Wikipedia Discovery logo

Wikipedia Discovery

Community
hugobowne
wikipedia-discovery

Use when navigating Wikipedia inside the split-pane extension—finding articles from a topic or phrase, teaching or routing the user toward articles, choosing what to explore next, Wikimedia REST or Action APIs with paging, or sending message_parent url_change (optional section `#fragment` on the same wiki). Use for Wikipedia search, summaries, links/backlinks, or updating the mirrored page URL.

Overview

Publisherhugobowne
Repositoryshow-us-your-agent-skills
Skill namewikipedia-discovery
Stars
70
Forks
10
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hugobowne on GitHub. Read the source before you install it.

Installation

Install the Wikipedia Discovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hugobowne/show-us-your-agent-skills/tree/main/skills/wikipedia-discovery
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hugobowne/show-us-your-agent-skills.git /tmp/show-us-your-agent-skills
mkdir -p .claude/skills
cp -r /tmp/show-us-your-agent-skills/skills/wikipedia-discovery .claude/skills/wikipedia-discovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wikipedia Discovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wikipedia Discovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wikipedia Discovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wikipedia discovery

Use the current wiki hostname (e.g. en.wikipedia.org) for all API requests unless you intentionally switch language wiki.

Helping someone learn (user-facing)

When the user wants to learn about something, steer them toward concrete articles (and sections by heading when helpful). In natural language:

  • Name articles by title and briefly say why each is relevant to their question.
  • Do not paste full URLs, do not use markdown links, and do not bullet raw links—readers use url_change on their own; your job in chat is titles + relevance only.

Behind the scenes, when it is time to open the mirror, use message_parent with a full Wikipedia url (optional # section / anchor per below); that string is not for display in the user-visible reply.

I have a phrase / topic — find articles

Search the index, return ranked titles/snippets, optionally narrow namespaces. Prefer REST search for simple JSON cards; use Action API list=search when you need Cirrus options, generators, or wikitext-era fields. Paging: Action list= modules return continue — merge those params on the next request until absent. REST search may use limit / offset where supported. Details: wikipedia-discovery/references/topic-search.md.

I’m on (or chose) this article — what’s next?

Use summary for a short lead, links / backlinks to move outward in the graph, extracts for longer previews, categories / random when exploration fits. Same continue discipline for any prop/list that paginates. Details: wikipedia-discovery/references/article-next-steps.md.

Changing the Wikipedia URL (message_parent / url_change)

When the mirrored page should change, call message_parent with:

json
{"type": "url_change", "url": "<full https URL on wikipedia.org, optional #section-or-id>"}

url must stay on Wikipedia (*.wikipedia.org / wikipedia.org). Query APIs first when you only need metadata; send url_change when the left pane should actually load that resource.

Section (scroll to heading): append # + heading with spaces → underscores, correct case. Example payload (for the tool, not for pasting to the user):

json
{"type": "url_change", "url": "https://en.wikipedia.org/wiki/Kitten#External_links"}

Section headings (# fragment)

Append # + section heading with spaces → underscores (MediaWiki heading ids usually follow this). Case-sensitive; wrong casing may jump to the top. Fragile: renamed or removed headings break the target. If punctuation is odd, copy the heading’s id from the live DOM (mw-headline / stable anchor) instead of guessing.

Custom anchors

Template:Anchor (or other fixed ids) — the fragment is # + that id, which may differ from the visible heading string. Prefer copying #... from the browser once, or inspect the element’s id.

The left pane is an iframe; normal #fragment scrolling (heading / id) is what url_change should rely on for deep-linking inside the mirror.

The parent extension never reloads the full tab or the right (localhost) pane: only the left iframe navigates. history.replaceState updates the address bar only when url is same origin as the tab; another *.wikipedia.org host still loads in the left iframe but the tab’s visible origin cannot change without a full navigation (which we avoid).

Reference files

FilePurpose
wikipedia-discovery/references/topic-search.mdTopic → article discovery (APIs)
wikipedia-discovery/references/article-next-steps.md“What next” from a known page (APIs)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wikipedia Discovery AI skill do?

Use when navigating Wikipedia inside the split-pane extension—finding articles from a topic or phrase, teaching or routing the user toward articles, choosing what to explore next, Wikimedia REST or Action APIs with paging, or sending message_parent url_change (optional section `#fragment` on the same wiki). Use for Wikipedia search, summaries, links/backlinks, or updating the mirrored page URL.

Why use Wikipedia Discovery on TypingMind?

Because you install it once and use it with any model. Wikipedia Discovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wikipedia Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hugobowne/show-us-your-agent-skills/tree/main/skills/wikipedia-discovery. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wikipedia Discovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wikipedia Discovery?

As many as you like. As long as a model supports skills, you can use Wikipedia Discovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wikipedia Discovery AI skill free?

Yes. It is published on GitHub by hugobowne under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇