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: Papers Reveal When Agent Skill Retrieval Helps—and Hurts(4 posts)→
More from coding & agent
- HeyGen + Canva MCP turns slide speaker notes into an avatar presentation video — HeyGen · 2026-10-27
- 10 practical ways to run Astra computer use on Premiere Pro for video editing — beechinour · 2026-10-27
- Dev ships a delightful free shadcn UI for agent run and tool-call traces — round · 2026-10-27
- Phil Schmid launches Gemini API CLI: a stateless multimodal tool belt for your existing coding agent — _philschmid · 2026-10-27
- Musk hails Grok Bot as 'incredibly competent chief of staff' as user automates inbox triage — elonmusk · 2026-10-27
- shadcn's /improve skill paired with Grok on SuperGrok Heavy for plowing through issues — shadcn · 2026-10-27