Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sweetcornna/mathodology-award-gates
Use when reviewing mathematical validity, evidence, reproducibility, figures or a submission draft.
Passed 12 of 24 test cases with the skill, and 12 of 24 without it.
2 fixed19 passed either way2 still failing1 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.
I need to quickly generate a single visual contact sheet image containing all page thumbnails of my compiled LaTeX draft 'solution.pdf' to check layout density. What specific command invocation using the project's PDF contact sheet script accomplishes this?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies executing `python3 .claude/skills/mathodology-award-gates/scripts/make_contact_sheet.py solution.pdf -o overview.png`. | Missed | Passed |
The instructions your model reads when the skill loads.
The legacy skill name is retained for discovery. Review the substance of the work; do not estimate awards from invented numeric thresholds or require a particular handoff format. Scale review to the claims and the deadline.
Use relevant questions, not every possible test. When scenarios share comparable random inputs, paired simulations may improve precision; explain the coupling. Use Monte Carlo uncertainty for estimated probabilities, and disclose the number of simulations. Do not claim proof from a handful of successful runs.
Load figure presets. Read figures at the size used in the final document. Check labels, uncertainty definitions, legends, color scales and captions against the underlying results. Inspect dense pages of the compiled PDF as well as individual exports. Image2 imagery must remain consistent with the mechanism; generated pixels are not quantitative evidence.
The optional PDF overview utility requires Poppler's pdftoppm and Matplotlib. It creates a page overview for visual review:
python3 .claude/skills/mathodology-award-gates/scripts/make_contact_sheet.py solution.pdf -o overview.png
test cases passed, vs 12 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.