Skills aren't a cheat code for coding agents. They're configuration drift waiting to happen.

Tue, 17 Mar 2026 00:00:00 +0000

If you’re betting on “agent skills” to level up your coding agent, you’re mostly buying ceremony, and sometimes negative ROI. SWE-Skills-Bench tested 49 popular skills against 565 real GitHub tasks and found that skill injection is a narrow intervention: usually inert, occasionally useful, and sometimes actively harmful. Independent research on a much larger dataset tells us why, and the answer isn’t what you’d expect.

The headline result is blunt. Across those 565 requirement-driven tasks (real repos pinned to commits, acceptance criteria enforced by tests), 39 of 49 skills produced zero pass-rate improvement. The average gain across all skills was +1.2%. That’s not “skills are the future.” That’s skills as a rounding error.

Agent-Skills on aeshift

Skills aren't a cheat code for coding agents. They're configuration drift waiting to happen.