NomaDamas/k-skill

한국인을 위한 스킬 모음집 - 에이전트를 한국인으로

What it solves

k-skill is a comprehensive collection of over 125 specialized tools (skills) designed to allow AI agents to interact with South Korean digital services and real-life data. It bridges the gap between general-purpose LLMs and the specific, often fragmented, local services of Korea, enabling agents to perform tasks like booking transport, searching real estate, checking government notices, and analyzing financial data.

How it works

The project provides a set of installable skills that can be integrated into various coding agents (such as Claude Code, Codex, OpenCode, and OpenClaw/ClawHub). These skills act as functional extensions that the agent can call to fetch real-time data or perform actions. Some skills use public APIs, some use a proxy server (k-skill-proxy) for data retrieval, and others utilize local helpers (e.g., Python for railway timetables) or browser-based automation.

Who it’s for

Developers and users of AI agents who need their agents to have deep, functional integration with South Korean public and private sector services, including transportation, law, finance, and shopping.

Highlights

  • Massive Scope: Covers 125+ skills across categories like transportation (KTX, buses), real estate, law, public administration, business/tax, and shopping.
  • Agent Compatible: Directly supports popular coding agents like Claude Code and other MCP-compatible environments.
  • Local Specialization: Includes niche Korean tools such as HWP document conversion, Korean spell-check, and specialized financial analysis for the KRX.
  • Low Friction: Simple installation via npx and minimal requirement for additional API layers in most cases.

Related

  • Project
    mxyhi/ok-skills

    A library of 31 ready‑to‑use “skills” (prompt‑plus‑script bundles) for AI coding agents like Codex, Claude Code, Cursor, OpenClaw and Autohand Code. Drop the repo into your `~/.agents/skills` (or Autohand) folder, merge the provided `CLAUDE_AGENTS.md` into your agent’s config, and then invoke skills such as `planning-with-files`, `find-docs` or `agent-browser` with natural language commands.

  • Project
    HughYau/qiushi-skill

    Qiushi‑Skill is a plug‑in library that adds nine philosophically‑derived reasoning methods (e.g., contradiction analysis, investigation‑first, mass‑line) to AI agents such as Claude Code, Cursor, and Codex. Installed via `npx qiushi-skill` or the Claude Code marketplace, it injects a lightweight kernel that enforces the principle “seek truth from facts” and routes tasks to the appropriate skill. Each skill provides trigger rules, step‑by‑step actions, output templates, hard constraints, and hand‑off specs, plus reference texts and optional sub‑agents for investigation or self‑criticism. The project aims to make agents more evidence‑driven, self‑critical, and strategically focused.

  • Project
    anbeime/skill

    Skill Store is a curated, automatically synced catalog of AI‑agent “skills” (JSON‑described plugins) covering document handling, content creation, video production, e‑commerce automation, and more. It pulls 182 official skills from the community‑maintained awesome‑agent‑skills repo every 24 h and adds 63 hand‑picked Chinese‑language skills. The repo provides Python scripts to update, export, and validate the skill definitions, plus a web UI for browsing. Ideal for developers building LLM‑orchestrated agents who want ready‑made, reusable capabilities.

  • Project
    dzhng/skills

    A library of reusable, composable AI‑agent “skills” (prompt‑driven actions) for building autonomous software‑factory loops, installable via npm and usable with many coding assistants.

  • Project
    elastic/agent-skills

    A library of curated instructions and tools that teach AI coding agents how to correctly interact with Elasticsearch, Kibana, and Elastic Observability/Security platforms.