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。
记忆
gdelt-research
试用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.
它能做什么
Search and chart global news coverage and US television news via the GDELT Project's own indexes — full-text search, sentence-level context search, coverage/tone timelines, and (for TV) transcripts, captions, on-screen text, and computer-vision labels — all as normalized JSON from the Crawlora API,…
技能文档
News & TV coverage research (GDELT)
Search and chart global news coverage and US television news via the GDELT Project's own indexes — full-text search, sentence-level context search, coverage/tone timelines, and (for TV) transcripts, captions, on-screen text, and computer-vision labels — all as normalized JSON from the Crawlora API, no scraping.
When to use this skill
- "What's the recent news coverage of X?" / "Search global news for X."
- "How has coverage of X trended over time?" / "Is coverage of X positive or negative?" (timeline + tone/sentiment).
- "What sentences mention X near Y?" (sentence-level co-occurrence, last 72 hours only).
- "What did US TV news say/show about X?" (transcripts, captions, on-screen text).
- "Which TV stations/shows covered X the most?" / "What's trending on TV right now?" (word cloud, station/show comparisons).
- OSINT, media-monitoring, or political/social-science research needing a free, no-auth global news/TV corpus.
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
Web news:
- Search —
/gdelt/search(query, required; optionalcountry,domain,language,from/to/timespan,sort,maxrecords) searches GDELT's continuously updated global news index. - Context —
/gdelt/context(query, required;is_quoteto scope to quoted text) does sentence-level co-occurrence search — last 72 hours of coverage only. - Timeline —
/gdelt/timeline(query,metricfor volume vs. tone,smooth) returns how coverage volume or tone has trended over time. - Tone chart —
/gdelt/tonechart(query) returns a sentiment histogram for a query's matching coverage.
US television (GDELT Television 2.0 AI):
- Search —
/gdelt/tv-search(station, required; optionalshow,caption/transcript/onscreen_text/visual/concepttext filters and matchingexclude_*negations,day_of_week) searches transcripts, captions, OCR text, and computer-vision visual labels. - Timeline / comparisons —
/gdelt/tv-timeline(airtime volume over time),/gdelt/tv-showchart(top shows by coverage share),/gdelt/tv-stationchart(cross-station comparison) — same filter params as search,stationrequired. - Word cloud —
/gdelt/tv-wordcloud(station+channel, both required) returns a frequency-ranked word/label cloud for one match. - Reference lists —
/gdelt/tv-stationdetails(no params) lists current stations;/gdelt/tv-concept-entitiesand/gdelt/tv-visual-entities(limit) list GDELT's own Knowledge-Graph concept and computer-vision label catalogs, useful for building validconcept/visualfilter values.
Full endpoint list, methods, and params: reference/endpoints.md.
Calling the API
# Global news search:
scripts/crawlora.sh /gdelt/search query="semiconductor export controls" | jq '.'
# Coverage volume trend over time:
scripts/crawlora.sh /gdelt/timeline query="semiconductor export controls" metric=timelinevol | jq '.'
# Sentiment histogram:
scripts/crawlora.sh /gdelt/tonechart query="semiconductor export controls" | jq '.'
# US TV: search one station's coverage:
scripts/crawlora.sh /gdelt/tv-search station=CNN show="Erin Burnett OutFront" | jq '.'
# US TV: current station list:
scripts/crawlora.sh /gdelt/tv-stationdetails | jq '.'
Raw curl fallback:
curl -fsS -H "x-api-key: $CRAWLORA_API_KEY" \
"https://api.crawlora.net/api/v1/gdelt/search?query=web+scraping" | jq '.'
Endpoint reference
See reference/endpoints.md for every GDELT
web-news and Television 2.0 AI endpoint this skill uses.
Examples
- Media narrative tracking:
/gdelt/timeline(volume) +/gdelt/tonechart(sentiment) for the same query to see both how much and how favorably a topic is covered over time. - Cross-medium check: the same query through
/gdelt/search(web news) and/gdelt/tv-search(TV) to compare print/online vs. broadcast framing. - Breaking-story monitoring:
/gdelt/contextfor sentence-level co-occurrence in the last 72 hours — catches emerging framing before a full-timeline trend is visible. - TV coverage-share research:
/gdelt/tv-showchartor/gdelt/tv-stationchartto see which shows/stations are driving coverage of a topic.
Notes & limits
- Credits / pay-on-success: billed only on
2xx; free tier 2,000 credits/mo. Key at https://crawlora.net. - Public data only — GDELT's own public indexes; no authentication possible or needed upstream.
- Security: key lives in
CRAWLORA_API_KEYonly — never hardcode, query-param, or commit it. /gdelt/contextonly covers the last 72 hours — use/gdelt/searchor the timeline/tone endpoints for anything further back.- Every TV endpoint requires
station(/gdelt/tv-wordcloudalso requireschannel) — list valid values via/gdelt/tv-stationdetailsfirst if unsure. timespanandfrom/toare alternative ways to scope a date range — don't mix them; pick one.
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。
按用户明确指令,在得到大脑(Get笔记)中保存、搜索并管理笔记与知识库。
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。
为自然搜索排名提供站点审计、内容撰写与竞品分析。
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。
crawlora-org 的更多技能
浏览全部技能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.
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.
Queries Crawlora's pre-built hosted datasets — Airbnb markets, App Store/Google Play apps, GitHub/Instagram/X users, job postings, US housing markets, Google Maps businesses, Goodreads, PitchBook, Steam, TrustMRR, Product Hunt, SEC companies, tech-stack, and more — via search/facets/item/nearby endpoints, returning clean JSON without live-crawling each platform. Use when the user wants bulk or aggregate analysis, to search a pre-indexed corpus, to facet/filter a large population, or to look up one record by its dataset id, instead of scraping pages one at a time.
Researches music, artists, playlists, and podcasts via the Crawlora API — Spotify tracks/albums/artists/playlists/profiles, Spotify Podcasts, Apple Podcasts, Discogs, and SoundCloud tracks/profiles/playlists — returning clean JSON. Use when the user wants a track/album/artist's details, a playlist or profile, podcast show/episode info and charts, a record's Discogs release/pressing data, or a SoundCloud track/user's stats.
Researches Old Navy's catalog (and its Gap Inc. sibling storefronts Gap, Banana Republic, Athleta) — categories, products, colors/sizes, in-store pickup availability, and reviews — using the Crawlora API, returning clean JSON. Use when the user asks to find a product on Old Navy/Gap/Banana Republic/Athleta, browse a category, check in-store pickup stock at a specific store, or pull product reviews — instead of scraping oldnavy.com.