한국어 |

음악 작곡 에이전트 스킬

AI music-composition Assistant에 대한 모듈식 지식 및 워크플로 기술.

이 저장소는 에이전트 턴 vague 창조적 인 요청을 돕기 위해 설계되었습니다. “코러스 히트 하드를 만들” “어둡게 K-pop 브리지,” “Jzz와 같은이를 잔류하지만, 너무 감당하지 않습니다,” “내 플레이리스트에 대한 재정적 참조 트랙”- 콘크리트 뮤지컬 결정 : chords, 멜로디 모양, 강저, 모양, 배열 이동, 진단 피드백 및 연구 워크플로.

현재 릴리스: v1.0 관련 날짜: 2026-04-27

---

설치

가장 간단한 방법은 skills CLI ( Node.js 필요)를 통해 입니다:

현재 프로젝트의 에이전트 디렉토리에 설치 (예를 들어, .claude/skills/). -g] user-level (global) install, or --all -y 을 추가하여 프롬프트를 건너 뛸 수 있습니다.

수동 설치의 경우, 저장소를 복제하고 에이전트를 시점 (또는 복사 SKILL.md]]) 및 에이전트의 기술 폴더에 관련 하위 디렉토리, 같은 ~/.claude/skills/ 또는 .claude/skills/] 프로젝트):

호환성

이 기술은 오픈 Agent Skills standard — SKILL.md + YAML frontmatter 형식 모두 Claude (Claude Code, Claude Agent SDK, Claude.

English | 한국어

Music Composition Agent Skill

A modular knowledge and workflow skill for an AI music-composition assistant.

This repository is designed to help an agent turn vague creative requests — “make the chorus hit harder,” “give me a darker K-pop bridge,” “reharmonize this like jazz but not too dense,” “find reference tracks for my playlist” — into concrete musical decisions: chords, melody shapes, grooves, forms, arrangement moves, diagnostic feedback, and research workflows.

Current release: v1.0
Release date: 2026-04-27

---

Installation

The simplest way is via the skills CLI (requires Node.js):

npx skills add SJY051/music-composition

This installs to your current project’s agent directory (e.g., .claude/skills/). Add -g for user-level (global) install, or --all -y to skip prompts.

For a manual install, clone the repository and point your agent at it (or copy SKILL.md and the relevant subdirectories into your agent’s skill folder, such as ~/.claude/skills/ or .claude/skills/ in a project):

git clone https://github.com/SJY051/music-composition.git

Compatibility

The skill follows the open Agent Skills standard — the SKILL.md + YAML frontmatter format used by both Claude (Claude Code, Claude Agent SDK, Claude.ai skills) and OpenAI (Responses API tools[].environment.skills). It works on any harness that reads this format.

---

Does it work?

Two benchmarks ship with v1.0:

Approach 1 (system-prompt injection, GLM-5.1, blind eval). With SKILL.md prepended to the system prompt, the skill version wins 6 of 8 representative composition prompts in an author-bias-controlled blind comparison. The strongest signal is the boundary test (P8) — the skill version explicitly declines an out-of-scope mixing question while the baseline answers freely.

Approach 2 (native lazy loading, Claude Opus 4.7). With the skill installed via Claude Desktop’s Skills feature, the model reads references on demand. Most striking: pansori OST advice cites yoseong, toeseong, chuseong with cents-and-milliseconds implementation values that exist only inside references/genres/korean-traditional.md — direct evidence the model used the skill’s full content, not just SKILL.md.