Show HN: Agent-skills-eval – Test whether Agent Skills improve outputs
28 points
5 hours ago
| 3 comments
| github.com
| HN
▲
ssgodderidge
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?

reply
▲
stingraycharles
52 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.

reply
▲
block_dagger
58 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).
reply
▲
egeozcan
2 hours ago
[-]
Are there any published results gathered using this?
reply
▲
ianhxu
1 hour ago
[-]
How do you iterate on the judge prompt? Is there an auto rater?
reply