wikidata-vector-search SKILL.md skillA
wikidata-vector-search from fuzheado/wikipedia-ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fuzheado/wikipedia-ai-skills/wikidata-vector-search@git:20261005.0b77b7bPins git:20261005.0b77b7b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fuzheado/wikipedia-ai-skills
- Path
.claude/skills/wikidata-vector-search/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261005.0b77b7b, committed Oct 5, 2026
- First version recorded
- Jun 3, 2026
- Size
- 27,431 bytes
- Repository stars
- 27
- License
- MIT
Query Wikidata by meaning, concept, or natural-language description — not just by exact label match. Uses semantic embeddings to find items (QIDs) and properties (PIDs) via vector similarity, keyword search, and Reciprocal Rank Fusion. Covers fuzzy semantic search, concept matching, similarity lookups, cross-lingual queries, and "find like this" when you do not know the exact QID or label.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
> ⚠️ **User-Agent required:** All calls to the Vector Database API require a descriptive `User-Agent` header. Requests without one are blocked with HTTP 403. See the **[wikimedia-api-access](../wikimedia-api-access/SKILL.md)** skill for the correct format. > ⚠️ **Alpha-quality service:** The Vector Database is in early testing (v0.2.1). Results may be incomplete or inaccurate. Queries are sent to JinaAI for embedding and logged for up to 90 days. The `instanceof` filter is non-functional in the current release. The **Wikidata Vector Database** ([wd-vectordb.wmcloud.org](https://wd-vectordb.wmcloud.org/)), part of the [Wikidata Embedding Project](https://www.wikidata.org/wiki/Wikidata:Embedding_Project) led by Wikimedia Deutschland, stores semantic embeddings of Wikidata entities. By default (`scope=with_sitelinks`) it searches **~23 million** entities — those with at least one Wikipedia article, which is what the CC0 bulk dataset covers (23M unique entities, **44M vectors** across the language shards, 512-dim), computed from the **May 2026** Wikidata snapshot (see the project page's changelog). Since **September 2026** the database also indexes Wikidata items **without** a… …
Read the whole file at its exact version.
How to install
mdr add fuzheado/wikipedia-ai-skills/wikidata-vector-search@sha256:4e2ba8204d21eab8The line at the top of this page pins the label git:20261005.0b77b7b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_npdimoj3laa4nzg6)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Jun 3, 2026 and Oct 5, 2026, about one every 21 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.0b77b7b latest | 2026-10-05 | 0b77b7b | 27,431 B | A | view · diff |
| git:20261005.0a3c68a | 2026-10-05 | 0a3c68a | 26,276 B | A | view · diff |
| git:20260704.d9ec07e | 2026-07-04 | d9ec07e | 22,170 B | A | view · diff |
| git:20260621.2a11fde | 2026-06-21 | 2a11fde | 21,646 B | A | view · diff |
| git:20260610.740f144 | 2026-06-10 | 740f144 | 21,370 B | A | view · diff |
| git:20260605.1f6dcda | 2026-06-05 | 1f6dcda | 21,344 B | A | view · diff |
| git:20260603.1111be8 | 2026-06-03 | 1111be8 | 21,340 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (27431 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
fuzheado/wikipedia-ai-skills · 27 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_npdimoj3laa4nzg6 GET https://markdownregistry.com/api/v1/resolve?ref=fuzheado/wikipedia-ai-skills/wikidata-vector-search GET https://markdownregistry.com/api/v1/blob/4e2ba8204d21eab83a0486e876decb0ce370dd17660d903b919ad2a31a57ff58
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.