Terraform Style Guide

eggboy

Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.

Agentic Evaluation

eggboy

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

java-best-practices

eggboy

Expert guidance on modern Java patterns (JDK 8-24) and industry best practices. Use when writing, reviewing, or refactoring Java code to apply modern language features, APIs, and architectural patterns. Covers type inference (var), Records, sealed classes, pattern matching, switch expressions, text blocks, Streams, virtual threads, structured concurrency, modern collections APIs, I/O improvements, security enhancements, DTO design, exception handling strategies (unchecked exceptions, validation-first approach, global handlers), naming conventions, code smells, and build verification. Essential for modernizing legacy Java code, Spring Boot applications, REST APIs, and enterprise Java development.

Azure naming convention

eggboy

Generate compliant Azure resource names following Microsoft Cloud Adoption Framework (CAF) best practices. Use when naming any Azure resource, generating IaC (Bicep, Terraform, ARM), scaffolding Azure projects, or reviewing existing resource names for compliance. Triggers on: Azure resource naming, name Azure resources, naming convention, resource abbreviation, CAF naming.

agent-framework-azure-ai-py

eggboy

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.

python-best-practices

eggboy

Python coding best practices, conventions, and architectural patterns for production-ready applications. Use when writing, reviewing, or refactoring Python code to apply modern patterns and idiomatic style. Covers: general Python conventions (PEP 8, type hints, testing with pytest/Hypothesis/Faker), FastAPI best practices (async endpoints, error handling, OpenAPI docs, dependency injection), dataframe mindset (vectorization, columnar operations, method chaining across Pandas/Polars/DuckDB/Spark), and Python data model (dunder methods, iterators, context managers, descriptors, properties). Applicable to Python 3.12+ projects using pyproject.toml and Ruff for linting.

skillshare

eggboy

Syncs skills across AI CLI tools from a single source of truth. Global (~/.config/skillshare/) or project (.skillshare/) mode. Install from any Git host. Use when: skillshare CLI, skill management, or troubleshooting.

Azure Verified Modules

eggboy

Azure Verified Modules (AVM) requirements and best practices for developing certified Azure Terraform modules. Use when creating or reviewing Azure modules that need AVM certification.

Skill Creator

eggboy

A guide for creating effective Agent Skills that follow the agentskills.io specification. Use this when you want to create a new skill or update an existing one that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations. Applicable to GitHub Copilot, Claude, and other AI assistants.