Skills are just fancy prompts. Here's why that matters.
Agent 'skills' are dynamically loaded prompts enabling progressive capability disclosure
“Skills are just prompts, they're fancy prompts, but they're really easy to share and they can help agents really narrow in and do a certain task well.”
LangChain explains that agent 'skills' are modular prompts loaded on-demand rather than stuffed into a single large system prompt. This progressive disclosure pattern keeps agent context clean while enabling specialized capabilities at runtime. The pattern is gaining traction as a practical solution to context window bloat in multi-capability agents.