PluginBench
Skill
Pass
Audit score 90

k-schoollunch-menu

nomadamas/k-skill

Fetch Korean school meal menus by education office and school name via NEIS data.

What is k-schoollunch-menu?

Retrieves daily meal menus for Korean schools using natural-language school and education office names. Use this when users ask for 급식 식단 (school lunch menus) to look up what's being served at a specific school.

  • Query Korean school meal menus by education office and school name
  • Integrate with k-skill-proxy NEIS school-search and school-meal routes
  • Support natural-language input for school identification
  • Fetch daily meal information from official NEIS (National Education Information System) data

How to install k-schoollunch-menu

npx skills add https://github.com/nomadamas/k-skill --skill k-schoollunch-menu
Prerequisites
  • Node.js 18 or later
  • npx or npm installed
  • Access to k-skill-proxy NEIS routes
Claude Code
Cursor
Windsurf
Cline

How to use k-schoollunch-menu

  1. 1.Run `npx -y @nomadamas/k-skill@0 instruct k-schoollunch-menu` to get full runtime-specific instructions
  2. 2.Provide the education office name (시도교육청) and school name in natural language
  3. 3.The skill queries NEIS school-search to identify the school
  4. 4.The skill fetches meal menu data via the school-meal route
  5. 5.Review the returned menu information

Use cases

Good for
  • A parent wants to know what lunch is being served at their child's school today
  • A student checks the weekly menu before deciding what to bring for lunch
  • A school administrator needs to verify meal data for a specific school
  • A nutrition researcher collects meal menu data across multiple Korean schools
Who it's for
  • Parents and guardians of Korean school students
  • Students planning meals
  • School administrators and staff
  • Educators and nutrition professionals

k-schoollunch-menu FAQ

What data source does this skill use?

It uses NEIS (National Education Information System), the official Korean school data system, accessed via k-skill-proxy routes.

Can I search by school code instead of name?

The skill is designed for natural-language school and education office names; refer to the full CLI instructions for alternative query methods.

What if the school name is ambiguous?

The NEIS school-search route will return matching schools; you may need to clarify the exact school or education office.

Is this skill Korea-specific?

Yes, it retrieves data only for Korean schools registered in NEIS and requires Korean education office and school names.

Full instructions (SKILL.md)

Source of truth, from nomadamas/k-skill.


name: k-schoollunch-menu description: Use when the user asks for Korean school meal menus (급식 식단) by natural-language education office and school name, via k-skill-proxy NEIS school-search and school-meal routes. license: MIT metadata: category: utility locale: ko-KR phase: v1

k-schoollunch-menu

<!-- k-skill:cli-stub — generated by scripts/generate-skill-stubs.js; edit skill.json / instruction.md instead -->

Get the full instructions (required first step)

Run this and follow its output as the primary instructions for this skill:

npx -y @nomadamas/k-skill@0 instruct k-schoollunch-menu

The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:

npx -y @nomadamas/k-skill@0 files k-schoollunch-menu

Keep the CLI and every coding-agent skill install current (including Vercel Agent Skills) with:

npx -y @nomadamas/k-skill@0 update

If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the source instructions at https://github.com/NomaDamas/k-skill/blob/main/k-schoollunch-menu/instruction.md.

Hard rules even without the CLI

  • Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
  • Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
  • Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.