nicar2026_skills_in_codex_claude: Skill for Claude Code

Skill Creator

This skill provides guidance for creating effective skills.

About Skills

Skills are modular, self-contained packages that extend an agent's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks: they transform a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

What Skills Provide

1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks

Anatomy of a Skill

Every skill consists of a required SKILL.md file and optional bundled resources. For portable Claude Code and Codex skills, include name and description in frontmatter even when one surface treats a field as optional.

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata
│   │   ├── name: portable display/invocation name
│   │   └── description: trigger description
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

SKILL.md (required)

Metadata Quality: The name and description in YAML frontmatter determine when the agent will use the skill. Be specific about what the skill does and when to use it. Put the most important trigger language first. Use the third-person (e.g. "This skill should be used when..." instead of "Use this skill when...").

Surface-specific metadata: Keep the core workflow portable in SKILL.md. Add surface-specific controls only when needed:

• Claude Code can use fields such as disable-model-invocation, user-invocable, allowed-tools, disallowed-tools, argument-hint, arguments, and context for invocation control, tool permissions, arguments, and subagent behavior.
• Codex can use optional agents/openai.yaml metadata for UI display, implicit-invocation policy, and tool dependencies.
• Plugins are the right distribution surface when a reusable workflow should be installed beyond one repo, bundled with multiple skills, or shipped with connectors/MCP tools.