# From 36% to 100%: How Self-Improving Agents Write Their Own Skills — Rafal Wilinski, Runlayer

## Executive summary

This talk outlines a framework for creating a self-improving enterprise by moving beyond single-agent intelligence. The core concept involves using 'skills'—reusable playbooks—to guide AI agents through complex, multi-step tasks. To scale this knowledge across an entire organization, the speaker proposes using MCP (Message/Command Protocol) as a unified distribution layer. By implementing a 'self-improving organizational flywheel,' successful and failed agent runs are distilled into skills, turning ephemeral, borrowed frontier intelligence into persistent, proprietary corporate knowledge.

## Key takeaways

- Skills are essential for deep work and reliability.: As agents become capable of working for hours, the initial trajectory is critical. Skills act as playbooks, guiding the agent and preventing it from wasting tokens or time by rediscovering known procedures, which is crucial for complex tasks (3:51, 4:31).
- MCP provides the necessary centralized governance for skills.: To overcome the limitations of skills being local and client-specific, using MCP as a distribution layer allows the company to create a single source of truth for all skills, accessible to non-technical departments (7:55, 10:00).
- The organizational flywheel converts failure into knowledge.: Knowledge should be distilled from both successful and failed agent runs. Failures are particularly valuable as they expose missing guardrails or edge cases, making the resulting skills more robust (11:59).

## Technical details

- Skills Definition and Function: A skill is defined as a playbook that agents can read. It utilizes 'progressive disclosure,' meaning the agent first sees a summary, but can inject the full knowledge into the context when needed to change the task's trajectory (2:12).
- Skill Distillation Process: The process involves taking a successful or failed agent run (a 'trace') and using a Large Language Model (LLM) to distill the sequence of tool calls into a reusable skill. This process is designed to be autonomous and asynchronous (11:34).
- The Self-Improving Flywheel: The system groups similar agent runs, distills them into skills, and serves them via the MCP gateway. This creates a constantly evolving, centralized knowledge base that persists even if the underlying LLM models change or deprecate (15:23).

## Practical implications

- Implement a centralized, governed system (like an MCP gateway) to distribute AI skills, ensuring consistency across all departments and clients.
- Treat agent failure traces as valuable data points, as they often reveal critical missing guardrails or edge cases that successful runs overlook.
- Focus on building proprietary, distilled knowledge (the 'flywheel') rather than relying solely on the raw intelligence of external LLMs, thereby creating a sustainable competitive moat.

## Topics

AI Agents, Skills Engineering, Message/Command Protocol (MCP), Knowledge Graph, Self-Improvement, Build Automation, Runlayer, Voyager paper, MCP (Message/Command Protocol)

Source: https://www.youtube.com/watch?v=u-o0sW9nwmk