Skill Creator

This is a meta-skill that writes other skills according to the agentskills.io spec. It walks through a five-step process: validating metadata with a Python script, setting up the directory structure with scripts, references, and assets folders, drafting the main SKILL.md in third-person imperative, bundling fragile logic into CLI tools, and checking for hallucination gaps. The progressive disclosure approach keeps core logic under 500 lines by moving schemas and complex rules into separate reference files that agents read on demand. Useful if you're publishing skills to a marketplace and need to follow a specific format, but overkill if you just want to document internal tooling.

skills.sh installs: 478
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add webmaxru/enonic-agent-skills --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.