Skills are modular, on-demand data that transform general-purpose LLMs into specialized agents. It's not about MCP or fancy protocols - it's about context engineering: loading the right information at the right time.
A skill is a memory, instruction, fact, or code snippet loaded on-demand into your LLM's context window.
A skill is also RAG + System Instructions + Domain Expertise.
Everything you can achieve with skills, you can technically achieve without them. Just load 50k tokens of tools, instructions, and examples into context, use the biggest reasoning model with enough thinking time, and you'll get decent results.
But the new skills-based approach is: simpler, faster, cheaper, and so scalable.
It's Not About MCP
I've been writing code for 14 years. I'm a tech geek following most AI updates, and a vibe-coder. Almost a year ago I shared my thoughts about MCP from a developer's perspective.
My core argument: MCP as an approach and programming pattern may not be the best solution.
Here's my personal experience so far.
- I don't use MCP servers - because I don't need to, because they don't work well for my use cases
- Coding agents already have enough - terminal commands, file system, web search handle most scenarios
- When agents must call external tools (e.g., creating a Google Calendar event), I need more robust custom code, not an MCP wrapper
- My debugging workflow - manually add 3-4 files + 1-2 documentation links. Works better than any automated context retrieval
Those 3-4 files and 1-2 links could be found automatically. That's what skills promise to deliver: to make agents smarter.
Context Engineering
I feel like architectural shift is coming:
Before: Big generalized pretrained model OR fine-tuned model
After: Small reasoning model with new architecture to learn + Skills for task-specific problems.
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy
The key insight: it's not about having the biggest model - it's about having the right context at the right moment.
The Path Forward
It's still R&D - a branch from mainstream LLM development, not a replacement. Anthropic has been working on this for 6+ months, and we're now just early adopters - discovering a better direction before the mainstream. My prediction, is that in 6 months, everyone will rush into skills-based agent architectures.
What we need:
- Automatic skill discovery
- Composable skill libraries - combine skills for complex multi-step workflows like n8n
- Domain-specific skill packs - pre-built expertise for common developer tasks, e.g. Angular skills, or Github Runner skills
Conclusion
Skills represent this philosophy: modular, reusable, on-demand expertise that transforms any LLM into a specialized agent for your specific workflow. I believe this is the right path, and I'm planning closely follow its progress and start coding some cool new things for skills or using skills.
Top comments (0)