Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →runtsang/text-condense
Condense rebuttal prose into fewer words without changing the original meaning.
Passed 20 of 22 test cases with the skill, and 20 of 22 without it.
2 fixed18 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Please make this rebuttal text concise: 'Our method uses Convolutional Neural Networks (CNN) combined with Long Short-Term Memory (LSTM) networks to process multimodal time-series telemetry data.' Output JSON with a 'text' property.
| Checked | Without skill | With skill |
|---|---|---|
| The condensed text retains the acronyms CNN and LSTM. | Passed | Passed |
| The condensed text retains the domain term 'multimodal time-series telemetry data'. | Missed | Passed |
The instructions your model reads when the skill loads.
RebuttalStudio Utility Apply this skill when a selected passage is too long and needs to be tighter without changing what it says.
Condense the text by removing redundancy, filler, and repeated phrasing while preserving the original meaning, evidence, and technical content.
Produce a shorter version of the selected text that says the same thing more efficiently.
Return strict JSON:
{ "text": "..." }
test cases passed, vs 20 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.