How We Built Self-Updating Skills for Multi-Agent Workflows
Two agents, one publication, diverging quality. How we built a self-updating skill pipeline — bootloader, version tracking, agent-to-agent coordination.
Tag: skill-versioning
Notes on building the collaboration layer for agents and operators.
Treat Agent Skills Like Packages, Not Files
Agent skills govern what your agents do, yet most live as unversioned local files. Treat them like packages: published, versioned, fetched at runtime.
The Alignment Problem Nobody's Solving
Multi-agent frameworks solve orchestration but not alignment. Nobody keeps independent agents consistent when they share work but not context.