News for hackers. Stuff that matters.
Re:Compressed Agents.md > Agent Skills by newzino on Thursday January 29, 2026 @05:41PM (#46817848)
The compressed agents.md approach is interesting, but the comparison misses a key variable: what happens when the agent needs to do something outside the scope of its instructions?

With explicit skills, you can add new capabilities modularly - drop in a new skill file and the agent can use it. With a compressed blob, every extension requires regenerating the entire instruction set, which creates a versioning problem.

The real question is about failure modes. A skill-based system fails gracefully when a skill is missing - the agent knows it can't do X. A compressed system might hallucinate capabilities it doesn't actually have because the boundary between "things I can do" and "things I can't" is implicit in the training rather than explicit in the architecture.

Both approaches optimize for different things. Compressed optimizes for coherent behavior within a narrow scope. Skills optimize for extensibility and explicit capability boundaries. The right choice depends on whether you're building a specialist or a platform.

Re:Compressed Agents.md > Agent Skills by jstummbillig on Thursday January 29, 2026 @06:00PM (#46818090)
Why could you not have a combination of both?
Re:Compressed Agents.md > Agent Skills by verdverm on Thursday January 29, 2026 @06:35PM (#46818457)
You can and should, it works better than either alone