Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI-powered analysis of coagulation disorders, thrombosis risk prediction, anticoagulation management, and platelet function assessment using machine learning.
.claude/skills/coagulation-thrombosis-agent/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 46% | 0% |
<!--
#
#
-->
The Coagulation and Thrombosis Agent provides AI-driven analysis of hemostatic disorders, thrombosis risk assessment, and anticoagulation management. It integrates coagulation cascade modeling, platelet function analysis, and machine learning for personalized thrombosis prevention.
User: "Calculate VTE risk for this hospitalized patient and optimize LMWH prophylaxis."
Agent Action:
bashpython3 Skills/Hematology/Coagulation_Thrombosis_Agent/thrombosis_analyzer.py \ --patient_data patient_demographics.json \ --labs coagulation_panel.csv \ --risk_model improved_padua \ --anticoagulant lmwh \ --renal_function egfr_45 \ --output vte_assessment.json
| Model | Application | Key Features | |-------|-------------|--------------| | Padua (Enhanced) | Medical VTE risk | 11 clinical factors + ML enhancement | | Caprini (AI) | Surgical VTE risk | 40+ factors with ML weighting | | CHADS2-VASc | Atrial fibrillation stroke risk | Standard guideline scoring | | HAS-BLED | Anticoagulation bleeding risk | Major bleeding prediction | | IPSET-thrombosis | MPN thrombosis | JAK2, age, prior thrombosis |
| Test | Normal Range | Elevations Suggest | Decreases Suggest | |------|--------------|-------------------|-------------------| | PT/INR | 11-13.5s / 0.9-1.1 | Warfarin, VII def, liver disease | - | | aPTT | 25-35s | Heparin, VIII/IX/XI def, lupus AC | - | | Fibrinogen | 200-400 mg/dL | Acute phase, inflammation | DIC, liver disease | | D-dimer | <500 ng/mL | VTE, DIC, inflammation | - | | Platelet | 150-400K | Reactive, MPN | ITP, marrow failure |
Deep Learning for Platelet Morphology:
VTE Prediction Models:
Anticoagulation Dosing:
AI Group - Biomedical AI Platform
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 5,558 | 2,151 | -61% | 1 | 1 | 0% | 1,009 | 1,717 | +70% | 0 | 0 | — |
case-02 | fail→pass | 7,199 | 3,852 | -46% | 1 | 1 | 0% | 1,388 | 1,842 | +33% | 0 | 0 | — |
case-03 | pass→pass | 9,279 | 8,086 | -13% | 1 | 1 | 0% | 1,685 | 2,600 | +54% | 0 | 0 | — |
case-04 | pass→pass | 12,628 | 11,306 | -10% | 1 | 1 | 0% | 2,432 | 3,342 | +37% | 0 | 0 | — |
case-05 | pass→pass | 10,430 | 10,904 | +5% | 1 | 1 | 0% | 1,863 | 3,271 | +76% | 0 | 0 | — |
case-14 | pass→pass | 13,282 | 13,088 | -1% | 1 | 1 | 0% | 2,550 | 3,784 | +48% | 0 | 0 | — |
case-06 | pass→pass | 11,176 | 11,570 | +4% | 1 | 1 | 0% | 2,115 | 3,451 | +63% | 0 | 0 | — |
case-07 | pass→pass | 11,478 | 8,652 | -25% | 1 | 1 | 0% | 2,163 | 2,841 | +31% | 0 | 0 | — |
case-08 | fail→pass | 14,113 | 2,200 | -84% | 1 | 1 | 0% | 2,448 | 1,570 | -36% | 0 | 0 | — |
case-09 | pass→pass | 6,560 | 4,730 | -28% | 1 | 1 | 0% | 1,349 | 2,104 | +56% | 0 | 0 | — |
case-10 | pass→pass | 7,009 | 5,643 | -19% | 1 | 1 | 0% | 1,278 | 2,250 | +76% | 0 | 0 | — |
case-11 | pass→pass | 8,041 | 4,072 | -49% | 1 | 1 | 0% | 1,597 | 2,021 | +27% | 0 | 0 | — |
case-12 | pass→pass | 13,159 | 3,759 | -71% | 1 | 1 | 0% | 2,589 | 1,975 | -24% | 0 | 0 | — |
case-13 | fail→pass | 10,754 | 2,043 | -81% | 1 | 1 | 0% | 1,770 | 1,573 | -11% | 0 | 0 | — |
case-15 | pass→pass | 12,963 | 14,043 | +8% | 1 | 1 | 0% | 2,082 | 3,763 | +81% | 0 | 0 | — |
case-16 | pass→pass | 9,251 | 2,080 | -78% | 1 | 1 | 0% | 1,606 | 1,607 | +0% | 0 | 0 | — |
case-17 | fail→pass | 6,217 | 1,312 | -79% | 1 | 1 | 0% | 964 | 1,403 | +46% | 0 | 0 | — |
case-18 | fail→pass | 8,894 | 2,415 | -73% | 1 | 1 | 0% | 1,489 | 1,634 | +10% | 0 | 0 | — |
case-19 | fail→pass | 11,026 | 1,542 | -86% | 1 | 1 | 0% | 1,761 | 1,499 | -15% | 0 | 0 | — |
case-20 | pass→pass | 17,257 | 12,227 | -29% | 1 | 1 | 0% | 3,124 | 3,367 | +8% | 0 | 0 | — |
case-21 | pass→pass | 16,259 | 14,028 | -14% | 1 | 1 | 0% | 2,985 | 3,827 | +28% | 0 | 0 | — |
case-22 | pass→pass | 11,947 | 16,097 | +35% | 1 | 1 | 0% | 2,336 | 4,734 | +103% | 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 +32 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/26/2026 | +9% |
Other measured skills in the registry, with their headline benchmark lift.