Skip to content

created: 2026-04-24 updated: 2026-04-24 tags: [source, video, youtube, agent-skills, anthropic] type: source url: https://www.youtube.com/watch?v=CEvIs9y1uog author: "AI Engineer" (Barry Zhang, Mahesh Murag) published: 2025-12-09


Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, Anthropic

Summary

Anthropic engineers Barry Zhang and Mahesh Murag present Agent Skills — a minimal form factor for packaging procedural knowledge that agents can dynamically load. The talk covers why Anthropic believes skills are the solution to agents lacking domain expertise.

Key Takeaways

The Problem: Intelligence ≠ Expertise

Analogy: Who do you want doing your taxes? - Mahesh — 300 IQ mathematical genius who's never done taxes - Barry — experienced tax professional who's done thousands of returns

Agents today are like Mahesh: brilliant generalists who lack domain-specific expertise. They can figure things out from first principles but don't come preloaded with specific knowledge, workflows, or institutional memory.

The Old Assumption vs. Reality

Old assumption: Agents in different domains will look very different — separate agent for each use case.

Reality: The agent underneath is more universal than expected. Code is the universal interface to the digital world. Claude Code is actually a general-purpose agent that can generate financial reports, analyze data in Python, synthesize insights — all through bash and filesystem.

What Are Skills?

Skills are organized collections of files that package composable procedural knowledge for agents. In other words: they're folders.

  • A SKILL.md markdown file with instructions
  • Scripts as tools (Python, bash, etc.)
  • Reference documents, templates, examples
  • Versionable in Git, shareable via Google Drive, zippable for teams

Progressive Disclosure

Skills are progressively disclosed to protect the context window: 1. At runtime, only metadata is shown (skill name + short description) 2. When agent decides it needs a skill, it reads the full SKILL.md 3. The rest of the folder is organized for ease of access 4. This allows hundreds or thousands of skills without context overload

Three Types of Skills

Type Description Examples
Foundational New general/domain capabilities Document skills (Office docs), Cadence scientific research skills
Third-party Partners' product-specific skills Browserbase (Stagehand web automation), Notion workspace skills
Enterprise Company/team-specific skills Fortune 100 org best practices, internal software workflows, developer productivity team code style guides

Skills + MCP = Complete Agent Architecture

Component Role Analogy
Model Processing power CPU
Agent runtime Orchestrates context, tokens in/out Operating System
MCP servers Connection to outside world Network/IO
Skills Expertise and procedural knowledge Applications

"MCP is the hands. Skills are the experience."

Emerging Agent Architecture

Agent Loop (context management) ↓ Runtime Environment (filesystem, code read/write) ↓ MCP Servers (external tools and data) ↓ Library of Skills (dynamically loaded on demand)

This pattern is already helping Anthropic deploy Claude to new verticals — financial services and life sciences launched immediately after skills launch, each with specific MCP servers + skill sets.

Future Directions

  1. Treat skills like software — testing, evaluation, quality measurement
  2. Versioning — track skill evolution and resulting agent behavior lineage
  3. Dependencies — skills that explicitly depend on other skills, MCP servers, packages
  4. Collective knowledge base — skills shared across organizations and community
  5. Agent-created skills — Claude already creates skills via "Skill Creator"; continuous learning as agents write their own skills from experience

The Computing Analogy

Computing Layer AI Equivalent
Processors Models (massive investment, immense potential)
Operating System Agent runtime (orchestrates processes, resources, data)
Applications Skills (encode domain expertise, unique points of view)

"A few companies build processors and operating systems, but millions of developers have built software that encoded domain expertise. We hope that skills can help us open up this layer for everyone."