Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Collection of LaTeX templates for papers, presentations, and CVs
.claude/skills/brycewang-stanford-latex-templates-collection/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 55% | 0% |
A skill providing a curated collection of LaTeX templates for academic papers, conference presentations, CVs, cover letters, and other documents commonly needed by researchers. Based on the latex-templates repository (655 stars), this skill helps researchers quickly start professionally formatted documents without spending hours on layout configuration.
Researchers spend significant time formatting documents to meet the requirements of different journals, conferences, and institutions. A well-organized template library eliminates this overhead by providing ready-to-use starting points that comply with common formatting standards. This skill catalogs templates by document type and provides guidance on selection, customization, and best practices for each category.
The templates cover the full range of academic document needs: research papers, technical reports, conference slides, academic CVs, cover letters, grant proposals, and poster presentations. Each template is designed for professional quality output with clean typography and proper academic formatting.
Journal Article Templates
Conference Paper Templates
Template Structure
Beamer Templates
Presentation Best Practices
Animation and Overlays
Academic CV Templates
Resume Templates
Cover Letter Templates
Thesis and Dissertation
Grant Proposals
Posters
Font Selection
mathptmx or newtxtext/newtxmathhelvet or sourcesanspro for modern appearanceinconsolata for code listingsColor Schemes
xcolor package with named colors for maintainabilityPage Layout
geometry package for margin and page size configurationsetspace package (single, 1.5, double)fancyhdr packageparskip or manual settingsThis skill supports the Research-Claw document preparation workflow:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,572 | 9,886 | -37% | 1 | 1 | 0% | 2,267 | 2,757 | +22% | 0 | 0 | — |
case-02 | pass→pass | 14,446 | 10,046 | -30% | 1 | 1 | 0% | 2,245 | 3,057 | +36% | 0 | 0 | — |
case-03 | pass→pass | 12,873 | 11,539 | -10% | 1 | 1 | 0% | 2,267 | 3,340 | +47% | 0 | 0 | — |
case-04 | fail→pass | 14,479 | 11,074 | -24% | 1 | 1 | 0% | 2,523 | 2,933 | +16% | 0 | 0 | — |
case-05 | fail→pass | 18,513 | 9,598 | -48% | 1 | 1 | 0% | 2,806 | 2,964 | +6% | 0 | 0 | — |
case-06 | pass→pass | 7,053 | 6,595 | -6% | 1 | 1 | 0% | 1,276 | 2,500 | +96% | 0 | 0 | — |
case-07 | pass→pass | 6,255 | 8,268 | +32% | 1 | 1 | 0% | 1,043 | 2,721 | +161% | 0 | 0 | — |
case-08 | pass→pass | 14,619 | 11,427 | -22% | 1 | 1 | 0% | 2,578 | 3,145 | +22% | 0 | 0 | — |
case-09 | pass→pass | 20,060 | 21,271 | +6% | 1 | 1 | 0% | 3,132 | 4,619 | +47% | 0 | 0 | — |
case-10 | fail→fail | 14,460 | 17,234 | +19% | 1 | 1 | 0% | 2,307 | 3,655 | +58% | 0 | 0 | — |
case-11 | fail→pass | 23,858 | 28,693 | +20% | 1 | 1 | 0% | 4,035 | 6,293 | +56% | 0 | 0 | — |
case-12 | pass→pass | 10,262 | 10,743 | +5% | 1 | 1 | 0% | 1,588 | 3,196 | +101% | 0 | 0 | — |
case-13 | pass→pass | 14,035 | 10,660 | -24% | 1 | 1 | 0% | 2,676 | 3,346 | +25% | 0 | 0 | — |
case-14 | fail→pass | 15,029 | 11,654 | -22% | 1 | 1 | 0% | 2,000 | 3,091 | +55% | 0 | 0 | — |
case-15 | pass→pass | 10,888 | 10,188 | -6% | 1 | 1 | 0% | 1,475 | 2,908 | +97% | 0 | 0 | — |
case-16 | pass→pass | 14,804 | 12,976 | -12% | 1 | 1 | 0% | 2,555 | 3,424 | +34% | 0 | 0 | — |
case-17 | pass→pass | 15,339 | 16,515 | +8% | 1 | 1 | 0% | 2,706 | 3,664 | +35% | 0 | 0 | — |
case-18 | pass→pass | 15,795 | 17,043 | +8% | 1 | 1 | 0% | 2,539 | 3,610 | +42% | 0 | 0 | — |
case-19 | pass→pass | 11,698 | 14,459 | +24% | 1 | 1 | 0% | 1,962 | 3,433 | +75% | 0 | 0 | — |
case-20 | pass→pass | 15,090 | 15,882 | +5% | 1 | 1 | 0% | 2,666 | 3,570 | +34% | 0 | 0 | — |
case-21 | pass→pass | 16,587 | 16,543 | -0% | 1 | 1 | 0% | 2,215 | 3,709 | +67% | 0 | 0 | — |
case-22 | pass→pass | 9,962 | 8,371 | -16% | 1 | 1 | 0% | 1,492 | 2,800 | +88% | 0 | 0 | — |
case-23 | pass→pass | 15,316 | 10,846 | -29% | 1 | 1 | 0% | 2,373 | 3,346 | +41% | 0 | 0 | — |
case-24 | pass→pass | 7,956 | 5,450 | -31% | 1 | 1 | 0% | 1,145 | 2,010 | +76% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +21 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.