메뉴
Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill skill-structure명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | skill-structure |
| description | Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation. |
Custom slash commands and skills are the same thing. A file at .claude/commands/review.md and a skill at .claude/skills/review/SKILL.md both create /review. Existing .claude/commands/ files keep working. Skills add: a directory for supporting files, frontmatter to control invocation, and automatic context loading.
If a skill and command share the same name, the skill takes precedence.
When to use which:
| Type | When |
|---|---|
Command file (commands/name.md) | Simple single-file workflow, no supporting files |
Skill directory (skills/name/SKILL.md) | Needs references, background knowledge, or progressive disclosure |
| Rule | Example |
|---|---|
| Format | kebab-case, lowercase, 1-64 chars |
| Pattern | ^[a-z][a-z0-9]*(-[a-z0-9]+)*$ |
| Must match | Directory name exactly |
Good/Bad Examples:
| Good | Bad | Why |
|---|---|---|
stimulus-coder |
MySkill |
| Uppercase not allowed |
tdd-workflow | skill_helper | Underscores not allowed |
pdf-processing | -invalid | Can't start with hyphen |
seo-content | skill--bad | No consecutive hyphens |
plugins/majestic-rails/skills/stimulus-coder/SKILL.md
-> name: stimulus-coder
-> invoked as: Skill("stimulus-coder")
plugins/majestic-rails/skills/dhh-coder/SKILL.md
-> name: dhh-coder
-> invoked as: Skill("dhh-coder")
Key Points:
name field is ONLY the final skill name (not the full path)name exactlyFor complex skills, split into multiple files:
my-skill/
+-- SKILL.md (overview, <500 lines)
+-- references/
| +-- patterns.md (detailed patterns)
| +-- examples.md (extended examples)
+-- scripts/
+-- helper.py (utility scripts)
Rules:
scripts/, references/, assets/---
name: skill-name # Matches directory, defaults to dir name if omitted
description: What it does... # Recommended, max 1024 chars
allowed-tools: Read Bash # Optional, space-delimited
---
| Field | Required | Description |
|---|---|---|
name | No | Lowercase letters, numbers, hyphens (max 64 chars). Defaults to directory name. |
description | Recommended | What it does AND when to use it. Max 1024 chars. |
argument-hint | No | Hint during autocomplete. Example: [issue-number] |
disable-model-invocation | No | true = Claude cannot auto-load. For manual workflows. Default: false |
user-invocable | No | false = hidden from / menu. For background knowledge. Default: true |
allowed-tools | No | Tools without permission prompts. Example: Read, Bash(git *) |
model | No | haiku, sonnet, or opus |
context | No | fork to run in isolated subagent context |
agent | No | Subagent type when context: fork: Explore, Plan, general-purpose, or custom |
[What it does]. Use when [trigger contexts]. Triggers on [specific keywords].
Rules:
| Frontmatter | User can invoke | Claude can invoke | When loaded |
|---|---|---|---|
| (default) | Yes | Yes | Description always in context, full content on invocation |
user-invocable: false | No | Yes | Description always in context, loads when relevant |
Decision guide:
user-invocable: falseNote: Avoid disable-model-invocation: true. Commands/skills with side effects should use confirmation steps (AskUserQuestion) rather than blocking model invocation entirely.
Use $ARGUMENTS for user input. If not present in content, arguments are appended automatically.
---
name: fix-issue
---
Fix GitHub issue $ARGUMENTS following our coding standards.
Individual args: $ARGUMENTS[0] or shorthand $0, $1, $2.
The !`command` syntax runs shell commands before content reaches Claude:
## Context
- Current branch: !`git branch --show-current`
- PR diff: !`gh pr diff`
Commands execute immediately; output replaces the placeholder.
Add context: fork to run in isolation (no conversation history):
---
name: deep-research
description: Research a topic thoroughly
context: fork
agent: Explore
---
Research $ARGUMENTS thoroughly...
| Tools Needed | Example Use Case |
|---|---|
Read, Grep, Glob | Search codebase for patterns |
Bash(git *) | Git operations only |
Bash(gh *) | GitHub CLI operations |
WebFetch | Fetch external documentation |
| None | Pure knowledge/guidance |
^[a-z][a-z0-9]*(-[a-z0-9]+)*$AskUserQuestion for confirmation if skill has side effectsallowed-tools set if specific tools neededscripts/, references/, assets/Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Includes framework-specific guidance for Tailwind, React, Vue, and Rails/Hotwire ecosystems.
Forces adversarial reasoning before committing to decisions. Triggers on architectural choices, approach selection, and planning phases to prevent premature commitment bias.
Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.