Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jaechang-hits/nejm-figure-guide
NEJM figure preparation: resolution (300-1200 DPI), editable vector formats (AI/EPS/SVG), in-house medical illustration policy, and strict image integrity requirements.
Passed 21 of 22 test cases with the skill, and 14 of 22 without it.
and 8 more in the full report
7 fixed14 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am drafting an Images in Clinical Medicine entry for NEJM. My title is 'A case of acute silent myocardial infarction presenting with sudden dyspnea' and my legend is 120 words. Does my title meet the journal's word limit?
| Checked | Without skill | With skill |
|---|---|---|
| Flags the 10-word title for exceeding NEJM's 8-word maximum limit | Missed | Passed |
The instructions your model reads when the skill loads.
This guide provides the complete specifications for preparing figures for submission to the New England Journal of Medicine (NEJM). A unique feature of NEJM is that medical illustrations are created by NEJM's in-house illustrators working directly with authors — authors should NOT submit finished medical illustrations due to copyright considerations.
Official reference: https://www.nejm.org/author-center/new-manuscripts
| Image Type | Minimum Resolution | Notes |
|---|---|---|
| Black-and-white line art | 1,200 DPI | Highest requirement |
| Photographic / halftone images | 300 DPI | Standard for photographs |
| Peer review stage | Lower resolution acceptable | High-res required for final publication |
from PIL import Image
def check_nejm_resolution(image_path, image_type='photo', stage='final'):
"""Check if image meets NEJM resolution requirements.
Args:
image_type: 'lineart' (1200 DPI) or 'photo' (300 DPI)
stage: 'review' (lower OK) or 'final' (strict requirements)
"""
min_dpi = {'lineart': 1200, 'photo': 300}
required = min_dpi.get(image_type, 300)
if stage == 'review':
print("NOTE: Lower resolution acceptable for peer review")
required = 150 # relaxed for review
img = Image.open(image_path)
dpi = img.info.get('dpi', (72, 72))
print(f"Stage: {stage} | Type: {image_type}")
print(f"Required: {required} DPI | Actual: {dpi[0]} DPI")
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.