The Wikidata Query Skill empowers AI agents to translate plain English questions into complex SPARQL queries to extract structured data from Wikidata.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install query-wikidata
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install query-wikidata using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Wikidata Query Skill?
The Wikidata Query Skill is a sophisticated tool designed for developers and researchers who need to tap into the world's largest collaborative knowledge base. By integrating this skill into your workflow, you enable an AI agent to navigate the complex web of Q-numbers and P-numbers that define Wikidata's architecture. This Openclaw Skills component handles the entire lifecycle of data retrieval, from identifying the correct entity identifiers to executing optimized SPARQL queries.
Beyond simple data fetching, the skill excels at synthesizing information into human-readable formats. It bridges the gap between raw semantic data and actionable insights by providing automated label resolution and high-quality visualization options. Whether you are building a research assistant or a data-driven automation pipeline, this skill ensures your agent has access to real-time, property-rich information across millions of topics.
Wikidata Query Skill Use Cases
- Querying Wikidata using natural language to find specific entities like films, books, or historical figures.
- Generating beautiful, interactive HTML reports from complex datasets for stakeholder presentations.
- Extracting multilingual data with high temporal accuracy, such as publication dates and population history.
- Automating the creation of structured Markdown tables for documentation and technical research within Openclaw Skills.
How Wikidata Query Skill Works
- The skill analyzes the natural language prompt to identify the core subject and the desired properties.
- It resolves names into Wikidata Q-numbers (entities) and maps actions to P-numbers (properties) using a descriptive search process.
- A valid SPARQL query is constructed, incorporating the Wikidata Label Service to ensure results are returned with human-readable names instead of just IDs.
- The query is dispatched to the official Wikidata Query Service via a secure HTTP GET request with a specialized User-Agent.
- The returned JSON results are parsed and formatted into the user's requested output format, such as a styled HTML page or a Markdown table.
Wikidata Query Skill Setup
To utilize the Wikidata Query Skill, you must ensure your agent is configured to send the mandatory User-Agent header to avoid rate limiting. Use the following structure for manual interactions with the endpoint:
# Standard query execution via curl
curl -s -G "https://query.wikidata.org/sparql" \
-H "Accept: application/sparql-results+json" \
-H "User-Agent: Claude-Code-Wikidata-Skill/1.0" \
--data-urlencode "query=[SPARQL_QUERY_HERE]"
Wikidata Query Skill Data Schema & Taxonomy
The skill utilizes the standard Wikidata RDF structure. Data is organized through the following taxonomy:
| Component | Namespace | Description |
|---|---|---|
| Entities | wd:Q### | Unique identifiers for items (e.g., Spike Lee is Q51566) |
| Properties | wdt:P### | Direct relationship claims (e.g., P57 for Director) |
| Labels | rdfs:label | Human-readable names resolved via the Label Service |
| Results | application/json | The default machine-readable response format |
Wikidata Query Skill Advanced Features
- Multi-format output support including raw JSON, Markdown tables, and interactive HTML visualizations.
- Integrated Wikidata Label Service support for automatic English and multilingual translation of entity IDs.
- Pre-defined query patterns for common research tasks like geographic data extraction and biographical analysis.
- Automated SPARQL syntax highlighting and error handling for complex join operations.
- Seamless integration with the broader ecosystem of Openclaw Skills for multi-agent data research workflows.
SKILL.md
Loading
Related Openclaw Skills
DBpedia Query Skill
A powerful integration that transforms natural language questions into complex SPARQL queries to extract and visualize structured data from DBpedia.
sys-guard-linux-remediator
A forensically-aware framework for analyzing, securing, and remediating Linux hosts during security events using distribution-aware commands.
MemoryLayer
MemoryLayer is a high-performance semantic memory infrastructure that enables AI agents to store and retrieve relevant information with 95% token savings.
Academic Formula Converter
A specialized utility for converting LaTeX mathematical formulas within Markdown files into production-ready Word and HTML documents.
Virtuoso Support Agent
An advanced AI-driven assistant designed for technical support, database administration, and automated RDF Views generation for OpenLink Virtuoso Servers.
Adversarial Coach
A dialectical AI reviewer that validates implementation completeness against requirements through rigorous adversarial logic.
Featured*
