{"_id":"medorqis","_rev":"3-c7438e837bbbc763095d4d363d99b6a7","name":"medorqis","dist-tags":{"latest":"2.1.1"},"versions":{"0.0.0-stage":{"name":"medorqis","version":"0.0.0-stage","_id":"medorqis@0.0.0-stage","stub":true,"maintainers":[{"name":"tarek.eg","email":"seotarek@gmail.com"}],"dist":{"shasum":"0449187f6752158c007ff9e35eacdf11ca7106c1","tarball":"https://registry.npmjs.org/medorqis/-/medorqis-0.0.0-stage.tgz","fileCount":2,"integrity":"sha512-SkXhvVTfSCH1O/F3lTsGkMbEpdH5rr/2gGmvSpNVmLIO+I45mWTPLOie6EyA0JpObFQyjfFKnz00ocl3T8pwfA==","signatures":[{"sig":"MEUCIQDsoLo6rMAFoRID8xCK7pGS7L8ZsXxfcisMEcFBxmzKWAIgemexEzv+UAAVF+5oKXkTMM4EEAYc1J9xy6makhDDkgY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":330},"_npmUser":{"name":"tarek.eg","email":"seotarek@gmail.com"},"description":"Temporary package placeholder for staged publishing","directories":{}},"2.1.0":{"name":"medorqis","version":"2.1.0","keywords":["medical-ai","clinical-decision-support","skills","skills-cli","mcp-server","zero-token","healthcare","fhir","safety-guardrails","pediatrics","cardiology","pharmacology","claude-code","gemini-cli"],"author":{"name":"Tarek","email":"seotarek@gmail.com"},"license":"Apache-2.0","_id":"medorqis@2.1.0","maintainers":[{"name":"tarek.eg","email":"seotarek@gmail.com"}],"homepage":"https://seotarek.github.io/MedOrqis/","bugs":{"url":"https://github.com/seotarek/MedOrqis/issues"},"bin":{"medorqis":"bin/medorqis.js"},"dist":{"shasum":"30740a85254ad6f4edc26e34f4289b13e724698c","tarball":"https://registry.npmjs.org/medorqis/-/medorqis-2.1.0.tgz","fileCount":144,"integrity":"sha512-BjdcYlvVHv52FA0aVAkyT7Y0zG1LIl7um8VnwQ+uk7JI1LCC1NApFN4UCctgkmL4oKBf0wO+huYNdP+CVpNPWA==","signatures":[{"sig":"MEYCIQCRH5wt/QSw3DmeA8FAOV1iaceu6zTXZr1VCnJD+2ZOxQIhAJoZeK7mj9PMzURp6iBMslQW29f4HuqK8kT5PbxEx0M7","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCIFSUWwvYc7Y4KIsHNUHJgwazofMhIiMM7aPI9c3RNjwKAiA7QBuqJQYrQbxIkPvd0tir+xdUCwr1r5AvkxCo+OjPYg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":625648},"main":"bin/medorqis.js","gitHead":"43c6dbdd03b92e46928f6596122b19e022899422","_npmUser":{"name":"tarek.eg","email":"seotarek@gmail.com"},"repository":{"url":"git+https://github.com/seotarek/MedOrqis.git","type":"git"},"_npmVersion":"10.9.8","description":"MedOrqis — Medical AI Skills Ecosystem: 24 Specialized Clinical AI Skills, Deterministic Safety Guardrails & Zero-Token Calculators","directories":{},"_nodeVersion":"22.23.1","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/medorqis_2.1.0_1793052016795_0.2910065982135579","host":"s3://npm-registry-packages-npm-production"}},"2.1.1":{"_id":"medorqis@2.1.1","bin":{"medorqis":"bin/medorqis.js"},"bugs":{"url":"https://github.com/seotarek/MedOrqis/issues"},"dist":{"shasum":"2b787641cf168be032966057ab837c11bf755034","tarball":"https://registry.npmjs.org/medorqis/-/medorqis-2.1.1.tgz","fileCount":146,"integrity":"sha512-QV7DyM2l5Kn5Uqvt+WONzgEEaTSASbG2jBgJa/quPW+e978iuW7Tzdz3n3Bzxj7mX4g4xiw5FWht6R9JgKmsVg==","signatures":[{"sig":"MEUCIC/8kXxbndNQ5s2zQpmIKiECkr9+xeg1hA+0bn6gDvSNAiEA8gAULwaP5yLQqSimGmZzkN5Vd/Q4SfPci9PI8NU6+hw=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIQDaMSSFn/PkOMFb/2p6+3ObelHRKMhHKuQLI4bQ/h4/SAIgeb2xvXcnm5QIaDGD9RiCdo4ST+mpK/j1I8YwEKGrzxE="}],"unpackedSize":658864},"main":"bin/medorqis.js","name":"medorqis","author":{"name":"Tarek","email":"seotarek@gmail.com"},"gitHead":"aaebd316a03be963e8134666d292ef6b892ec630","license":"Apache-2.0","version":"2.1.1","_npmUser":{"name":"tarek.eg","email":"seotarek@gmail.com"},"homepage":"https://seotarek.github.io/MedOrqis/","keywords":["medical-ai","clinical-decision-support","skills","skills-cli","mcp-server","zero-token","healthcare","fhir","safety-guardrails","pediatrics","cardiology","pharmacology","claude-code","gemini-cli"],"repository":{"url":"git+https://github.com/seotarek/MedOrqis.git","type":"git"},"_npmVersion":"10.9.8","description":"MedOrqis — Medical AI Skills Ecosystem: 24 Specialized Clinical AI Skills, Deterministic Safety Guardrails & Zero-Token Calculators","directories":{},"maintainers":[{"name":"tarek.eg","email":"seotarek@gmail.com"}],"_nodeVersion":"22.23.1","_hasShrinkwrap":false,"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/medorqis_2.1.1_1793053577606_0.45392778211427576"}}},"time":{"created":"2026-10-26T21:58:05.160Z","modified":"2026-10-26T22:26:18.447Z","0.0.0-stage":"2026-10-26T21:58:05.160Z","2.1.0":"2026-10-26T22:00:16.904Z","2.1.1":"2026-10-26T22:26:17.720Z"},"bugs":{"url":"https://github.com/seotarek/MedOrqis/issues"},"author":{"name":"Tarek","email":"seotarek@gmail.com"},"license":"Apache-2.0","homepage":"https://seotarek.github.io/MedOrqis/","keywords":["medical-ai","clinical-decision-support","skills","skills-cli","mcp-server","zero-token","healthcare","fhir","safety-guardrails","pediatrics","cardiology","pharmacology","claude-code","gemini-cli"],"repository":{"url":"git+https://github.com/seotarek/MedOrqis.git","type":"git"},"description":"MedOrqis — Medical AI Skills Ecosystem: 24 Specialized Clinical AI Skills, Deterministic Safety Guardrails & Zero-Token Calculators","maintainers":[{"name":"tarek.eg","email":"seotarek@gmail.com"}],"readme":"# MedOrqis — Medical AI Skills Ecosystem (v2.1.1)\n\n[![License: Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-blue.svg)](LICENSE)\n[![npm version](https://img.shields.io/npm/v/medorqis.svg?color=cb3837)](https://www.npmjs.com/package/medorqis)\n[![Verification: 100% Passed](https://img.shields.io/badge/Verification-100%25%20Passed-brightgreen.svg)](tests/reports/VERIFICATION_REPORT.md)\n[![GitHub CI](https://github.com/seotarek/MedOrqis/actions/workflows/ci.yml/badge.svg)](https://github.com/seotarek/MedOrqis/actions)\n[![Safety: IEC 62304 / ISO 14971 Aligned](https://img.shields.io/badge/Safety%20Class-Class%20A%20%7C%20B%20%7C%20C-red.svg)](SAFETY_AND_GOVERNANCE.md)\n[![Skills Catalog: 24 Skills](https://img.shields.io/badge/Catalog-SKILLS.md-teal.svg)](SKILLS.md)\n[![Showcase: Interactive Hub](https://img.shields.io/badge/Showcase-Web%20Catalog-00e5a3.svg)](https://seotarek.github.io/MedOrqis/)\n[![MCP: Enabled](https://img.shields.io/badge/MCP-JSON--RPC%202.0-purple.svg)](mcp_server/medorqis_mcp_server.py)\n\n**MedOrqis** is an open-source, evidence-grounded, cross-platform ecosystem of **24 medical AI skills**, deterministic clinical engines, and platform adapters (Skills CLI, Claude Code, Gemini CLI, Model Context Protocol, and OpenAI).\n\n> 🌐 **Interactive Web Hub**: Explore the live searchable catalog and zero-token clinical calculators at [seotarek.github.io/MedOrqis](https://seotarek.github.io/MedOrqis/) or review [SKILLS.md](SKILLS.md).  \n> 📦 **NPM Registry**: Available as [`medorqis`](https://www.npmjs.com/package/medorqis) on npm. Run instantly via `npx medorqis`.\n\nBuilt with an **evidence-first, patient-safety-first architecture**, MedOrqis completely eliminates medical hallucination risks in high-stakes clinical calculations by executing arithmetic, unit conversions, PHI scrubbing, negation parsing, and drug interaction screenings through a **local, deterministic Python core with zero LLM API token overhead**.\n\n---\n\n## ⚡ Key Highlights & Token Economics\n\n1. **Zero-Token Deterministic Core (`core/`)**:\n   - High-risk calculations (stroke risk, race-free eGFR, creatinine clearance, pediatric dosing caps, pneumonia severity, DVT/PE probabilities) run locally in pure Python with **zero token cost**.\n   - PHI de-identification (HIPAA Safe Harbor, Egyptian 14-digit National IDs, Saudi 10-digit National IDs/Iqamas) and prompt injection defense run locally and deterministically.\n2. **Epistemic Provenance Rule**:\n   - `core/context_validator.py` enforces a hard architectural gate: no downstream skill can prescribe or dose medications based on a `MODEL_INFERRED_HYPOTHESIS`. High-risk clinical decisions strictly require confirmed `DOCUMENTED_CLINICAL_RECORD` provenance.\n3. **Cross-Platform Compatibility**:\n   - **Claude Code & Agent Skills**: Native `.claude/skills/` support.\n   - **Gemini CLI Extension**: `gemini-extension.json` with `GEMINI.md` context.\n   - **Model Context Protocol (MCP)**: Standalone stdio JSON-RPC server (`mcp_server/medorqis_mcp_server.py`).\n   - **OpenAI**: Strict Structured Outputs and Assistant function schemas.\n4. **Quantifiable Multilingual Semantic Invariance**:\n   - **100% Negation Preservation**: Preserves clinical negation in Modern Standard Arabic, Egyptian Arabic, Gulf Arabic, English, French, and Spanish.\n   - **BiDi Unit Fidelity**: Prevents decimal inversion (e.g. `0.25 mg`) and critical unit confusion (`mg` vs `mcg`).\n\n---\n\n## 🏥 The 24-Skill Risk-Stratified Taxonomy\n\n### Tier 1: Governance, Research & Operations (Class A)\n- `medorqis-orchestrator`: Context envelope routing and conflict resolution.\n- `ebm-research-biostatistics`: PICO, CASP, RoB-2 appraisal, and GRADE certainty.\n- `medical-documentation-translation`: SOAP, SBAR, and BiDi multilingual medical translation.\n- `healthcare-ops-telemedicine-ehr`: HL7 FHIR mapping and telemedicine intake.\n- `health-cybersecurity-privacy`: PHI scrubbing and prompt injection defense.\n- `public-health-epidemiology`: Screening metrics (sens/spec) and IPC protocols.\n\n### Tier 2: Diagnostic & Chronic Care Support (Class B)\n- `differential-diagnosis-cds`: VINDICATE differential framework.\n- `laboratory-medicine-pathology`: Critical panic values and LOINC mapping.\n- `radiology-medical-imaging`: ACR Appropriateness Criteria and radiation safety.\n- `internal-medicine-chronic`: Multi-morbidity chronic disease care plans.\n- `infectious-diseases-stewardship`: Antimicrobial stewardship and resistance awareness.\n- `nursing-clinical-care`: NEWS2 early warning score and Braden scale.\n- `clinical-nutrition-dietetics`: Caloric requirements and food-drug interactions.\n- `rehabilitation-physical-therapy`: Post-op and stroke rehab protocols.\n\n### Tier 3: High-Risk, Emergency & Vulnerable Populations (Class C)\n- `emergency-triage-redflags`: ABCDE primary survey and emergency redirection.\n- `clinical-safety-auditor`: Pre-output verification and safety gate check.\n- `pharmacology-dosing-interactions`: Renal/hepatic adjustments and DDI checks.\n- `clinical-toxicology-overdose`: Toxidromes, antidotes, and Poison Control escalation.\n- `pediatrics-neonatology`: Weight-based dose capping and pediatric safety.\n- `obstetrics-gynecology`: Maternal-fetal safety and pre-eclampsia triage.\n- `geriatrics-polypharmacy`: 2023 Beers Criteria and STOPP/START.\n- `mental-health-psychiatry`: Suicide crisis escalation and psychotropic monitoring.\n- `perioperative-surgical-care`: RCRI pre-op risk and anticoagulation bridging.\n- `oncology-palliative-care`: Oncologic emergencies and palliative pain control.\n\n---\n\n## 🚀 Quick Start & Integration Options\n\n### ⚡ Option 1: Universal AI Model Prompting (Zero Install — Any Model)\nYou do not need to install anything or run code to use MedOrqis with LLMs! You can send the repository link and prompt directly to **ChatGPT (with web access), Claude 3.5 Sonnet, Google Gemini, Cursor, Grok, or Antigravity**:\n\n> **Copy & Paste into any AI model:**\n> ```text\n> Read the open-source clinical AI skills ecosystem MedOrqis at:\n> https://github.com/seotarek/MedOrqis (Web catalog: https://seotarek.github.io/MedOrqis/)\n> \n> You are now operating under MedOrqis clinical governance rules (v2.1.1):\n> 1. Enforce zero-hallucination deterministic standards for all medical risk scores and formulas (CHA2DS2-VASc, CKD-EPI 2021, Cockcroft-Gault, Wells DVT/PE, CURB-65, Pediatric Capping).\n> 2. Epistemic provenance: Never recommend high-risk interventions based on unconfirmed model hypotheses.\n> 3. Missing Age Gatekeeper: If patient age is unrecorded, do NOT assume a default adult age (30); immediately flag SAFE_ABSTENTION_DATA_DEFICIT.\n> 4. Sentinel Emergency Red Flags: Immediate emergency redirection on acute stroke (FAST), ACS crushing chest pain, anaphylaxis, septic shock, or anticoagulation + active bleeding.\n> 5. Provide evidence-grounded differential diagnosis, drug interaction screening, and red-flag triage across all 24 MedOrqis clinical domains.\n> \n> Please summarize your activated clinical skills and await clinical input.\n> ```\n\n---\n\n### 📦 Option 2: NPX & NPM CLI Package (`medorqis`)\nAvailable globally via npm without manual cloning:\n```bash\n# Interactive menu & skills catalog\nnpx medorqis\n\n# List all 24 clinical skills grouped by tier\nnpx medorqis list\n\n# Print copyable Universal AI Prompt for web LLMs\nnpx medorqis prompt\n\n# Print MCP configuration block\nnpx medorqis mcp\n```\nOr install globally:\n```bash\nnpm install -g medorqis\n```\n\n---\n\n### 🛠️ Option 3: Install via Skills CLI (Vercel Labs)\nAdd MedOrqis to your active AI agent workspace with a single command:\n```bash\nnpx skills add seotarek/MedOrqis\n```\nOr install specific skills:\n```bash\nnpx skills add seotarek/MedOrqis --skill emergency-triage-redflags\nnpx skills add seotarek/MedOrqis --skill pharmacology-dosing-interactions\n```\n\n---\n\n### 🔌 Option 4: Model Context Protocol (MCP Server)\nRun the local MCP stdio server:\n```bash\npython3 mcp_server/medorqis_mcp_server.py\n```\nAdd to your Claude Desktop config (`claude_desktop_config.json`):\n```json\n{\n  \"mcpServers\": {\n    \"medorqis\": {\n      \"command\": \"python3\",\n      \"args\": [\"/path/to/MedOrqis/mcp_server/medorqis_mcp_server.py\"]\n    }\n  }\n}\n```\n\n---\n\n### 🐍 Option 5: Local Python Developer Setup\nClone the repository and install core dependencies:\n```bash\ngit clone https://github.com/seotarek/MedOrqis.git\ncd MedOrqis\npython3 -m pip install -e .\n```\n\n---\n\n### 🧪 Option 6: Run the Full Verification Suite\nExecute all 4 clinical verification test suites with a single command:\n```bash\npython3 tests/run_all_tests.py\n```\nThis automatically executes:\n1. `tests/unit/test_clinical_calculators.py`\n2. `tests/safety/test_safety_and_provenance.py`\n3. `tests/multilingual/test_multilingual_benchmark.py`\n4. `tests/platform_adapters/test_security_and_adapters.py`\n\nAnd generates:\n- [VERIFICATION_REPORT.md](tests/reports/VERIFICATION_REPORT.md)\n- [LANGUAGE_COVERAGE_MATRIX.md](LANGUAGE_COVERAGE_MATRIX.md)\n\n---\n\n## ⚖️ Governance & Regulatory Disclaimer\nMedOrqis is an open-source clinical reference architecture and research framework. It is **NOT** a certified Medical Device (SaMD) and does not autonomously diagnose or prescribe. Clinical Decision Support must always be reviewed by a licensed healthcare professional. See [MEDICAL_DISCLAIMER.md](MEDICAL_DISCLAIMER.md) and [SAFETY_AND_GOVERNANCE.md](SAFETY_AND_GOVERNANCE.md) for full details.\n\n---\n\n## 📜 License\nLicensed under the [Apache License, Version 2.0](LICENSE).\nMedical vocabularies and guidelines are attributed in [DATA_LICENSES_AND_ATTRIBUTIONS.md](DATA_LICENSES_AND_ATTRIBUTIONS.md).\n","readmeFilename":"README.md"}