Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ai-creed/ph01-one-token
Use when testing placeholder detection.
Passed 22 of 22 test cases with the skill, and 21 of 22 without it.
1 fixed21 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Write a Python function using the openai package to classify a movie review as 'P' or 'N'. The model should not generate any explanations. Some developers use `max_tokens=5` just in case, but what parameter should be set to guarantee the output is strictly restricted to the absolute minimum length?
| Checked | Without skill | With skill |
|---|---|---|
| Sets max_tokens to 1 | Missed | Passed |
The instructions your model reads when the skill loads.
TODO(shakespii): write the steps.
test cases passed, vs 21 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.