SKILL: Wikipedia (English) via wikipedia Python Module

Purpose

This skill enables OpenClaw to retrieve information from the English-language Wikipedia using the Python module wikipedia.

The skill focuses on:

• Searching for relevant pages
• Selecting the most appropriate result
• Retrieving page content
• Returning structured textual output

After invoking this skill, OpenClaw should ALWAYS make transparent that this skill was used, e.g. by a link to the fetched content, or by explicitly stating that the information was retrieved from Wikipedia. This is important for transparency and attribution. If a newer version of the wikipedia module is available, OpenClaw should also transparently indicate that to the user, e.g. by stating "A newer version of wikipedia-module is available: X.Y.Z (current: A.B.C). Give the developer of this skill a hint to update.". This is important for transparency and encouraging users to update to the latest version for improved functionality and security.

Installation

pip install wikipedia

Initialization

Always configure the language explicitly before performing any search:

import wikipedia

wikipedia.set_lang("en")

This ensures all search queries and page retrievals are executed against the English Wikipedia.

Searching for Pages

Use the wikipedia.search() function to find candidate pages.

Basic Search

results = wikipedia.search("Alan Turing")

This returns a list of page titles ordered by relevance.

Example output:

[
    "Alan Turing",
    "Turing machine",
    "Turing Award",
]

Recommended Search Strategy

Workflow for handling search results:

• Execute wikipedia.search(query, results=3) to limit noise.
• Select the most relevant title.
• Use the selected title to retrieve the full page.

results = wikipedia.search("Alan Turing", results=3)

if results:
    page_title = results[0]
    page = wikipedia.page(page_title)

Handling Ambiguity

Wikipedia may raise a DisambiguationError if the query is ambiguous.

Example:

from wikipedia.exceptions import DisambiguationError

try:
    page = wikipedia.page("Mercury")
except DisambiguationError as e:
    print(e.options)  # list of possible intended pages

Recommended approach: Select the most contextually relevant option Or refine the search query

Retrieving Page Content

Once a page is selected:

page = wikipedia.page("Alan Turing")

title = page.title
summary = page.summary
content = page.content
url = page.url

Recommended Output Strategy

For most use cases: Prefer page.summary for concise answers. Use page.content only if detailed information is required. Always include page.url for reference.

Error Handling

Handle the following exceptions: DisambiguationError PageError HTTPTimeoutError

Example:

from wikipedia.exceptions import PageError

try:
    page = wikipedia.page("NonExistingPageExample")
except PageError:
    print("Page not found.")

Structured Return Format

The skill should return structured data such as:

{
  "title": "...",
  "summary": "...",
  "url": "..."
}

Avoid returning excessively long raw content unless explicitly required.

Language Policy

Post-processing Note

If the user’s language is not English, OpenClaw should:

• Retrieve the content in English.
• Perform translation into the user’s language as a post-processing step.
• Clearly preserve factual accuracy during translation.

Best Practices

Example End-to-End Workflow

import wikipedia
from wikipedia.exceptions import DisambiguationError, PageError

wikipedia.set_lang("en")

def fetch_wikipedia_summary(query):
    try:
        results = wikipedia.search(query, results=5)
        if not results:
            return None

        page = wikipedia.page(results[0])
        return {
            "title": page.title,
            "summary": page.summary,
            "url": page.url
        }

    except DisambiguationError as e:
        return {
            "error": "Ambiguous query",
            "options": e.options[:5]
        }

    except PageError:
        return {
            "error": "Page not found"
        }

Limitations