All authors
Claude Skills by mdbabumiamssm
github.com/mdbabumiamssm1,578 skills3 installs3,530 views
- PydanticAI 2026--> --- name: pydanticai-2026 description: Build schema-first Python agents with typed tools, structured outputs, provider portability, and observability. Use when application code should stay explicit and validated rather than hidden behind framework magic. measurable_outcome: Specify a typed agent interface, validated tool schema, and observability path for a new or existing Python agent workflow within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- RewardHypothesisVerification Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'reward-hypothesis-verification' description: 'Verify and deploy LLM-generated reward hypotheses using competence-aware short-horizon forks and phase-aware RL training decisions.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- RlExplorationHackingSafetyAgent Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'rl-exploration-hacking-safety-agent' description: 'Detect and mitigate exploration hacking, where LLMs strategically suppress exploration during RL post-training to resist capability elicitation and influence training outcomes.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- SecurityAgentOperations Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'security-agent-operations' description: 'Operate security-focused coding agents with scoped authorization, lab isolation, adversarial workflows, tool boundaries, and defensive validation inspired by Raptor.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Smolagents 2026--> --- name: smolagents-2026 description: Build lightweight code-first or tool-calling agents with Hugging Face smolagents. Use when minimal abstractions, code agents, sandboxed execution, and model flexibility matter more than a heavy orchestration runtime. measurable_outcome: Select a smolagents agent type, sandbox boundary, and model path for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- StrandsAgentcoreReferenceArchitecture Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'strands-agentcore-reference-architecture' description: 'Implement AWS Strands Agents with Amazon Bedrock AgentCore reference architectures for chat, voice, A2A/MCP, browser automation, observability, deployment, and security.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- SwarmclawSelfHostedAgentRuntime Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'swarmclaw-self-hosted-agent-runtime' description: 'Deploy and operate SwarmClaw as a self-hosted multi-agent AI runtime with MCP servers, memory, skills, schedules, and multi-provider LLM routing.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- SyntheticComputersLongHorizonTraining Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'synthetic-computers-long-horizon-training' description: 'Generate persona-conditioned synthetic computer environments and run multi-thousand-turn long-horizon productivity simulations to produce experiential training data for agent self-improvement.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Browser Use 2026--> --- name: browser-use-2026 description: Build browser-native AI task automation with Browser Use. Use when real web execution, persistent browser workspaces, and managed browser infrastructure are core to the workflow rather than incidental. measurable_outcome: Select a Browser Use execution pattern, security boundary, and validation path for a concrete browser-agent workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- OpenClaw AgentOperate OpenClaw as a local AI assistant and agent OS with explicit security boundaries. Use when local system automation, browser work, and provider-pluggable execution need to stay on the operator's machine rather than moving to a hosted browser agent surface.Votes: 0GitHub stars: 6
- Care Coordination--> --- name: 'care-coordination' description: 'Care Coordination agent for healthcare workflows.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill implements the Care Coordination workflow using Anthropic's Claude.Votes: 0GitHub stars: 6
- Claims Appeals--> --- name: 'claims-appeals' description: 'Claims Appeals agent for healthcare workflows.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill implements the Claims Appeals workflow using Anthropic's Claude.Votes: 0GitHub stars: 6
- FHIR Development--> --- name: 'fhir-development' description: 'FHIR Development agent for healthcare workflows.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill implements the FHIR Development workflow using Anthropic's Claude.Votes: 0GitHub stars: 6
- Lab Results--> --- name: 'lab-results' description: 'Lab Results agent for healthcare workflows.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill implements the Lab Results workflow using Anthropic's Claude.Votes: 0GitHub stars: 6
- Regulatory Drafting--> --- name: 'regulatory-drafting' description: 'SOTA Regulatory Drafting agent for healthcare workflows (FDA/EMA submissions) aligned with Anthropic healthcare initiatives.' measurable_outcome: 'Draft a complete regulatory submission (e.g., IND, CTD Module 2) with >99% factual accuracy in < 10 minutes.' license: MIT metadata: author: Biomedical AI Team version: "2.0.0" compatibility: - system: BioKernel/MCP model_requirements: 'Claude 3.5 Sonnet (Speed) or Opus (Reasoning)' allowed-tools: -...Votes: 0GitHub stars: 6
- Research Literature--> --- name: 'research-literature' description: 'Research Literature agent for healthcare workflows.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill implements the Research Literature workflow using Anthropic's Claude.Votes: 0GitHub stars: 6
- ClinicalCostEffectivenessModeling Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-cost-effectiveness-modeling' description: 'Build auditable cost-effectiveness models for clinical interventions, including AI-derived outcomes, with QALYs, ICERs, uncertainty analysis, validation, and human review.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- ClinicalGuidelineDevelopmentLlm Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-guideline-development-llm' description: 'LLM-assisted clinical practice guideline development workflow grounded in real-time evaluation, evidence traceability, expert review, recommendation grading, and human governance.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- ClinicalLlmEvaluationBenchmarking Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-llm-evaluation-benchmarking' description: 'Design and run rigorous clinical LLM evaluation workflows grounded in systematic review evidence on AI-generated clinical note quality methods.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- ClinicalLlmPatientEducation Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-llm-patient-education' description: 'Translate radiology reports and clinical documents into personalized patient education while preserving meaning, uncertainty, next steps, and clinician review requirements.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Clinvar Lookup--> --- name: bio-clinical-databases-clinvar-lookup description: Query ClinVar for variant pathogenicity classifications, review status, and disease associations via REST API or local VCF. Use when determining clinical significance of variants for diagnostic or research purposes. tool_type: python primary_tool: requests measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Dbsnp Queries--> --- name: bio-clinical-databases-dbsnp-queries description: Query dbSNP for rsID lookups, variant annotations, and cross-references to other databases. Use when mapping between rsIDs and genomic coordinates or retrieving basic variant information. tool_type: python primary_tool: myvariant measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Gnomad Frequencies--> --- name: bio-clinical-databases-gnomad-frequencies description: Query gnomAD for population allele frequencies to assess variant rarity. Use when filtering variants by population frequency for rare disease analysis or determining if a variant is common in the general population. tool_type: python primary_tool: requests measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Hla Typing--> --- name: bio-clinical-databases-hla-typing description: Call HLA alleles from NGS data using OptiType, HLA-HD, or arcasHLA for immunogenomics applications. Use when determining HLA genotype for transplant matching, neoantigen prediction, or pharmacogenomic screening. tool_type: cli primary_tool: OptiType measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Myvariant Queries--> --- name: bio-clinical-databases-myvariant-queries description: Query myvariant.info API for aggregated variant annotations from multiple databases (ClinVar, gnomAD, dbSNP, COSMIC, etc.) in a single request. Use when annotating variants with clinical and population data from multiple sources simultaneously. tool_type: python primary_tool: myvariant measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Pharmacogenomics--> --- name: bio-clinical-databases-pharmacogenomics description: Query PharmGKB and CPIC for drug-gene interactions, pharmacogenomic annotations, and dosing guidelines. Use when predicting drug response from genetic variants or implementing clinical pharmacogenomics. tool_type: python primary_tool: requests measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Polygenic Risk--> --- name: bio-clinical-databases-polygenic-risk description: Calculate polygenic risk scores using PRSice-2, LDpred2, or PRS-CS from GWAS summary statistics. Use when predicting disease risk from genome-wide genetic variants. tool_type: mixed primary_tool: PRSice-2 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Somatic Signatures--> --- name: bio-clinical-databases-somatic-signatures description: Extract and analyze mutational signatures from somatic variants using SigProfiler or MutationalPatterns to characterize mutagenic processes. Use when identifying DNA damage mechanisms or etiology in cancer genomes. tool_type: mixed primary_tool: SigProfilerExtractor measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Tumor Mutational Burden--> --- name: bio-clinical-databases-tumor-mutational-burden description: Calculate tumor mutational burden from panel or WES data with proper normalization and clinical thresholds. Use when assessing immunotherapy eligibility or characterizing tumor immunogenicity. tool_type: python primary_tool: cyvcf2 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Variant Prioritization--> --- name: bio-clinical-databases-variant-prioritization description: Filter and prioritize variants by pathogenicity, population frequency, and clinical evidence for rare disease analysis. Use when identifying candidate disease-causing variants from exome or genome sequencing. tool_type: python primary_tool: pandas measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Clinical Note SummarizationStructure raw clinical notes into SOAP-format summaries with explicit contradictions, missing data, and ICD-linked assessments using the provided prompt + usage script.Votes: 0GitHub stars: 6
- DermatologyMultimodalLlmBccAnalysis Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'dermatology-multimodal-llm-bcc-analysis' description: 'Guide multimodal LLM-assisted review of clinical and dermoscopic images for basal cell carcinoma mimickers, emphasizing differential diagnosis, harm checks, and clinician review.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Digital Twin Clinical Agent--> --- name: 'digital-twin-clinical-agent' description: 'AI-powered patient digital twin creation for clinical trial simulation, treatment outcome prediction, and personalized medicine using real-world data and multi-omics integration.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Digital Twin Clinical Agent** creates AI-powered virtual replicas of individual patients by integrating genom...Votes: 0GitHub stars: 6
- ChatEHR--> --- name: chatehr-clinician-assistant description: EHR Chat Assistant keywords: - EHR - clinical - summarization - patient-records - FHIR measurable_outcome: Answer 5 clinical queries and generate a discharge summary from a patient record with <10s latency. license: Apache-2.0 metadata: author: Stanford Medicine version: "1.0.0" compatibility: - system: Python 3.10+ allowed-tools: - run_shell_command - read_file --- AI software for clinicians to interact with patient medical records via n...Votes: 0GitHub stars: 6
- EHR FHIR Integration--> --- name: 'ehr-fhir-integration' description: 'Provides comprehensive tools for working with Electronic Health Records (EHR) using the HL7 FHIR standard.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **EHR/FHIR Integration Skill** enables AI agents to interact with FHIR servers to search, read, and analyze clinical data.Votes: 0GitHub stars: 6
- GastroenterologyLlmClinicalPractice Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'gastroenterology-llm-clinical-practice' description: 'Support evidence-grounded use of LLMs in gastroenterology clinical practice, including endoscopy, IBD, hepatology, triage, documentation, and patient education.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Multimodal Analysis--> --- name: 'multimodal-medical-imaging' description: 'Analyzes medical images (X-ray, MRI, CT) using multimodal LLMs to identify anomalies and generate reports.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Multimodal Medical Imaging Analysis Skill** leverages state-of-the-art Vision-Language Models (VLMs) like Gemini 1.5 Pro and GPT-4o to interpret medical imagery alongside clinical text.Votes: 0GitHub stars: 6
- MicrosoftPriorAuthMultiAgentAccelerator Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'microsoft-prior-auth-multi-agent-accelerator' description: 'Guide payer-side prior authorization review using Microsoft Azure multi-agent patterns, Foundry-hosted agents, MCP healthcare data access, audit trails, and human oversight.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Multimodal Radpath Fusion Agent--> --- name: 'multimodal-radpath-fusion-agent' description: 'AI-powered multimodal diagnostic fusion integrating radiology imaging (CT/MRI/PET), digital pathology (WSI), genomics, and clinical data for comprehensive cancer diagnosis and treatment planning.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Multimodal Radpath Fusion Agent** integrates diverse clinical data sources including rad...Votes: 0GitHub stars: 6
- OnPremClinicalLlmDeployment Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'on-prem-clinical-llm-deployment' description: 'Plan and validate on-prem clinical LLM deployments for distilled open-source diagnosis models, balancing performance, privacy, hardware, governance, and human oversight.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Autonomous Oncology Agent--> --- name: autonomous-oncology-agent description: Precision Oncology keywords: - oncology - multimodal - H&E - biomarkers - NCCN measurable_outcome: Generate a prioritized treatment plan with evidence levels and predicted biomarker status (MSI/KRAS) within 5 minutes of data ingest. license: MIT metadata: author: Nature Cancer 2025 version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - web_fetch --- This skill implements the capabilities of the "Autonomou...Votes: 0GitHub stars: 6
- Precision Oncology Agent--> --- name: precision-oncology-agent description: Fuse genomic variants, pathology findings, and clinical context to draft evidence-linked therapy options for tumor board review. measurable_outcome: Deliver a ranked therapy list with OncoKB and NCCN citations plus a data-gap checklist for every case within 10 minutes of receiving inputs. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- OphthalmologyLlmSafetyEvaluation Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'ophthalmology-llm-safety-evaluation' description: 'Evaluate ophthalmology LLM answers to CME or board-style questions for correctness, omissions, harm risk, guideline consistency, and clinician review.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Prior Authorization--> --- name: 'prior-auth-coworker' description: 'SOTA Prior Auth Review Agent aligned with Anthropic and OpenAI healthcare initiatives.' measurable_outcome: 'Achieve >95% accuracy matching human UM reviewers, completing analysis in under 5 minutes.' license: MIT metadata: author: Biomedical AI Team version: "2.0.0" compatibility: - system: BioKernel/MCP allowed-tools: - read_file - run_shell_command - mcp_bio_tool --- This skill acts as an automated utilization management reviewer. It takes ...Votes: 0GitHub stars: 6
- ProstheticsLlmDecisionSupport Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'prosthetics-llm-decision-support' description: 'Assist clinician-reviewed prosthetic recommendations using ProsthetiX-AI-style intake, evidence retrieval, safety checks, and documentation.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- PsychiatryKnowledgeFusedReasoning Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'psychiatry-knowledge-fused-reasoning' description: 'Guides psychiatry-specific LLM support using PKFAR-style knowledge fusion and augmented reasoning for diagnosis, risk, medications, and care planning.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- RadGPT--> --- name: radgpt-radiology-reporter description: Radiology Reporter keywords: - radiology - report-generation - patient-friendly - summarization - explanation measurable_outcome: Generate a patient-friendly explanation of a radiology report with <1% hallucination rate within 30 seconds. license: MIT metadata: version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - read_file --- An LLM-based agent designed to summarize and explain complex radiology report...Votes: 0GitHub stars: 6
- AI Safety Auditor--> --- name: ai-safety-auditor description: Validates clinical AI outputs for safety, bias, and hallucination risks before delivery to end-users or clinicians. keywords: - ai-safety - compliance - bias-detection - hallucination-check - clinical-validation measurable_outcome: Identifies 100% of critical safety violations and potential PHI leakage in generated clinical notes. license: MIT metadata: author: Biomedical AI Team version: "1.0.0" compatibility: - system: Python 3.10+ allowed-tools:...Votes: 0GitHub stars: 6
- Safety--> --- name: 'safety-monitor' description: 'Safety Monitor' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Agent responsible for compliance and safety checks. It inspects content for safety violations, toxins, or medical misinformation.Votes: 0GitHub stars: 6
- SurgicalPatientCommunicationAi Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'surgical-patient-communication-ai' description: 'Draft clinician-reviewed surgical communication, education, consent-support, expectation-setting, and escalation materials using AI governance for surgery workflows.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6