Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs

Discussion (5 Comments)Read Original on HackerNews

ssgodderidge•about 1 hour ago

The example model in the documentation is 4o-mini, you might want to update that to a more recent model.

As an aside, 4o-mini came out months before agent skills were released… I’m curious how it performs with choosing to load skills in the first place?

stingraycharles•23 minutes ago

It’s an artifact of the documentation being AI generated, they usually pick gpt4-era models, without giving it further thought.

For Gemini it seems to always pick 2.5 despite 3.1 being the latest, Claude the 3.5-era models.

Not sure what’s preventing AI labs on ensuring this stuff is refreshed during training.

block_dagger•29 minutes ago

The skill is deterministically added to the prompt by the harness before the target model is invoked. There is no “choosing” to load a skill. You might be confusing skills with tools (MCP etc).

egeozcan•about 2 hours ago

Are there any published results gathered using this?

ianhxu•about 1 hour ago

How do you iterate on the judge prompt? Is there an auto rater?

Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs

⚡ Community Insights

Discussion (5 Comments)Read Original on HackerNews