Skip to content

README.md

Latest commit

 

History

History
216 lines (143 loc) · 8.44 KB

README.md

File metadata and controls

216 lines (143 loc) · 8.44 KB
Raw

Diffbot — structured web knowledge for developers

An installable agent plugin that gives your coding agent access to Diffbot's web-scale knowledge graph and structured knowledge APIs. Query organizations, people, and articles with ontology-aware DQL — then enrich, extract, resolve entities, or crawl as needed.

Compatible with Claude Code, GitHub Copilot (CLI + VS Code), Snowflake Cortex Code, and Factory.ai (Droid).

Install

Install directly from this public Git repository on every supported harness. Curated marketplace shortcuts are listed below where a catalog entry exists or is in progress.

Pinned release: v1.1.0 — adds /diffbot-news, /diffbot-organizations, /diffbot-people, /diffbot-places, and /diffbot-deals.

From Git (recommended)

Claude Code

git clone https://github.com/diffbot/diffbot-skills.git ~/.claude/skills/diffbot-skills

GitHub Copilot (CLI + VS Code)

copilot plugin install https://github.com/diffbot/diffbot-skills.git

Snowflake Cortex Code (CLI)

cortex plugin install diffbot/diffbot-skills

Pin the release tag:

cortex plugin install github:diffbot/diffbot-skills@v1.1.0

Cortex Code Desktop: Agent Settings → Plugins → Add from GitHub → diffbot/diffbot-skills (append #v1.1.0 to pin the tag).

Factory.ai (Droid)

droid plugin install https://github.com/diffbot/diffbot-skills.git

ForgeCode: no installable manifest — copy or symlink the skills/ tree into .forge/skills/.

After install, invoke skills as /diffbot-dql, /diffbot-news, /diffbot-organizations, /diffbot-people, /diffbot-places, /diffbot-deals, /diffbot-web-search, /diffbot-extract, /diffbot-entities, and /diffbot-crawl.

From a marketplace (when listed)

Harness Install Catalog Status
Claude Code /plugin install diffbot@claude-plugins-official claude-plugins-official Submission in progress — see docs/listing/anthropic/
GitHub Copilot /plugin install diffbot@awesome-copilot awesome-copilot Submission in progress — see docs/listing/github/
Factory (Droid) droid plugin marketplace add https://github.com/Factory-AI/factory-plugins then droid plugin install diffbot@factory-plugins factory-plugins Not yet submitted — see docs/listing/factory/
Cortex Code cortex plugin install diffbot Official Cortex marketplace No public form — partner channel; Git install works today — see docs/listing/cortex/

Listing playbooks and handoff bundles: docs/listing/.

Setup

  1. Get a Diffbot API token at app.diffbot.com/get-started.
  2. Save it to ~/.diffbot/credentials:
DIFFBOT_API_TOKEN=YOUR_TOKEN_HERE

Run this once on your machine (the skill will not write credentials for you):

echo "DIFFBOT_API_TOKEN=YOUR_TOKEN_HERE" > ~/.diffbot/credentials && chmod 600 ~/.diffbot/credentials
  1. Invoke any skill — the first run bootstraps ~/.diffbot/venv and installs diffbot-python (>= 0.2.1) from PyPI.

Skills

Ten skills ship as one suite of structured-knowledge tools. DQL is the headline capability — ontology-aware entity querying that no other marketplace plugin offers. Five use-case skills sit on top of it for the queries people actually ask, and four API skills cover search, extraction, entity resolution, and crawling.

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

Knowledge Graph

/diffbot-news — News and articles

type:Article search, newest-first by default. Filter by mentioned entity, topic taxonomy, publisher, language, date range, or sentiment.

/diffbot-news recent AI news
/diffbot-news negative coverage of OpenAI this month
/diffbot-news what has Sam Altman been quoted saying
/diffbot-news European coverage of the Nvidia earnings

/diffbot-organizations — Company search

type:Organization search by industry, headquarters, headcount, revenue, funding, ownership, or leadership.

/diffbot-organizations public semiconductor companies in the US
/diffbot-organizations AI software startups in Berlin under 100 employees
/diffbot-organizations companies like OpenAI, US only
/diffbot-organizations companies Sequoia has invested in
/diffbot-organizations everything Microsoft has acquired

/diffbot-people — People search

type:Person search by job title, employer, employer industry, skills, education, location, or nationality. Covers people with a public online professional presence — it is not a people-finder for private individuals.

/diffbot-people who runs Nvidia
/diffbot-people CTOs at biotech companies
/diffbot-people Stanford CS alumni
/diffbot-people female CEOs

/diffbot-places — Geographic entities

Cities, counties, states, countries, regions, and points of interest — by name, population, prominence, containing place, or proximity.

/diffbot-places list all countries in Europe
/diffbot-places largest cities in Japan by population
/diffbot-places counties in California
/diffbot-places national parks near Yosemite

/diffbot-deals — Funding and M&A

Funding rounds, investments, and acquisitions by industry, date, size, series, investor, or company.

/diffbot-deals AI rounds over $50M this year
/diffbot-deals Sequoia's recent investments
/diffbot-deals largest acquisitions of 2026
/diffbot-deals OpenAI funding history

/diffbot-dql — Raw Knowledge Graph queries

The general-purpose escape hatch behind the five skills above. Use it for products, patents, job posts, facets, and anything else in the ontology. The agent translates your request into DQL, explores the ontology, probes query variants, and exports typed JSON or CSV.

/diffbot-dql products by a given brand
/diffbot-dql top cities where data scientists work
/diffbot-dql what industries dominate Berlin startups
/diffbot-dql job posts mentioning Rust in the last month

Web APIs

/diffbot-web-search — Live web results

Ranked results with relevance scores, URLs, dates, and content snippets. For general web pages and lookups that aren't news — use /diffbot-news for news.

/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 Diffbot KG records. Returns confidence, salience, sentiment, and Diffbot IDs usable in 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

Why DQL

The Diffbot Knowledge Graph is a web-scale store of structured entities — organizations, people, articles, products, and more — each with a typed ontology of fields, composites, enums, and taxonomies. DQL lets the agent:

  • Look up field names and types before constructing queries (db dql ontology)
  • Probe query variants in parallel to validate selectivity
  • Export results as JSON (for downstream analysis) or CSV (for display)
  • Run facet aggregations for distribution questions

This is structured knowledge querying — not page fetching, not generic web search.

Requirements

  • Python 3.10+ (used to bootstrap ~/.diffbot/venv)
  • diffbot-python >= 0.2.1, installed automatically on first run
  • Diffbot API token (free tier available)
  • A supported agent harness with plugin support (see Install)

Permissions

Each skill pre-authorizes a minimal fixed-path Bash allowlist: db, venv creation, pip install, and jq (Knowledge Graph skills only). No broad Bash(*) grants. Credentials are user-managed at ~/.diffbot/credentials and never stored in this repo.

License

MIT — see LICENSE.