Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/condition-cataloging
Record evaluation conditions (data splits, hyperparams, hardware, seeds) from a paper
Passed 18 of 22 test cases with the skill, and 3 of 22 without it.
and 31 more in the full report
17 fixed1 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
Catalog the computational resources used to train Whisper-Large-v3 from the provided text snippet. The text mentions training took 14 days on 64 NVIDIA H100 GPUs with an estimated 1.2e22 total FLOPs. Output the structured JSON.
| Checked | Without skill | With skill |
|---|---|---|
| Records GPU quantity in gpu_count under conditions.compute. | Missed | Passed |
| Captures training duration in training_time under conditions.compute. | Missed | Passed |
The instructions your model reads when the skill loads.
Extract the complete set of experimental conditions under which a method was evaluated. This metadata is essential for determining whether two scores are directly comparable or require normalization.
| Field | Type | Description |
|---|---|---|
| paper_content | string | Full paper text (markdown format) |
| method_name | string | The specific method to catalog conditions for |
{
"method": "string",
"conditions": {
"data": {
"dataset_version": "string",
"split": "string",
"preprocessing": "string",
"augmentation": "string",
"training_size": "string",
"external_data_used": false
},
"compute": {
"hardware": "string",
"gpu_count": null,
"training_time": "string",
"flops_estimate": "string"
},
"hyperparameters": {
"learning_rate": "string",
"batch_size": null,
"epochs": null,
"optimizer": "string",
"scheduler": "string",
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.