skill-creator

Create and validate AI agent skills for Azure SDKs and Microsoft Foundry services.

1|Updated May 25, 2020
One-click install
npx skills add https://github.com/titaneric/dotfiles --skill skill-creator-titaneric
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/titaneric/dotfiles/tree/main/dot_agents/skills/skill-creator
Command: npx skills add https://github.com/titaneric/dotfiles --skill skill-creator-titaneric

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Writing consistent, high-quality skills for AI coding agents is hard: authors must follow frontmatter rules, keep SKILL.md concise, apply correct Azure SDK authentication patterns, and organize bundled resources. This Skill provides the authoring guidelines, templates, and validation tooling to do it correctly. ## Core Features & Use Cases - Skill Authoring Guidelines: Enforces core principles like progressive disclosure, degrees of freedom, and a standard section order for Azure SDK skills across Python, .NET, Java, TypeScript, Go, and Rust. - Scaffolding and Packaging Scripts: Includes init_skill.py to generate a new skill from a template, quick_validate.py to check frontmatter and naming rules, and package_skill.py to bundle a skill into a distributable .skill file. - Reference Documentation: Ships azure-sdk-patterns.md, output-patterns.md, and workflows.md covering authentication, pagination, LROs, and error handling per language. - Use Case: When asked to create a new skill for azure-storage-blob in Python, the agent follows the required section order, inserts the mandatory DefaultAzureCredential callout, scaffolds the directory with init_skill.py, and validates it before packaging. ## Quick Start Ask the agent to create a new skill for a specific Azure SDK package by providing the package name, documentation URL, and target language.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a new skill for an AI coding agent?

Run init_skill.py with the skill name and target path to scaffold a directory containing SKILL.md plus example scripts, references, and assets. Then edit the SKILL.md frontmatter description and body, following the section order and conciseness guidelines.

What is required before creating an Azure SDK skill?

You must provide the SDK package name, a Microsoft Learn documentation URL or GitHub repository reference, and the target language. The skill cannot be created without this context because Azure SDK APIs change frequently.

How do I validate a SKILL.md frontmatter?

Run quick_validate.py against the skill directory. It checks that SKILL.md exists, the YAML frontmatter contains name and description, the name is hyphen-case under 64 characters, and the description has no angle brackets and stays under 1024 characters.

Which credential should Azure SDK skills recommend for production?

Skills should recommend DefaultAzureCredential for local development and a specific credential such as ManagedIdentityCredential or WorkloadIdentityCredential for production. Rust skills use DeveloperToolsCredential locally since Rust has no DefaultAzureCredential.

How do I package a skill into a distributable file?

Run package_skill.py with the skill folder path and an optional output directory. It validates the skill first, then bundles all files into a zip-format .skill file named after the skill directory.

When should a skill be split into reference files?

Split content into references/ files when SKILL.md approaches 500 lines or 5k words. Detailed API patterns, migration guides, and streaming documentation belong in references so the main body stays concise.