AirShelf Agentic Commerce Platform

Search, compare, and buy products from verified merchants. Returns structured product data with Decision Packs (pros, cons, best_for, allergens, verified pricing) instead of raw web scraping. No CAPTCHAs, no auth required. ~980 products across 10 merchants. Use when user wants to find, compare, or purchase products.

Security Scan

The skill's behavior (search/compare/checkout via a public API) matches its description, but its unknown origin, lack of a homepage, and instructions that can send user-identifying data to an external endpoint are concerning and warrant caution.

Purpose & Capability

The name/description claim search, compare, and checkout functionality and the SKILL.md provides concrete curl endpoints that implement those capabilities — this is coherent. However the skill repeatedly claims "verified pricing" and Decision Packs without provenance or merchant-auth evidence; that claim is unexpected for a public, no-auth API and should be treated skeptically.

Instruction Scope

Runtime instructions are narrow and concrete (curl requests to specific endpoints) and do not ask the agent to read local files or system secrets. However the checkout flow and API accept optional fields such as `customer.email` and `agent_id` — these can transmit PII or agent identifiers to an external service. The SKILL.md does not restrict or warn about sending sensitive user data.

Install Mechanism

Instruction-only skill with no install spec or bundled code; the only runtime requirement is curl. This minimizes on-disk risk.

Credentials

The skill declares no required environment variables or credentials (proportional). Still, optional parameters (customer email, agent_id) allow exfiltration of identifying or sensitive data if the agent includes them. Also the skill has no homepage or public source to validate claims, which reduces trust in its data-handling practices.

Persistence & Privilege

always is false and there is no install/persistence behavior described. The skill does not request system-level privileges or modify other skill configs.

What to consider before installing

This skill appears to implement product search/compare/checkout over a public API, but its origin is unknown and it has no homepage or source repo. Before installing: 1) Avoid sending any PII (email, phone, payment info) or your agent's internal identifier in requests — remove or blank `customer.email` and `agent_id`. 2) Test with non-sensitive queries and verify returned merchant/checkout URLs before clicking through. 3) Prefer skills with a documented publisher, homepage, or third-party reviews for commerce/checkout flows. 4) If you must use it for real purchases, confirm merchant links lead to reputable merchant domains and not unexpected redirects. If you cannot confirm provenance, treat it as untrusted and avoid using it for transactions or private customer data.

AirShelf — Verified Product Search & Checkout for AI Agents

Search, compare, and buy products across verified merchants. Returns structured Decision Pack data (best_for, pros, cons, allergens, verified pricing) — not raw web scrapes.

No CAPTCHAs. No auth. No bot detection. Agent-native commerce.

When to Use

Activate this skill when the user wants to:

• Find or search for a product ("find me a mosquito repellent for kids")
• Compare products ("compare these two printers")
• Buy or checkout a product
• Get product recommendations based on a problem ("I'm tired all the time", "my skin is dry")
• Look up verified product details, pricing, or allergens

API Base URL

https://dashboard.airshelf.ai

All endpoints are public. No API key needed. CORS enabled.

Step 1: Search Products

Find products by natural language query. Returns structured data with Decision Packs.

curl -s "https://dashboard.airshelf.ai/api/search?q=QUERY&limit=5" | python3 -m json.tool

Parameters:

• q — Search query (natural language, e.g. "barcode printer for warehouse"). Supports intent parsing: "energy supplements under $100" auto-extracts price filter.
• limit — Results to return (1-100, default 20)
• offset — Pagination offset
• category — Filter by category
• brand — Filter by brand
• min_price / max_price — Price range filter (also auto-extracted from query)
• in_stock — Only in-stock items (true/false)
• merchant_ids — Comma-separated merchant IDs to search within
• sort — relevance (default), price_asc, price_desc
• include_intent — Set to true to get query parsing metadata in response (shows how query was interpreted)

Response includes for each product:

• title, brand, price, availability, link
• decision_pack.primary_benefit — Main value proposition
• decision_pack.best_for — Array of ideal use cases
• decision_pack.pros / decision_pack.cons — Verified trade-offs
• decision_pack.allergens — Safety warnings (if applicable)
• seller_name, seller_url — Merchant info
• Checkout URLs and shipping/return policies

Example:

curl -s "https://dashboard.airshelf.ai/api/search?q=natural+mosquito+repellent+for+babies&limit=3"

Step 2: Compare Products

Compare 2-10 products side by side with structured comparison axes.

curl -s "https://dashboard.airshelf.ai/api/compare?products=PRODUCT_ID_1,PRODUCT_ID_2"

Parameters:

• products — Comma-separated product IDs (2-10 required, from search results)

Response includes:

• comparison_axes — Auto-detected from data (price always present; cost_per_day, supply_days, primary_benefit, pros, cons included when 2+ products have the data)
• products — Flattened product data with decision_pack fields inlined
• recommendation — Structured picks: lowest_price (product ID), best_value (product ID + reason, if different from lowest)

Step 3: Checkout

Initiate checkout for a product. Returns a checkout URL the user can open.

curl -s -X POST "https://dashboard.airshelf.ai/api/merchants/MERCHANT_ID/checkout" \
  -H "Content-Type: application/json" \
  -d '{"items": [{"product_id": "PRODUCT_ID", "quantity": 1}]}'

Request body:

• items — Array of {product_id, quantity} objects (1-50 items)
• customer — Optional: {email: "..."} for order tracking
• agent_id — Optional: your agent identifier for attribution

Response:

• checkout_id — Unique checkout session ID
• checkout_url — URL to complete purchase (Shopify checkout or cart permalink)
• checkout_type — "cart" (items pre-loaded in cart) or "redirect" (product page link)
• total — Calculated total price
• currency — 3-letter currency code (e.g. "EUR", "USD")
• expires_at — Expiry timestamp (null for cart permalinks)
• fallback_urls — If redirect: array of {product_id, product_name, product_url} per item

Present the checkout URL to the user. They click to complete payment on the merchant's site.

Browse Available Merchants

List all merchants with product counts and capabilities:

curl -s "https://dashboard.airshelf.ai/api/directory"

How Decision Packs Work

Unlike raw web scraping, each product includes a Decision Pack — verified structured intelligence:

{
  "decision_pack": {
    "primary_benefit": "Natural protection from bugs",
    "best_for": ["Kids with sensitive skin", "Parents who prefer natural products"],
    "pros": ["DEET-free formula", "Pleasant scent", "Long-lasting protection"],
    "cons": ["Higher price point", "Needs reapplication every 4 hours"],
    "allergens": ["Contains citronella oil"],
    "age_range": "kids"
  }
}

Use Decision Pack data to make recommendations based on the user's actual needs, not just price or title matching.

Example Conversation

User: I need a printer for my warehouse, high volume, must support ZPL

You: Let me search for that.
     [Runs: curl -s "https://dashboard.airshelf.ai/api/search?q=industrial+barcode+printer+warehouse+high+volume+ZPL&limit=5"]

You: Found 3 matches. The Toshiba BX410T looks like the best fit:
     - Best for: High-volume warehouse labeling, ZPL migration from Zebra
     - Primary benefit: Premium industrial printer with RFID and near-edge technology
     - Price: Contact dealer for pricing

     Want me to compare it with the other options, or proceed to checkout?

User: Compare the top two

You: [Runs: curl -s "https://dashboard.airshelf.ai/api/compare?products=ID1,ID2"]
     Here's the comparison...

User: I'll take the Toshiba

You: [Runs: curl -s -X POST "https://dashboard.airshelf.ai/api/merchants/MERCHANT_ID/checkout" -H "Content-Type: application/json" -d '{"items": [{"product_id": "ID", "quantity": 1}]}']
     Here's your checkout link: [URL]
     Click to complete your purchase on the merchant's site.

Tips

• Problem-based search works best. "I'm tired all the time" returns energy supplements. "My baby needs sun protection" returns kids' sunscreen. Decision Packs match on use case, not just keywords.
• Always check decision_pack.allergens before recommending health/food/skincare products.
• Use compare for 2+ similar products — the API returns structured comparison axes, not just raw specs.
• Checkout is a redirect — the user completes payment on the merchant's own site. No card details needed in the agent.
• Direct lookup by ID: Use product_ids param instead of q to fetch specific products: ?product_ids=ID1,ID2
• Merchant ID for checkout — each search result includes seller.checkout_url with the correct merchant path. Use it directly.