Skip to content
Agentmart
Submit a tool

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…

Skill by hugobowne

IndexedMIT★ 70
Write a review

Chalk Labs

Need help deploying wikipedia-discovery?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hugobowne-wikipedia-discovery

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/wikipedia-discovery

What's inside

Skill name
wikipedia-discovery
Description
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.
License
MIT
Compatibility
Calls go to the active wiki host (e.g. en.wikipedia.org). The localhost panel must implement postMessage handling for tool message_parent with type url_change when navigation is required.
Instructions
57 lines in SKILL.md · view on GitHub

Files (4)

  • README.md
  • SKILL.md
  • article-next-steps.md · references/
  • topic-search.md · references/

SKILL.md (first lines)

# 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 **`id`s**) — 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

| File | Purpose |
|------|---------|
| `wikipedia-discovery/references/topic-search.md` | Topic → article discovery (APIs) |
| `wikipedia-discovery/references/article-next-steps.md` | “What next” from a known page (APIs) |

From hugobowne/show-us-your-agent-skills, MIT.

More from hugobowne/show-us-your-agent-skills

Signals

Stars
70
Forks
10
Open issues
0
Last commit (this folder)
Jul 3, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hugobowne

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get wikipedia-discovery running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying wikipedia-discovery?

CallGet help
Cite this page

wikipedia-discovery skill. Agent Mart. https://agentmart.dev/skills/hugobowne-wikipedia-discovery (last updated 2026-10-24)