A curated daily reading list covering AI deployment, system topology, open models, and tech industry insights for IT professionals.
A curated tech reading list covering AI frameworks, agent skills, token counting, A2A updates, anomaly detection, and web development trends.
Advice on keeping GitHub Copilot Agent Skills small and focused for better AI performance and predictable output.
Agent Skills project enforces senior engineering workflows like specs and tests for AI coding agents, preventing shortcuts to 'done'.
Analyzes design choices for effective GitHub Copilot Agent skills, focusing on task shape, descriptions, boundaries, and testing.
Explains how Agent Skills can capture institutional knowledge for coding agents, ensuring consistent adherence to internal frameworks and practices.
Explores the evolution from saved prompts to Agent Skills, a new way to codify workflows for AI agents with metadata, scripts, and tools.
Guide to optimizing Xcode build performance using new Agent Skills, covering clean/incremental builds and caching.
A minimal demo of implementing and using AI Agent Skills in .NET, including prompt, Python, and C# based skills.
A framework to help developers evaluate and choose the right AI Agent Skills for their projects, avoiding conflicts and ensuring quality.
A guide to systematically evaluating and testing AI agent skills, covering success criteria, building an evaluation harness, and improving skill performance.
Learn how to create and use Agent Skills in GitHub Copilot to automate Azure Bicep workflows, moving from manual tasks to efficient, repeatable processes.
Explores how AI is transforming Infrastructure as Code (IaC) by enabling standardization, shifting from writing code to describing intent, and automating tasks.
Introduces Agent Skills, an open format for sharing reusable AI knowledge across projects, replacing project-specific AGENTS.md files.
Explores the open standard for AI agent skills, detailing how tools like Goose use SKILL.md files to provide contextual expertise automatically.
A developer shares how they independently built two features for their personal AI system that were later released by Anthropic for Claude Code.
