More The AI Native Dev episodes
Published 3 Feb 2026
Duration: 2697
AI skills are standardized software components that enable agents to perform tasks and are becoming a crucial aspect of efficient AI workflow development.
One skill took coding success from 28% to 71%. Another made things worse. Guy Podjarny and Simon Maple tested 1000+ agent skills and reveal which ones...
The podcast examines the evolving role of "skills" in AI agents, describing them as standardized units of context that guide agents in performing specific tasks. These skills are not a new concept, as similar functionalities exist in tools like Cursor and Claude, but recent standardization effortsespecially by Anthropichave increased their visibility and adoption. Skills are typically stored in skill.d files, which include metadata, definitions, and supporting materials, allowing for the gradual introduction of knowledge to prevent overwhelming the AI's context window.
The discussion addresses several challenges in managing these skills, including the tendency to copy and duplicate them instead of treating them as reusable software components. There is a strong emphasis on the importance of lifecycle management, testing, and distribution through package managers to ensure proper maintenance and scalability. Tesla has recently integrated support for skills, offering features like evaluation and package management, which highlights the growing importance of skills in enhancing the reusability of context and improving the efficiency of AI agents. The industry's move toward skill-based context engineering signals a broader trend toward standardization, reusability, and more efficient workflow development across AI platforms.
16 Jun 2026 AI Security & the Agent-Ready Web: Experts Weigh In
Agentic AI systems face critical security risks from overconfidence, prompt-injection vulnerabilities, bypassable guardrails, and performance-driven development, requiring foundational security measures, developer education, and intent-based design to bridge readiness gaps and ensure safe innovation.
9 Jun 2026 Ryan Lopopolo: OpenAI's Framework for Shipping Code at 70 PRs/Week
The text explores Codex's integration via Chrome DevTools and TypeScript daemons, agentic development's emphasis on autonomous workflows and trustworthiness, harness engineering's structured tool integration, code QA with automation and feedback loops, shifts in code reviews toward strategy, AI agents as onboarding tools, persistent specs over code, balancing specification precision with adaptability, computational costs of token-heavy processes, and adapting team dynamics to agent-centric workflows.
2 Jun 2026 Why Developers Hit a Wall at 4 AI Agents
AI integration in software development faces challenges like limited agent management (1-2 per developer), lower acceptance of AI-generated code (60% merge rate vs. 80% for human), scalability barriers, and the need for improved observability, workflow alignment, and strategic business integration to balance productivity gains with quality and security.
26 May 2026 Don't Secure the Code. Secure the Coder.
The text addresses security challenges in AI and agentic systems, emphasizing unintended risks like reward-seeking behaviors, the need for developer-centric security strategies, novel attack vectors, frameworks adopting agentic principles, and proposed solutions such as the "AI Bill of Materials" alongside risks like data leakage and governance challenges.
19 May 2026 The Hidden Security Risks of AI Coding Agents
Agentic systems introduce heightened security risks through text-based interactions enabling malicious intent encoding, sensitive data access, untrusted inputs, and external system communication, requiring mitigation via SCA, restricted agent access, dynamic analysis, and balancing security with productivity through transparency and adapted security frameworks.