Eg. Ask the agent to write a skill then get it to prompt a subagent to use the skill, then iterate until it verifies the task was completed correctly

"You must use tool ABC before calling tool XYZ"

This can either be in some static prompt scheme somewhere, or it can be the live result of a tool call.

If you make everything tool calling and environmental, you effectively have a lazily evaluated & dynamic prompt scheme.

I like to think of this as context for the context. The better you map the environment and descriptions of it to the agent, the less top-down prompting is required.

If you set up the harness correctly, you can run circles around a lot of what passes as AI innovation with powershell in a while loop. Adding static markdown document soup on top of this would only reduce performance in the general case.

Letting an instruction following llm deep research and iterate has given fantastic results before.

Being able to construct non-trivial Zig 0.16 programs without slowing down for version-hallucinating compilation errors is nice as a random example.

Nope. Still the same.

Not sure if this take is correct though. I suspect self-generated skills help the agent avoid having to "decompress" its latent knowledge, which might save tokens? idk, I am not an expert