Skill Atlas which agent skills are worth usinghosted preview

Can an agent pick better skills using the atlas?

Short answer

Yes, for avoiding bad picks. With the atlas, an agent's top 5 picks almost never repeat the same skill, it sees more real choices, and it no longer picks skills from known harmful collections. The picks are about as relevant as without the atlas. The atlas filters out bad options; it doesn't yet find better ones.

What we found

1. Far fewer duplicates

→
out of 100 picks were copies of a skill already picked, with plain file search vs with the atlas.

2. More real choices

→
different skills in the top 5 (plain search that also skips exact copies: ).

3. No picks from harmful collections

→
out of picks came from known harmful collections or were high risk, plain search vs atlas. Before this week's fixes the atlas still picked .

4. Same relevance

→
of picks fit the task in a blind check. Picks that fit well and are reusable: → , too small a gap to be sure.

The atlas's own search (the API agents call) used to return nothing for of searches, because it needed the exact phrase. Now every word just has to appear, and it returned results for all . Its picks fit the task of the time, and were good picks, vs for plain search.

Duplicate picks, out of 100

Picks from harmful collections or high risk, out of 300

Both counts use today's labels, so the change shows what the atlas now avoids, not a change of yardstick. Plain search has no atlas, so it doesn't change.

What the atlas doesn't do yet

Honest caveats

How we measured this