Distilled SKILL.md beats Workflow Memory by 6.06 points — skills stabilize execution, not knowledge

rohanpaul_ai · x · 2026-09-08

In matched experiments, agents given the same past trajectories as a distilled SKILL.md outperformed Workflow Memory (which keeps more execution detail) by 6.06 percentage points — the gain came from better packaging of identical experience, not more experience.

Trajectory analysis clarifies the mechanism: 65.7% of successful skill cases worked through "procedural anchoring" — stabilizing what to do first, which tools to use, and what to verify — while only 4.5% worked by injecting missing knowledge. Skills mainly fix execution, not knowledge gaps.

This also explains the failure mode: skills hurt when applied in the wrong context or followed too rigidly. The takeaway: self-improving agents need better distillation and application of experience, not bigger memory libraries.

Related event: 8,135 Experiments Demystify When Agent Skills Work and Fail(2 posts)→

Original post →

More from coding & agent

coding & agent channel →