把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
设计与多媒体
zara-research
试用Researches Zara's catalog — category taxonomy, category listings, product detail, keyword search, search suggestions, and nearby physical stores — using the Crawlora API, returning clean JSON. Use when the user asks to find a product on Zara, browse a Zara category, search Zara's catalog by keyword, pull a Zara product's colors/sizes/images, or find a nearby Zara store — instead of scraping zara.com.
它能做什么
Browse Zara's category taxonomy, list or search products, and pull full product detail (color variants, per-size stock, images) and nearby physical stores — all as normalized JSON from the Crawlora API, with no HTML scraping.
技能文档
Zara research
Browse Zara's category taxonomy, list or search products, and pull full product detail (color variants, per-size stock, images) and nearby physical stores — all as normalized JSON from the Crawlora API, with no HTML scraping.
When to use this skill
- "What does X cost on Zara?" or "find X on Zara."
- "Browse Zara's {section} category" / "what's in Zara's WOMAN/MAN/KID line?"
- "Search Zara for {keyword}."
- "Pull the colors/sizes/images for this Zara product."
- "Find the nearest Zara store to {location}."
Setup (one-time)
- Get a free Crawlora API key (2,000 credits/mo, no card) at https://crawlora.net.
export CRAWLORA_API_KEY=sk_your_key_here- All requests:
x-api-key: $CRAWLORA_API_KEYagainsthttps://api.crawlora.net/api/v1. Missing/invalid key →401.
How it works
- Browse categories —
/zara/categoriesreturns Zara's full US storefront category/subcategory tree (WOMAN, MAN, KID, etc). Each entry'sidis thecategoryIdto pass to category-products. - List or search —
/zara/category/{categoryId}/productsreturns a category's complete product listing in one call (Zara doesn't paginate this endpoint), or/zara/search(query,section) runs a keyword search with real offset-based pagination. Both return normalized products with pricing, images, and availability, one entry per purchasable color variant rather than one per color-grouped product. Use/zara/suggest(query) for typeahead search-term ideas before committing to a keyword. - Detail —
/zara/product/{productId}(numeric id, taken from a search/category result'surlfield, the digits after-p) fetches every purchasable color variant with its real marketing description, per-size stock, and full image gallery — richer than the listing/search summaries. - Stores —
/zara/storesfinds nearby physical Zara stores bylat/lng(both required — no free-text zip/city search), with optionalradius,pickup_only, anddonation_onlyfilters.
Full endpoint list, methods, and params: reference/endpoints.md.
Calling the API
# List categories to find a categoryId:
scripts/crawlora.sh /zara/categories | jq '.'
# Browse a category's full listing (no pagination):
scripts/crawlora.sh /zara/category/2417941/products | jq '.'
# Keyword search within a section, paginated:
scripts/crawlora.sh /zara/search query="linen shirt" section="MAN" limit=24 offset=0 | jq '.'
# Product detail (colors, sizes, images):
scripts/crawlora.sh /zara/product/12345678 | jq '{name,detail}'
Raw curl fallback:
curl -fsS -H "x-api-key: $CRAWLORA_API_KEY" \
"https://api.crawlora.net/api/v1/zara/search?query=linen+shirt§ion=MAN" | jq '.'
Endpoint reference
See reference/endpoints.md for every Zara
endpoint this skill uses (method, path, params, description).
Examples
- Category browse with pricing:
/zara/categoriesto find a section'scategoryId, then/zara/category/{categoryId}/productsfor the full listing — no paging needed, the response is already complete. - Search and compare:
/zara/suggestto refine a keyword, then/zara/search(paginated vialimit/offset) for candidates, then/zara/product/{productId}on the top picks to compare colors, per-size stock, and images before recommending one. - Local store check:
/zara/storeswithlat/lng(and optionallyradius,pickup_only,donation_only) to list nearby stores before telling a shopper where to try something on.
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 Zara product/category/store pages; respect Zara's terms.
- Security: key lives in
CRAWLORA_API_KEYonly — never hardcode, query-param, or commit it. - No reviews or Q&A endpoint — this build only covers categories, listings, product detail, search, suggest, and stores.
- Category listings aren't paginated —
/zara/category/{categoryId}/productsalways returns the category's complete listing in one call; only/zara/searchhas real pagination (limit/offset, zero-based offset, defaultslimit=24,offset=0). - Search is best-effort, not exact-match — for an obscure or nonsense
query, Zara's own search falls back to a broader recommended set instead of an empty result, and there's no field to distinguish that fallback from a true keyword match. An offset past the last result returns a normal empty page withis_last_page: true, not an error. - One entry per color variant, not per product — both
/zara/category/{categoryId}/productsand/zara/searchlist each purchasable color as its own entry;/zara/product/{productId}groups all of a product's colors together. - Product identity comes from the result URL —
productIdfor/zara/product/{productId}is the numeric id in a search/category result'surlfield (the digits after-p), not a SKU; an unrecognized id returns404. - Stores requires coordinates —
/zara/storesneedslatandlngdirectly; there's no zip/city text search.radiusdefaults to 30 miles (1–500). A location with no stores in range returns a normal response with an emptystoresarray, not an error.
相关技能
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
为自然搜索排名提供站点审计、内容撰写与竞品分析。
crawlora-org 的更多技能
浏览全部技能Researches Yahoo's editorial content network — Autos, Entertainment, Health, Life, News, Shopping, Sports, and Tech — via the Crawlora API, returning clean JSON. Each vertical shares a home/category story-stream plus full-article-content pattern; Yahoo Sports adds deeper sports-data endpoints (scoreboards, standings, team/player/roster, golf, MMA, motorsports, tennis, Olympics). Use when the user wants a Yahoo section's story feed, a Yahoo article's full content, Yahoo News comments, Yahoo Shopping deals/lists, or Yahoo Sports scores/standings/schedules. Yahoo Finance and Yahoo Search are covered by their own separate skills, not this one.
Compare luxury resale listings and sales
Fetches any company's job openings straight from its Applicant Tracking System (ATS) via the Crawlora API — Greenhouse, Lever, Workday, Ashby, SmartRecruiters, Workable, Personio, Recruitee, iCIMS, Oracle Recruiting, Rippling, Pinpoint, Eightfold, Gem, UKG, and Teamtailor — returning clean JSON. Use when the user wants every open role from a specific company's ATS-hosted career page, a single job posting's full detail, or a hiring-velocity snapshot for a company, given its ATS platform and company/board slug.
Researches products, prices, sellers, and reviews across major online marketplaces and big-box/specialty retailers (Amazon, eBay, Shopify stores, Shop.app, Target, Costco, Walmart, Nike, Zara, Adidas, Best Buy, Home Depot, Sephora, SHEIN, IKEA, Chewy, and more) using the Crawlora API, returning clean JSON. Use when the user asks to find a product, compare prices or sellers, track listings, or pull marketplace/retailer reviews — instead of scraping store pages.
Researches hotels, flights, attractions, short-term rentals, and live events via the Crawlora API — Booking.com, Expedia, Agoda, TripAdvisor, Trip.com, Airbnb, and Ticketmaster — returning clean JSON. Use when the user wants to search or compare hotel/stay prices and reviews, look up flight options, find attractions/things-to-do or concerts/events, or research an Airbnb host or listing.
Researches global news and US television coverage via the Crawlora API — GDELT web-news search/context/timeline/sentiment, plus GDELT Television 2.0 AI's index of US TV transcripts, captions, on-screen text, and visual labels — returning clean JSON. Use when the user wants coverage-volume or sentiment trends over time, cross-outlet news search, sentence-level co-occurrence search, or what US TV news said/showed about a topic — OSINT, media-monitoring, and political/social-science research.