Skill Builder

source_urls

v1.0.0

이 스킬 정보

Install Skill Builder, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

기능

I automatically load when you mention:
"build a skill" or "create a skill"
"generate a skill" or "make a skill"
"design a skill" or "develop a skill"
"skill builder" or "new skill"
youugiuhiuh youugiuhiuh
[0]
[0]
업데이트: 2/26/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Install Skill Builder, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

이 스킬을 사용하는 이유

추천 설명: skill-builder helps agents i automatically load when you mention:. Skill Builder Purpose Helps users create production-ready Claude Code skills that follow best practices from official Anthropic documentation

최적의 용도

적합한 상황: i automatically load when you mention:.

실행 가능한 사용 사례 for Skill Builder

사용 사례: I automatically load when you mention:
사용 사례: "build a skill" or "create a skill"
사용 사례: "generate a skill" or "make a skill"

! 보안 및 제한 사항

  • 제한 사항: Example: "Read reference.md when you need complete API details"
  • 제한 사항: Requires repository-specific context from the skill documentation
  • 제한 사항: Works best when the underlying tools and dependencies are already configured

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

SKILL.md
Readonly

Skill Builder

Purpose

Helps users create production-ready Claude Code skills that follow best practices from official Anthropic documentation and amplihack's ruthless simplicity philosophy.

When I Activate

I automatically load when you mention:

  • "build a skill" or "create a skill"
  • "generate a skill" or "make a skill"
  • "design a skill" or "develop a skill"
  • "skill builder" or "new skill"
  • "skill for [purpose]"

What I Do

I create skills in 5 steps using amplihack's specialized agents:

  1. Clarify → Define purpose, scope, users (prompt-writer)
  2. Design → Plan structure, token budget, templates (architect)
  3. Generate → Create SKILL.md with proper format (builder)
  4. Validate → Enforce progressive disclosure, check compliance (reviewer)
  5. Test → Define activation tests and edge cases (tester)

For detailed requirements, see Validation Checklist below.

Skill Types Supported

  • skill: Claude Code skills in ~/.amplihack/.claude/skills/ (auto-discovery)
  • agent: Specialized agents in ~/.amplihack/.claude/agents/amplihack/specialized/
  • command: Slash commands in ~/.amplihack/.claude/commands/amplihack/
  • scenario: Production tools in ~/.amplihack/.claude/scenarios/

See examples.md for detailed examples of each type.

Command Interface

For explicit invocation:

bash
1/amplihack:skill-builder <skill-name> <skill-type> <description>

Examples in examples.md.

Official Best Practices Enforcement

This skill enforces Claude API Skill Authoring Best Practices:

  1. Progressive Disclosure Pattern (MANDATORY)

    • SKILL.md < 500 lines (target 1,000-2,000 tokens)
    • Split content into reference.md, examples.md, patterns.md
    • Content-based splitting: beginner (SKILL.md) vs expert (supporting files)
  2. Navigation Guides (MANDATORY for multi-file skills)

    • Explicit "When to Read Supporting Files" section
    • Clear guidance on when to read each file
    • Example: "Read reference.md when you need complete API details"
  3. Source Attribution (MANDATORY for documentation-based skills)

    • source_urls field in YAML frontmatter
    • Enables drift detection and proper attribution
    • Format: source_urls: [list of documentation URLs]
  4. Token Budget

    • SKILL.md: 1,000-2,000 tokens (warning at 2,000+)
    • Supporting files: Unbounded (referenced on-demand)
    • Aggressive splitting encouraged for better UX
  5. Quality Thresholds

    • YAML syntax validation
    • Required fields (name, description, auto_activates, source_urls if applicable)
    • Philosophy compliance > 85%
    • Description clarity for autonomous discovery

Validation Checklist

Before creating any skill, verify:

Name Validation:

  • Kebab-case format (lowercase with hyphens)
  • 3-64 characters
  • No spaces or underscores

Description Quality:

  • 10-1024 characters
  • Includes trigger keywords for auto-discovery
  • Specific, not generic

File Size Limits:

  • SKILL.md < 500 lines (target 300-400 lines)
  • SKILL.md < 2,000 tokens (target 1,000-2,000)
  • Use wc -l SKILL.md to verify

Progressive Disclosure (multi-file skills):

  • "When to Read Supporting Files" section exists
  • Clear navigation guidance
  • Content split: beginner → SKILL.md, expert → reference.md

Source Attribution (docs-based skills):

  • source_urls in YAML frontmatter
  • Links to official documentation

Philosophy Compliance:

  • Score > 85%
  • No stubs or placeholders
  • Zero-BS implementation

Documentation

Supporting Files (progressive disclosure):

  • reference.md: Complete best practices, YAML spec, architecture, validation rules
  • examples.md: Real-world skill creation workflows, testing, troubleshooting

Original Documentation Sources (embedded in reference.md):

  1. Official Claude Code Skills: https://code.claude.com/docs/en/skills
  2. Anthropic Agent SDK Skills: https://docs.claude.com/en/docs/agent-sdk/skills
  3. Agent Skills Engineering Blog: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
  4. Claude Cookbooks - Skills: https://github.com/anthropics/claude-cookbooks/tree/main/skills
  5. Skills Custom Development Notebook: https://github.com/anthropics/claude-cookbooks/blob/main/skills/notebooks/03_skills_custom_development.ipynb
  6. metaskills/skill-builder (Reference): https://github.com/metaskills/skill-builder

All documentation is embedded in reference.md for offline access. Links provided for updates and verification.


Note: This skill automatically loads when Claude detects skill building intent. For explicit control, use /amplihack:skill-builder.

FAQ 및 설치 단계

Mirrors the structured data on this page for better search understanding.

이 스킬 설치 방법

  1. 1

    터미널 열기

    프로젝트 디렉터리에서 터미널 또는 명령줄을 여세요.

  2. 2

    설치 명령 실행

    npx killer-skills add youugiuhiuh/web3-demos/skill-builder 를 실행하세요. CLI가 IDE 또는 에이전트를 자동으로 감지하고 스킬을 설정합니다.

  3. 3

    스킬 사용 시작

    스킬이 이제 활성화되었습니다. 현재 프로젝트에서 Skill Builder을 바로 사용할 수 있습니다.

? 자주 묻는 질문

Skill Builder은 무엇인가요?
Install Skill Builder, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.
Skill Builder은 어떻게 설치하나요?
다음 명령을 실행하세요: npx killer-skills add youugiuhiuh/web3-demos/skill-builder. Cursor, Windsurf, VS Code, Claude Code와 19개 이상의 다른 IDE에서 동작합니다.
Skill Builder은 어디에 쓰이나요?
주요 활용 사례는 다음과 같습니다: 사용 사례: I automatically load when you mention:, 사용 사례: "build a skill" or "create a skill", 사용 사례: "generate a skill" or "make a skill".
Skill Builder 와 호환되는 IDE는 무엇인가요?
이 스킬은 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer 와 호환됩니다. 통합 설치에는 Killer-Skills CLI를 사용하세요.
Skill Builder에 제한 사항이 있나요?
제한 사항: Example: "Read reference.md when you need complete API details". 제한 사항: Requires repository-specific context from the skill documentation. 제한 사항: Works best when the underlying tools and dependencies are already configured.

관련 스킬

Looking for an alternative to Skill Builder or another community skill for your workflow? Explore these related open-source skills.

모두 보기

openclaw-release-maintainer

Logo of openclaw
openclaw

현지화된 요약: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. Claude Code, Cursor, and Windsurf workflows.

333.8k
0
인공지능

widget-generator

Logo of f
f

현지화된 요약: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat. It covers ai, artificial-intelligence, awesome-list workflows. Claude Code, Cursor, and Windsurf

149.6k
0
인공지능

flags

Logo of vercel
vercel

현지화된 요약: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. Claude Code, Cursor, and Windsurf workflows.

138.4k
0
브라우저

pr-review

Logo of pytorch
pytorch

현지화된 요약: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review. It covers autograd, deep-learning, gpu workflows. Claude Code, Cursor, and Windsurf workflows.

98.6k
0
개발자