Wikis

Skill markbang/wikis-skill/skills/wikis

Query 250K+ Fandom, Miraheze, wiki.gg wikis. Search pages, infobox, images, Markdown. Live fallback for unsynced wikis via Cloudflare Worker.From its SKILL.md

Install

npx -y skills add markbang/wikis-skill --skill wikis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 935 tokens by cl100k_base, as published. Nobody here has run it

Wikis Skill

HTTP API skill for game/IP and community wikis (Fandom, Miraheze, wiki.gg, and live fallbacks). Prefer this when you need structured wiki data (search, page markdown, infobox, images) without HTML scraping.

Base URL: https://fff-wiki.neta.art

Coverage: 253,142+ wikis (full Fandom + Miraheze + wiki.gg), with live fallback.

Install this skill

npx skills add https://github.com/markbang/wikis-skill \
  --skill "wikis" \
  --agent codex \
  --yes \
  --copy

Config Space tip: install into your name=config Space and Save so it publishes to /configs/user/.agents/skills/wikis.

Endpoints

# List wikis
GET /wikis?page=0&size=20

# Search
GET /wikis/{wiki}/search?q={query}&page=0&size=20

# Pages
GET /wikis/{wiki}/pages/{title}?format=summary    # summary (fastest)
GET /wikis/{wiki}/pages/{title}?format=md         # Markdown
GET /wikis/{wiki}/pages/{title}?format=text       # plain text
GET /wikis/{wiki}/pages?category={cat}&page=0&size=20

# Structured
GET /wikis/{wiki}/infobox/{title}
GET /wikis/{wiki}/images/{title}?page=0&size=20

# Image proxy (anti-bot bypass, ~24h cache)
GET https://fandom-crawl.atou.workers.dev/proxy/image?url={image_url}

# Meta
GET /wikis/{wiki}/categories?page=0&size=20
GET /wikis/{wiki}/stats

{wiki} is the wiki id/slug (e.g. genshin-impact, dontstarve, minecraft).
{title} should be URL-encoded (spaces → %20).

Examples

# Search
curl -sS "https://fff-wiki.neta.art/wikis/genshin-impact/search?q=Hu%20Tao"

# Markdown page
curl -sS "https://fff-wiki.neta.art/wikis/dontstarve/pages/Wilson?format=md"

# Infobox
curl -sS "https://fff-wiki.neta.art/wikis/elden-ring/infobox/Malenia,%20Blade%20of%20Miquella"
curl -sS "https://fff-wiki.neta.art/wikis/pokemon/infobox/Pikachu"
curl -sS "https://fff-wiki.neta.art/wikis/naruto/infobox/Naruto%20Uzumaki"

# Category listing (default page=0&size=20)
curl -sS "https://fff-wiki.neta.art/wikis/minecraft/pages?category=Blocks&page=0&size=20"
curl -sS "https://fff-wiki.neta.art/wikis/dontstarve/categories"

# Image proxy
curl -sS "https://fandom-crawl.atou.workers.dev/proxy/image?url=https://terraria.wiki.gg/images/thumb/9/96/Brain_of_Cthulhu.png/800px-Brain_of_Cthulhu.png"

Agent guidance

Prefer format=summary first; upgrade to md / infobox when needed.
URL-encode titles and queries.
For knowledge Spaces: write API JSON/md into raw/wikis/..., then distill into wiki/ pages (do not treat curl output as the only memory).
Image hotlinking may fail — use the image proxy when fetching media.
This skill is HTTP API based. Optional local MediaWiki CLI: fandom-cli.

Repo: https://github.com/markbang/wikis-skill
Awesome Cohub: https://github.com/markbang/awesome-cohub
Alternative CLI skill: https://github.com/kjx-talesofai/claude-skill-fandom-cli

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.