instagram or Marketplace link or a product photo.

How do I install Product Shopping Search in Claude Code?

Run `npx skills add win4r/MuseAI-Skills --skill shopping -a claude-code`. Or copy the skill folder (opt/hatch/skills/shopping in win4r/MuseAI-Skills) into .claude/skills/shopping in your project. Claude Code loads it when a task matches its description.

How do I install Product Shopping Search in Codex?

Run `npx skills add win4r/MuseAI-Skills --skill shopping -a codex`. Or copy the skill folder (opt/hatch/skills/shopping in win4r/MuseAI-Skills) into .agents/skills/shopping in your project. Codex loads it when a task matches its description.

Can I use Product Shopping Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add win4r/MuseAI-Skills --skill shopping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shopping, .gemini/skills/shopping, .github/skills/shopping and .opencode/skills/shopping in your project.

What does Product Shopping Search need to run?

Going by SKILL.md and its folder, Product Shopping Search needs the command-line tools its instructions call (jq). Our summary lists: The meta-catalog-search, browser.spawn_task and facebook-cli tools; The shopping.resolve_results tool.

Does Product Shopping Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Product Shopping Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Product Shopping Search use?

No licence was found for Product Shopping Search or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Product Shopping Search use?

About 9.1k tokens (SKILL.md is roughly 36k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.8k tokens, read only when the agent opens those files.

What are the alternatives to Product Shopping Search?

Skills that share tags, products or a category with Product Shopping Search: Seedance Ecommerce Ad (beshuaxian/higgsfield-seedance2-jineng, 950 stars), Product Reel Generator (gooseworks-ai/goose-skills, 1.2k stars), Social Media Monitor (nexscope-ai/eCommerce-Skills, 1.1k stars) and Seedance Ecommerce Ad (beshuaxian/higgsfield-seedance2-jineng, 950 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Shopping Search?

win4r (a GitHub user) maintains it in win4r/MuseAI-Skills, which has 336 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 28, 2026.

Source: win4r/MuseAI-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.