LaunchKit · 2026
Back to Skills

query-wikidata

Transform natural language questions into SPARQL queries for Wikidata and generate beautiful HTML results pages.

0
0 downloads
by @kidehen

Setup & Installation

openclaw skills install @kidehen/query-wikidata

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install query-wikidata

What This Skill Does

Converts natural language questions into SPARQL queries and runs them against the Wikidata knowledge base. Returns results as JSON, Markdown tables, or styled HTML pages. Handles entity lookup, property mapping, and label resolution automatically.

Wikidata's structured Q/P identifier system and multilingual label service enable more precise, property-rich queries than DBpedia or plain web search.

When to use it

  • Finding all films directed by a specific person
  • Listing books by an author with publication dates
  • Querying capitals and populations of countries in a region
  • Retrieving Nobel Prize winners by category and year
  • Looking up birthplaces and dates for people in a given occupation

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: List all films directed by Christopher Nolan with release dates and budgets

AGENT
  1. 1Searches Wikidata to resolve Christopher Nolan's Q-number (wd:Q25191)
  2. 2Maps natural language fields to Wikidata properties: director P57, release date P577, budget P2130
  3. 3Constructs SPARQL query with label service and OPTIONAL clauses for missing properties
  4. 4Executes HTTP GET against https://query.wikidata.org/sparql with required User-Agent header
  5. 5Formats results into a styled HTML page with Wikidata branding and linked entity names
OUTPUT

HTML file saved locally listing 12 films with available release dates and budget figures, plus the executed SPARQL query displayed inline