Agent Skills, traced
Stop growing your system prompt. How SKILL.md folders and progressive disclosure work, how to write a description that fires, and when a skill beats a tool or an MCP server.
See: Agent Skills, traced
The architecture as diagrams, so you can hold the whole system in your head.
Reading Agent Skills is free. Pro unlocks the other four modes on all Agentic Systems topics, so you can go from understanding it to building it.
- SeeThe architecture as diagrams, so you can hold the whole system in your head.
- AnimateStep through the flow one stage at a time and watch the data move.
- TestScenario questions with explanations that show exactly where your model of it breaks.
- BuildA guided implementation with code you can run and adapt for production.
Continue reading
All Agentic Systems articles →Durable Agents and Sandboxing: Surviving the Crash
Checkpoints do not make a side effect safe. Idempotency keys, the interrupt replay trap, choosing a runtime, and the isolation and egress rules that contain generated code.
Harness Engineering: Everything Around the Model
Long-running agents fail in the code around the model. Clean sessions, progress on disk, a task list that starts failing, and checks the agent cannot talk its way past.
A2A: When Your Agent Needs Another Team’s Agent
Agent Cards, long-running tasks and artifacts, how A2A differs from MCP, and the honest test for when a plain function call is the better answer.
Discussion
Sign in to share your feedback and join the discussion.