Agent Skills ​

▶ github.com/diffbot/diffbot-skills

Plug Diffbot into Claude Code, Github Copilot, Snowflake Cortex, and other agent harnesses. Skills abstract Diffbot APIs into distinct web research tasks ranging from web fetching (extract) to web search and entity resolution (NLP).

Installation ​

Installation instructions for popular agents listed in the README.

Skills ​

Five skills ship as one suite of structured-knowledge tools. DQL is the headline capability — ontology-aware entity querying that no other marketplace plugin offers.

Skill names are prefixed diffbot- to avoid collisions in the flat plugin namespace (e.g. /diffbot-dql, not /dql).

/diffbot-dql — Knowledge Graph queries ​

The agent translates your request into DQL, explores the ontology, probes query variants, and exports typed JSON or CSV.

/diffbot-dql find public semiconductor companies in the US
/diffbot-dql show me CTOs at public biotech companies
/diffbot-dql recent negative articles about OpenAI
/diffbot-dql top cities where data scientists work
/diffbot-dql software startups in Berlin under 100 employees with a female CEO

/diffbot-web-search — Live web results ​

Ranked results with relevance scores, URLs, dates, and content snippets.

/diffbot-web-search AI chip startups 2024
/diffbot-web-search recent earnings reports Tesla

/diffbot-extract — Structured page content ​

Fetch and extract structured content from any URL — markdown by default, full JSON on request.

/diffbot-extract https://example.com/article
/diffbot-extract https://example.com/product-page

/diffbot-entities — Named entity resolution ​

Identify and link entities in text to real entities in the Diffbot KG. Returns confidence, salience, sentiment, and Diffbot IDs for pulling more context via DQL.

/diffbot-entities Apple CEO Tim Cook announced record quarterly earnings.
/diffbot-entities Elon Musk founded Tesla and SpaceX.

/diffbot-crawl — Site crawling ​

Crawl a website for structured content and manage crawler jobs.

/diffbot-crawl https://docs.example.com
/diffbot-crawl https://example.com --url-process-pattern /blog/ --max-to-process 200