Agent skill

Meilisearch

by xlanex6 in xlanex6/nuxt-meilisearch

Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance.

MITAuto-check passedBackend & APIs

Install Meilisearch

skills CLI
$ npx skills add xlanex6/nuxt-meilisearch --skill meilisearch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xlanex6/nuxt-meilisearch meilisearch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xlanex6/nuxt-meilisearch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/meilisearch .claude/skills/meilisearch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
meilisearch
GitHub stars
123
Token cost
~1.1k tokens
SKILL.md length
356 words
Files
10 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance.

  • Integrating Meilisearch
  • SKILL.md covers Core concepts, Quick start (JavaScript SDK), When to use which reference and Key rules to remember
  • Calls npm; needs MEILISEARCH_KEY
  • Building search UIs

What it does

Meilisearch is an agent skill from xlanex6/nuxt-meilisearch. Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance. Use when integrating Meilisearch, building search UIs, configuring indexes, embedders, ranking, filters, tenant tokens, or self-hosting.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `references/ai-search.md`, `references/api-reference.md` and `references/filtering-sorting-faceting.md`).

It sits in Backend & APIs, covering Search implementation. It works with Nuxt. The repository describes itself as: 🔎 Meilisearch module for Nuxt 3. The licence is MIT.

When your agent uses it

  • Integrating Meilisearch
  • Building search UIs
  • Configuring indexes

Example prompts

  • “/meilisearch”

Requirements

  • Node.js
  • Docker
  • A credential in MEILISEARCH_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit fe56224. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MEILISEARCH_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Meilisearch loads about 1.1k tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 356 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xlanex6/nuxt-meilisearch at commit fe56224, republished under its MIT licence (© xlanex6). 356 words, ~1,070 tokens.

Download SKILL.mdSave it as .claude/skills/meilisearch/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
meilisearch
description
Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance. Use when integrating Meilisearch, building search UIs, configuring indexes, embedders, ranking, filters, tenant tokens, or self-hosting.
metadata.source
Generated from https://www.meilisearch.com/docs/llms.txt

Meilisearch is an open-source, RESTful search engine optimized for fast, relevant, typo-tolerant search. It supports full-text, semantic, and hybrid (AI-powered) search, plus filtering, sorting, faceting, geosearch, and multi-tenancy. Available as Meilisearch Cloud or self-hosted; default port is 7700.

Core concepts

  • Instance: a running Meilisearch server, secured by a master key (self-hosted) and scoped API keys.
  • Index: a collection of documents with its own settings, identified by a uid (e.g. movies). Similar to a SQL table.
  • Document: a JSON object with fields. Each document must have a unique primary key (e.g. id).
  • Task: writes (add documents, update settings) are asynchronous and return a taskUid. Poll the task or use waitForTask to confirm completion.
  • Settings: per-index configuration controlling searchable/filterable/sortable attributes, ranking rules, synonyms, typo tolerance, embedders, etc.

Quick start (JavaScript SDK)

Install the official client and search in a few lines. Writes are async, so wait for the task before searching.

bash
npm install meilisearch
javascript
import { Meilisearch } from 'meilisearch'

const client = new Meilisearch({
  host: process.env.MEILISEARCH_URL, // e.g. http://localhost:7700
  apiKey: process.env.MEILISEARCH_KEY,
})

const task = await client.index('movies').addDocuments([
  { id: 1, title: 'The Matrix', genres: ['Action', 'Sci-Fi'], year: 1999 },
  { id: 2, title: 'Inception', genres: ['Action', 'Thriller'], year: 2010 },
])
await client.waitForTask(task.taskUid)

const results = await client.index('movies').search('matrix')

To filter, first declare filterable attributes, then pass a filter:

javascript
await client.index('movies').updateFilterableAttributes(['genres', 'year'])
const { hits } = await client.index('movies').search('', {
  filter: 'genres = "Sci-Fi" AND year > 2000',
})

When to use which reference

TopicDescriptionReference
Getting startedInstall (Docker/cURL/Cloud), connect, official SDKs, framework guidesgetting-started
Search/search parameters, pagination, highlighting/cropping, multi-search, federationsearch
Filtering, sorting, facetingFilter expression syntax, operators, facets, geosearchfiltering-sorting-faceting
IndexingDocuments, primary key, async tasks, batches, large importsindexing
RelevancyRanking rules, custom ranking, typo tolerance, synonyms, stop wordsrelevancy
AI-powered searchEmbedders, hybrid/semantic search, similar documents, conversational searchai-search
Index settings & APIFull REST endpoint map and settings referenceapi-reference
SecurityAPI keys, tenant tokens, multitenancysecurity
Self-hostingConfiguration, deployment, backups (dumps/snapshots), shardingself-hosting
Show full SKILL.md (105 more words)Show less

Key rules to remember

  • All write operations are asynchronous. Always confirm via task status before relying on the result.
  • An attribute must be in filterableAttributes before you can filter/facet on it, and in sortableAttributes before you can sort on it.
  • PATCH /indexes/{uid}/settings (and updateSettings) merges only the fields you send; sending null resets a setting to default.
  • Updating an index that does not exist via document or settings routes creates it automatically.
  • Prefer the POST /search route over GET for auth caching and performance.
  • Never expose the master key or admin API key to clients; use a search-only key or tenant token in the browser.

© xlanex6, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in .agents/skills/meilisearch of xlanex6/nuxt-meilisearch.

  • SKILL.md
  • references/ai-search.md
  • references/api-reference.md
  • references/filtering-sorting-faceting.md
  • references/getting-started.md
  • references/indexing.md
  • references/relevancy.md
  • references/search.md
  • references/security.md
  • references/self-hosting.md

Open the folder on GitHubat commit fe56224

Compare with similar skills

Meilisearch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Meilisearch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meilisearch this skillxlanex6/nuxt-meilisearch123—~1.1kAutomated safety check: PassMIT
Nuxt Contentsecondsky/claude-skills227—~4.3kAutomated safety check: PassMIT
Firecrawl Search Integrationfirecrawl/firecrawl190k1 repos~1.1kAutomated safety check: PassISC
Product Full-Text Searchlobehub/lobehub83k—~4.1kAutomated safety check: PassCustom licence
Hackernewssigcli/sigcli2931 repos~2kAutomated safety check: PassMIT
Nitro Server Toolkitantfu/skills5.9k—~948Automated safety check: PassMIT

Similar skills

  • Nuxt Content

    secondsky/claude-skills

    Nuxt Content v3 Git-based CMS for Markdown/MDC content sites.

    227 GitHub stars~4.3k tokensUpdated 10 days ago
    Frontend & DesignAuto-check passed
  • Firecrawl Search Integration

    firecrawl/firecrawl

    Guidance for adding Firecrawl's /search endpoint to product code and agent workflows when a feature starts from a query rather than a URL.

    190k GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check passed
  • Guides work on LobeHub's own product search: the shared search repository, provider choice, Elasticsearch mappings, change syncing and reindexing.

    83k GitHub stars~4.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Hackernews

    sigcli/sigcli

    Interact with Hacker News (news.ycombinator.com) — browse top, new, and best stories, read item details and comment threads, look up user profiles, and search posts via Algolia.

    293 GitHub starsUsed in 1 repo~2k tokens
    Backend & APIsAuto-check passed
  • Reference for Nitro v3, the server toolkit behind Nuxt: file routing, route rules, caching, storage, tasks, websockets and deployment presets.

    5.9k GitHub stars~948 tokensUpdated 9 days ago
    Backend & APIsAuto-check passed
  • Foundatio Repositories

    exceptionless/Exceptionless

    Query, aggregate, patch, or paginate Exceptionless data through its Elasticsearch repository abstractions.

    2.5k GitHub stars~1.9k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from xlanex6/nuxt-meilisearch

  • Create Skill

    xlanex6/nuxt-meilisearch

    Guide for creating effective skills following best practices.

    123 GitHub stars~752 tokensUpdated 3 mo ago
    Auto-check passed
  • Nuxt Modules

    xlanex6/nuxt-meilisearch

    A skill your agent uses when creating Nuxt modules: (1) Published npm modules (@nuxtjs/, nuxt-), (2) Local project modules (modules/ directory), (3) Runtime extensions (components, composables…

    123 GitHub stars~664 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Meilisearch

What does Meilisearch do?

Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance. Meilisearch is an agent skill from xlanex6/nuxt-meilisearch. Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance.

When should I use Meilisearch?

Meilisearch fits situations like: integrating Meilisearch; building search UIs; configuring indexes.

How do I install Meilisearch in Claude Code?

Run `npx skills add xlanex6/nuxt-meilisearch --skill meilisearch -a claude-code`. Or copy the skill folder (.agents/skills/meilisearch in xlanex6/nuxt-meilisearch) into .claude/skills/meilisearch in your project. Claude Code loads it when a task matches its description.

How do I install Meilisearch in Codex?

Run `npx skills add xlanex6/nuxt-meilisearch --skill meilisearch -a codex`. Or copy the skill folder (.agents/skills/meilisearch in xlanex6/nuxt-meilisearch) into .agents/skills/meilisearch in your project. Codex loads it when a task matches its description.

Can I use Meilisearch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xlanex6/nuxt-meilisearch --skill meilisearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meilisearch, .gemini/skills/meilisearch, .github/skills/meilisearch and .opencode/skills/meilisearch in your project.

What does Meilisearch need to run?

Going by SKILL.md and its folder, Meilisearch needs the command-line tools its instructions call (npm) and credentials named MEILISEARCH_KEY. Our summary lists: Node.js; Docker; A credential in MEILISEARCH_KEY.

Does Meilisearch access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Meilisearch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Meilisearch use?

Meilisearch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meilisearch use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.3k tokens, read only when the agent opens those files.

What are the alternatives to Meilisearch?

Skills that share tags, products or a category with Meilisearch: Nuxt Content (secondsky/claude-skills, 227 stars), Firecrawl Search Integration (firecrawl/firecrawl, 190k stars), Product Full-Text Search (lobehub/lobehub, 83k stars) and Hackernews (sigcli/sigcli, 293 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meilisearch?

xlanex6 (a GitHub user) maintains it in xlanex6/nuxt-meilisearch, which has 123 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 6, 2026.

Source: xlanex6/nuxt-meilisearch on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.