Mode d’emploi
- Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
- Consultez le document original pour les outils, identifiants et environnements requis.
- Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/crawlora-org/crawlora-skills --skill walmart-researchAvant de commencer
- L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
- Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.
Walmart research
Look up and compare Walmart products, prices, and reviews — all as normalized JSON from the Crawlora API, with no HTML scraping.
When to use this skill
- "What does X cost on Walmart?" or "compare prices for X on Walmart."
- "Find listings for X on Walmart" / "search Walmart for this product."
- "Pull reviews / ratings for this Walmart product."
- "Track this Walmart product's price / availability."
- Competitive pricing or catalog research on Walmart.
Setup (one-time)
- Get a free Crawlora API key (2,000 credits/mo, no card) at https://crawlora.net.
- Set
CRAWLORA_API_KEYin the environment before running the helper. - The helper reads
CRAWLORA_API_KEYfrom the environment and sends requests tohttps://api.crawlora.net/api/v1. Missing/invalid key →401.
How it works
- Search / discover —
/walmart/search(qrequired) to find
candidate products by keyword.
- Detail — fetch a specific product with
/walmart/product/{item_id}
(the numeric id from a Walmart /ip/{id} URL) for price, availability, brand, images, rating, seller, description, highlights, specifications, and variants.
- Reviews — pull the on-page reviews snapshot with
/walmart/product/{item_id}/reviews: average rating, total review count, per-star breakdown, recommended percentage, top positive/negative review, and a sample of recent reviews.
Full endpoint list, methods, and params: `reference/endpoints.md`.
Calling the API
# Search Walmart (GET, key=value params):
scripts/crawlora.sh /walmart/search q="standing desk" | jq '.'
# Product detail (item_id is a path segment, not a query param):
scripts/crawlora.sh /walmart/product/414781783 | jq '.data'
# Product reviews:
scripts/crawlora.sh /walmart/product/414781783/reviews | jq '.'Use scripts/crawlora.sh for all requests; it keeps the API key out of command-line arguments.
Endpoint reference
See `reference/endpoints.md` for every Walmart endpoint this skill uses (method, path, params, description).
Examples
- Price check:
/walmart/searchfor a product name, grab theitem_id
of the best match, then /walmart/product/{item_id} for the current price and availability.
- Review summary:
/walmart/product/{item_id}/reviewsto summarize a
product's average rating, rating breakdown, and top positive/negative reviews before recommending it.
- Catalog sweep: paginate
/walmart/searchwithpageacross a set of
queries to build a candidate list, then fetch /walmart/product/{item_id} for each to compare prices.
Notes & limits
- Credits / pay-on-success: billed only on
2xx; free tier 2,000 credits/mo.
Key at https://crawlora.net.
- Public data only — public Walmart product/search pages; respect Walmart's terms.
- Security: key lives in
CRAWLORA_API_KEYonly — never hardcode, query-param, or commit it. - Search results are paginated — pass
pageto walk listings. - `item_id` is required for detail and reviews — it's the numeric id in a
Walmart /ip/{id} product URL, not the product slug.
- Reviews are a single on-page snapshot, not a full paginated feed — a
product with no reviews returns zero counts and an empty reviews list.
