Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet
A skill is a capability you provide to an AI agent — essentially a short file (skill.md) with a name and description that serves as routing signals for the agent to select the right tool.
At small scales, a simple registry suffices, but as the system grows — over ten skills require search and embeddings, over a hundred require actual governance with ownership, testing, and review. Critically, skills without tests begin to malfunction when new models are released, and at enterprise scale, governing and reviewing skills is at least as important as writing them.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago