What do I need to use Wiki Summary?

The topic; Language edition; Why they're asking.

Is Wiki Summary free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Wiki Summary

Q: How do I know the Wiki Summary output is good?

The skill verifies itself against its own quality checks: The extract is attributed to Wikipedia and dated — never blended into model voice; Ambiguous titles produced options, not a guess; Fact-checks compare the specific claim to the specific sentence; Training-memory vs. live-article deltas are called out when found.

🔵 Stable🕐 updated 2026-07-18 🔷 SkillSpec L3 pm-live

Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory. Use when asked what does Wikipedia say about X, get me the current summary of a topic, check a fact against Wikipedia, or has this article changed. Produces the live extract with the article link, disambiguation handling, and a clean separation between what Wikipedia says and what the model adds.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The topic — resolved to an article title (spaces → underscores); ambiguous names get the disambiguation treatment, not a silent pick

▸Language edition — en default; the endpoint pattern works on any edition (`de.wikipedia.org`, `ja.wikipedia.org`) and the user's question may belong in one

▸Why they're asking — a fact-check wants the specific claim compared; a primer wants the extract; "has this changed" wants fetched-vs-recalled differences called out

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The extract is attributed to Wikipedia and dated — never blended into model voice

✓Ambiguous titles produced options, not a guess

✓Fact-checks compare the specific claim to the specific sentence

✓Training-memory vs. live-article deltas are called out when found

✓The canonical URL appears

⚠️ What it refuses to do

Do not paraphrase the live extract into model voice — the fetch's value is the attribution

Do not silently pick among namesakes — disambiguate out loud

Do not treat Wikipedia as final authority for high-stakes facts — one good source, framed as such

Do not answer "what does Wikipedia say" from memory — that question is a fetch instruction by definition

Do not skip the URL — the link is the receipt

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="wiki-summary"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Wiki Summary is one of 743 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog