Skills Guide

Create Claude Code Agents

VerifiedCaution

Helps create and run custom Claude Code agents by defining agent configurations using --agents JSON and executing them via --agent flag. Useful when users need to build specialized agents for specific tasks or migrate agents from other formats like OpenCode.

Download and use
Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#agent-creation#claude-code#custom-agents#configuration

Recommended for

Backend developerClaude CodeCode reviewFrontend developerFullstack developerRefactoring

Automated summary

This skill guides the creation and execution of custom Claude Code agents using the --agents and --agent CLI flags.

Strengths

  • Clear structure with ready-to-use JSON examples
  • Supports migration from other formats like OpenCode
  • Detailed instructions for both one-shot and interactive execution
  • Systematic validation by test execution

Limitations

  • Requires knowledge of file paths and shell commands
  • Migration from other formats may be partial due to feature mismatches
  • No automatic dependency management between agents
When to use it

Use this skill when you need to create, configure, or run a custom Claude Code agent to automate repetitive tasks.

When not to use it

Avoid this skill if you need a generic assistant without Claude Code-specific CLI configuration.

Security analysis

Caution
Quality score92/100

The skill uses Bash to execute 'claude' commands, which is a powerful tool, but only for legitimate agent creation and execution purposes. There are no destructive commands, exfiltration, or obfuscation. The risk is minimal as it's user-invocable and does not instruct dangerous actions.

No concerns found

How this analysis is made

Examples

Create a code review agent
Create a new agent named 'code-review' that checks pull requests for style issues and provides feedback.
Migrate OpenCode config
Convert my OpenCode agents.json to Claude Code agent format and save it to .claude/agents/agents.json.
Run existing agent interactively
Run the 'issue-infer' agent with a prompt to extract symptoms from a bug report.

name: create-agent description: | Claude Code 커스텀 에이전트를 만들고 실행할 때 사용하는 스킬. 사용자가 "에이전트 만들어", "Claude agent 생성", "--agents 설정"을 요청하면 활성화됩니다. argument-hint: "[agent-name] [agent-description]" disable-model-invocation: false user-invocable: true allowed-tools: Read, Write, Edit, Bash

Claude Code 에이전트 생성/실행 가이드

요청: $ARGUMENTS

이 스킬은 Claude CLI에서 확인한 실제 방식만 사용한다.

  • 에이전트 정의 주입: --agents <json>
  • 실행 에이전트 선택: --agent <name>

1) 생성 규칙

  1. 에이전트 이름은 lowercase-hyphen 형식으로 만든다.
  2. 에이전트 정의는 JSON 객체로 작성한다.
  3. 각 엔트리는 아래 키를 사용한다.
    • description: 언제 쓰는지 한 줄 설명
    • prompt: 에이전트 시스템 지시문

예시:

{
  "issue-infer-extract-symptom": {
    "description": "증상 텍스트를 추출하는 에이전트",
    "prompt": "너는 증상 추출 전문가다. ..."
  }
}

2) 저장 위치

프로젝트 기준 아래 경로를 기본으로 사용한다.

  • .claude/agents/agents.json
  • 필요 시 에이전트별 원문 프롬프트 문서: .claude/agents/<agent-name>.md

3) 실행 방법

단발 실행

claude -p \
  --agents "$(cat .claude/agents/agents.json)" \
  --agent <agent-name> \
  "<실행 프롬프트>"

대화형 시작

claude --agents "$(cat .claude/agents/agents.json)"

필요하면 시작 시 바로 선택:

claude --agents "$(cat .claude/agents/agents.json)" --agent <agent-name>

4) 변환(마이그레이션) 작업 지침

OpenCode/기타 형식에서 변환 요청을 받으면 아래 순서로 처리한다.

  1. 원본 frontmatter의 name, description을 우선 보존한다.
  2. 본문 지시문은 prompt로 이동한다.
  3. OpenCode 전용 필드(mode, tools 등)는 Claude JSON에 직접 넣지 않는다.
  4. 결과를 .claude/agents/agents.json에 합친다.
  5. 최소 1개 에이전트는 claude -p --agents ... --agent ...로 실행 검증한다.

5) 완료 보고 형식

작업 완료 시 아래를 반드시 보고한다.

  • 생성/수정 파일 목록
  • 사용한 실행 명령
  • 검증 결과(성공/실패 + 핵심 로그)
  • 다음 액션(필요 시)

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/create-claude-code-agents-mm8o529g' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/create-claude-code-agents-mm8o529g/download' --output '.skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md.part' && mv '.skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md.part' '.skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md' && test -s '.skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/create-agent' && cp -R '.skill-downloads/create-claude-code-agents-mm8o529g' '.claude/skills/create-agent'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/create-claude-code-agents-mm8o529g'

openskills read 'create-claude-code-agents-mm8o529g'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/create-claude-code-agents-mm8o529g/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

React Hook Form Best Practices

Development

Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.

Claude CodeCursorWindsurf+2intermediateSafe 108,623
Skills Guide Bot

Emotion to Mantine Migration

Development

Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.

Claude CodeCursorWindsurf+1intermediateSafe 48,981
Skills Guide Bot

Scope Creep Detector

Development

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.

Claude CodeCursorCodexintermediateSafe 135,015
Skills Guide Bot