Guides

A practical way to pick one agent skill from this directory without installing a pile of prompts you will never run again.

What the install prompt on a skill page actually does, how to tell that it took effect, and how to take it back out.

The cases where a skill card should stay a card: secrets, personal data, licenses you cannot accept, and prompts that fight your agent.

What a DeepSeek Harness plugin is, how it differs from an agent skill, and how to try one without losing the session you were in.

What each DeepSeek Harness plugin category is promising, and the mix-ups that waste an afternoon.

What the fields on a model page mean, which ones are safe to compare, and which ones are just the vendor's sentence.

How to choose between an open-weight model and a hosted proprietary model using the fields this directory actually has.

What to do with the comparison table: which highlighted cell matters, and which ones you should ignore.

A small set of skills, plugins, and model choices for the first week, instead of installing the top of every list.

Ten checks to run on a skill, plugin, or model page before you install or call it.

What the score, download count, and star count actually sort, and what they deliberately do not mean.

Which parts of AI Agent Hub are aggregated listings, which parts we write, and how to ask for a fix.