Skill Creator

If you're building skills for AI agents and want them to follow the agentskills.io spec properly, this walks you through the full authoring process. It enforces progressive disclosure (keeping core logic under 500 lines), validates metadata with a Python script before you go too far, and structures everything into scripts, references, and assets directories. The third-person imperative style takes some getting used to, but it keeps instructions crisp. Honestly most useful if you're cranking out multiple skills and need a consistent framework, less so if you're just prototyping one-offs. The validation script alone saves you from metadata mistakes that would break discoverability.

skills.sh installs: 481
GitHub stars: 1
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add webmaxru/ai-native-dev --skill skill-creator --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Authoring Procedure

Follow these steps to generate a skill that adheres to the agentskills.io specification and progressive disclosure principles.

Step 1: Initialize and Validate Metadata

Define a unique name: 1-64 characters, lowercase, numbers, and single hyphens only.
Draft a description: Max 1,024 characters, written in the third person, including negative triggers.
Execute Validation Script: Run the validation script to ensure compliance before proceeding: python scripts/validate-metadata.py --name "[name]" --description "[description]"
If the script returns an error, self-correct the metadata based on the stderr output and re-run until successful.

Step 2: Structure the Directory

Create the root directory using the validated name.
Initialize the following subdirectories:
- scripts/: For tiny CLI tools and deterministic logic.
- references/: For flat (one-level deep) context like schemas or API docs.
- assets/: For output templates, JSON schemas, or static files.
Ensure no human-centric files (README.md, INSTALLATION.md) are created.