Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for HTMX development with Flask integration.
.claude/skills/amariahak-cursor-rules-for-htmx-development-with-flask-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-04 | ✓→✓ | = Same ✓ | -17% | 0% |
Cursor rules for HTMX development with Flask integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/htmx-flask-cursorrules-prompt-file.mdc.
// HTMX with Flask .cursorrules
// HTMX and Flask best practices
const htmxFlaskBestPractices = "Use Flask's render_template for server-side rendering", "Implement Flask-WTF for form handling", "Utilize Flask's url_for for generating URLs", "Use Flask's jsonify for JSON responses", "Implement Flask-SQLAlchemy for database operations", "Utilize Flask's Blueprint for modular applications", ];
// Folder structure
const folderStructure = app/ templates/ static/ css/ js/ models/ routes/ __init__.py config.py run.py ;
// Additional instructions
const additionalInstructions =
;
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 20,467 | 20,779 | +2% | 1 | 1 | 0% | 3,992 | 3,814 | -4% | 0 | 0 | — |
case-01 | fail→pass | 16,961 | 17,230 | +2% | 1 | 1 | 0% | 3,446 | 3,163 | -8% | 0 | 0 | — |
case-02 | fail→pass | 17,381 | 14,806 | -15% | 1 | 1 | 0% | 3,011 | 3,323 | +10% | 0 | 0 | — |
case-04 | pass→pass | 13,234 | 7,972 | -40% | 1 | 1 | 0% | 2,233 | 1,860 | -17% | 0 | 0 | — |
case-05 | pass→pass | 8,733 | 5,896 | -32% | 1 | 1 | 0% | 1,764 | 1,432 | -19% | 0 | 0 | — |
case-06 | pass→pass | 8,196 | 6,619 | -19% | 1 | 1 | 0% | 1,509 | 1,573 | +4% | 0 | 0 | — |
case-07 | pass→pass | 9,909 | 4,314 | -56% | 1 | 1 | 0% | 1,816 | 1,107 | -39% | 0 | 0 | — |
case-08 | pass→pass | 4,260 | 2,826 | -34% | 1 | 1 | 0% | 765 | 848 | +11% | 0 | 0 | — |
case-09 | pass→pass | 13,888 | 9,590 | -31% | 1 | 1 | 0% | 2,574 | 2,219 | -14% | 0 | 0 | — |
case-10 | pass→pass | 7,745 | 4,453 | -43% | 1 | 1 | 0% | 1,474 | 929 | -37% | 0 | 0 | — |
case-11 | pass→pass | 11,107 | 5,431 | -51% | 1 | 1 | 0% | 2,179 | 1,381 | -37% | 0 | 0 | — |
case-12 | pass→pass | 10,754 | 8,777 | -18% | 1 | 1 | 0% | 1,994 | 2,078 | +4% | 0 | 0 | — |
case-13 | pass→pass | 11,252 | 4,043 | -64% | 1 | 1 | 0% | 2,037 | 994 | -51% | 0 | 0 | — |
case-14 | pass→pass | 10,622 | 3,438 | -68% | 1 | 1 | 0% | 1,945 | 919 | -53% | 0 | 0 | — |
case-15 | pass→pass | 18,144 | 12,680 | -30% | 1 | 1 | 0% | 2,731 | 2,711 | -1% | 0 | 0 | — |
case-16 | pass→pass | 5,757 | 3,058 | -47% | 1 | 1 | 0% | 1,009 | 819 | -19% | 0 | 0 | — |
case-17 | pass→pass | 18,901 | 18,099 | -4% | 1 | 1 | 0% | 3,681 | 3,741 | +2% | 0 | 0 | — |
case-18 | fail→pass | 13,080 | 8,119 | -38% | 1 | 1 | 0% | 2,430 | 1,807 | -26% | 0 | 0 | — |
case-19 | pass→pass | 4,878 | 2,478 | -49% | 1 | 1 | 0% | 820 | 719 | -12% | 0 | 0 | — |
case-20 | pass→pass | 14,141 | 10,146 | -28% | 1 | 1 | 0% | 2,629 | 2,182 | -17% | 0 | 0 | — |
case-21 | pass→pass | 17,162 | 12,222 | -29% | 1 | 1 | 0% | 3,478 | 2,825 | -19% | 0 | 0 | — |
case-22 | pass→pass | 18,192 | 14,769 | -19% | 1 | 1 | 0% | 3,774 | 3,402 | -10% | 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. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 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.