From 36% to 100%: How Self-Improving Agents Write Their Own Skills — Rafal Wilinski, Runlayer
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Agents can write their own skills by distilling traces, with failed runs teaching the most. Serving them over MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → from one governed server shares them across every client, which can lift task success substantially.
Key takeaways · AI-distilled
Wilinski argues skills matter more as agents run for hours, because a bad start can send an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → down an hours-long rabbit hole.
He names three problems holding skills back: they are built for developers, nobody has time to write them, and many clients do not support them.
The approach of distilling skills from agent traces is borrowed from the agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → library in the Voyager Minecraft paper.
His case for the flywheel: frontier intelligence is rented, but distillationTraining a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.Full definition → skills keep an organization's hard-won knowledge as models change.
Terms in this piece · Glossary
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
videoIs Speculative Decoding Worth It? Profiling vLLM on NVIDIA Blackwell — Akamai
videoGrep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex
videoThe 6 Pillars of an Agentic Harness for Production — Varun Krovvidi, Resolve AI
videoEvery AI Company Is Accidentally Building a Bank — Dor Sasson, Stigg
videoAI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlackAI Engineer
videoHow I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOSAI Engineer
videoSkill issue: Lessons from skilling up coding agents to use Langfuse - Marc Klingen, ClickhouseAI Engineer