All authors
Claude Skills by mdbabumiamssm
github.com/mdbabumiamssm1,577 skills5 installs3,735 views
- Mistral Platform Operations 2026Integrate and operate Mistral APIs with current model catalog, SDKs, and agent features. Use when implementing Mistral chat, agents, conversations, files, or coding workflows.Votes: 0GitHub stars: 32
- OpenAI Platform Operations 2026--> --- name: openai-platform-operations-2026 description: Operate and integrate OpenAI APIs with current model, modality, and migration workflows. Use when building or updating OpenAI-based chat, reasoning, transcription, speech, image, or video pipelines, and when replacing deprecated models. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 32
- XAI Grok Operations 2026Integrate and operate xAI Grok APIs with current documentation and SDK guidance. Use when implementing Grok tool use, Responses-style workflows, files or collections search, or migration from other provider SDKs.Votes: 0GitHub stars: 32
- AgentScope Runtime--> --- name: bio-agentscope-runtime description: Deploy AgentScope + AgentScope Runtime for secure sandboxed multi-agent services inside BioKernel. tool_type: mixed primary_tool: Unknown measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- AgentScope is a production-ready multi-agent framework with ReAct agents, memory, human-in-the-loop steering, MCP/A2A integrations, and voice support, while AgentSco...Votes: 0GitHub stars: 32
- Plan And Solve--> --- name: 'plan-and-solve-agent' description: 'Breaks down complex queries into a step-by-step plan before execution, improving performance on multi-hop reasoning tasks.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Plan-and-Solve Agent** separates high-level planning from low-level execution. It is ideal for complex scientific inquiries that require multiple distinct steps (e.g., "Fin...Votes: 0GitHub stars: 32
- Agentic Evals ObservabilityDesign evaluation, tracing, monitoring, scope-control, and rollback discipline for agent systems. Use when an agent workflow is becoming important enough that you need evidence, not vibes, to decide whether it is good.Votes: 0GitHub stars: 32
- Automated Web Research--> --- name: automated-web-research description: Run evidence-first web research with multi-query search, page fetch, source vetting, and cited synthesis. Use when the answer depends on recent information, official documentation, or current external services. keywords: - research - web - citations - verification - official-docs measurable_outcome: Produce a cited brief grounded in at least 5 sources, with source-quality notes and unresolved gaps called out, within 20 minutes. metadata: autho...Votes: 0GitHub stars: 32
- Claude Code Operations 2026Build and operate Claude Code workflows in the terminal, IDE, and GitHub Actions with hooks, MCP, and approval-aware repo automation. Use when evaluating or deploying Anthropic's coding-agent surface rather than generic Claude API usage.Votes: 0GitHub stars: 32
- Computer Use Agents 2026Design and operate browser and desktop agents that rely on screenshots, mouse and keyboard control, or hybrid bash/editor/computer loops. Use when deciding between DOM automation, browser agents, and full computer-use workflows.Votes: 0GitHub stars: 32
- DeepResearch Swarm--> --- name: deep-research-swarm description: Coordinate a multi-agent research workflow for difficult literature or market-intelligence questions that need parallel search, verification, synthesis, and explicit evidence tracking. keywords: - research - literature - swarm - multi-agent - verification measurable_outcome: Produce a structured research package with search log, verified evidence summary, and open questions within 30 minutes for a focused topic. metadata: author: Biomedical OS Te...Votes: 0GitHub stars: 32
- Google ADK AgentsBuild, evaluate, and deploy agents with Google's Agent Development Kit (ADK). Use when you want code-first multi-agent systems, workflow agents, MCP tools, or Google-supported agent deployment paths.Votes: 0GitHub stars: 32
- LangGraph Self Hosted--> --- name: langgraph-self-hosted description: Deploy LangGraph Platform-compatible backends (Aegra) to run regulated biomedical agent workflows on private infrastructure with security guardrails. keywords: - langgraph - self-hosted - agentic-ai - fastapi - postgres measurable_outcome: Stand up a LangGraph-compatible deployment (API + persistence) behind your firewall, register at least one graph, and route traffic through it within 4 hours. license: Apache-2.0 (Aegra) metadata: author: Age...Votes: 0GitHub stars: 32
- Multi Agent Systems--> --- name: 'swarm-orchestrator' description: 'Run Agent Swarms' keywords: - swarm - orchestration - multi-agent - parallel-execution - routing measurable_outcome: Successfully coordinates 3+ specialized agents to resolve complex queries with 100% completion rate. allowed-tools: - read_file - run_shell_command --- This skill activates a multi-agent system where a central "Overmind" routes tasks to specialized agents. It is designed for complex queries requiring multiple perspectives (search...Votes: 0GitHub stars: 32
- OpenAI Codex AgentsBuild and operate OpenAI-first coding and agent workflows using Codex app/cloud, the Responses API, current GPT and Codex models, Agents SDK, hosted tools, tool search, MCP/connectors, skills, and approval-aware tool execution. Use when you need long-horizon software agents or OpenAI-native multi-agent orchestration.Votes: 0GitHub stars: 32
- OpenHands Coding Agent--> --- name: bio-openhands-coding-agent description: Run OpenHands headless CLI/SDK missions from BioKernel swarms for autonomous software work. tool_type: mixed primary_tool: Unknown measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- OpenHands (formerly OpenDevin) is a 70k+ star open-source coding agent stack that exposes the same engine through a Python SDK, a CLI, a local GUI, a hosted cloud works...Votes: 0GitHub stars: 32
- Memory Management--> --- name: memory-management description: Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base. keywords: - memory - context - decoding - glossary - collaboration measurable_outcome: Correctly identifies and decodes 90% of user-specific shorthands and acronyms in conversation. allo...Votes: 0GitHub stars: 32
- Task Management--> --- name: task-management description: Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments. keywords: - tasks - todo - tracking - active - dashboard measurable_outcome: Maintains an up-to-date TASKS.md reflecting all active user commitments and deadlines. allowed-tools: - read_file - run_shell_command --- Tasks are tracked in a simple `TASKS.md` file that both you and the ...Votes: 0GitHub stars: 32
- PydanticAI AgentsBuild typed, provider-agnostic agents with PydanticAI. Use when structured I/O, dependency injection, MCP support, and OpenTelemetry-friendly observability matter more than framework hype.Votes: 0GitHub stars: 32
- Scientific Discovery Agents 2026Design, evaluate, and operate agentic systems for biomedical and scientific discovery. Use when building or selecting agents for hypothesis generation, experiment planning, autonomous notebook analysis, lab-in-the-loop validation, pathology concept discovery, or multi-agent research workflows.Votes: 0GitHub stars: 32
- ClinicalGuidelineDevelopmentLlm Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-guideline-development-llm' description: 'Guide LLM-assisted clinical practice guideline drafting with real-time review, evidence traceability, recommendation grading, and clinician 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: 32
- ClinicalLlmEvaluationBenchmarking Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-llm-evaluation-benchmarking' description: 'Design and run clinical LLM evaluation benchmarks grounded in systematic review evidence on AI-generated clinical note evaluation 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: 32
- ClinicalLlmPatientEducation Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'clinical-llm-patient-education' description: 'Translate clinical documents into personalized patient education while preserving diagnostic meaning, uncertainty, next steps, and clinician-review safeguards.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- 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: 32
- Clinical NLP--> --- name: 'clinical-nlp-extractor' description: 'Extracts medical entities (Diseases, Medications, Procedures), patient outcomes with temporal anchors, and registry-oriented real-world data from unstructured clinical text using regex and simple rules (or LLM wrappers).' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Clinical NLP Skill** converts free-text clinical notes into structured d...Votes: 0GitHub stars: 32
- Clinical Note Summarization--> --- name: clinical-note-summarization description: Structure raw clinical notes into SOAP-format summaries with explicit contradictions, missing data, and ICD-linked assessments using the provided prompt + usage script. measurable_outcome: Produce SOAP markdown and JSON outputs covering all four sections with at least 95% note coverage and explicit missing information within 2 minutes per note. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 32
- Clinical Workflow Automation Agent--> --- name: clinical-workflow-automation description: An autonomous agentic system for automating and streamlining clinical workflows and healthcare administrative tasks. keywords: - clinical-workflow - healthcare-ai - automation - ehr-integration measurable_outcome: Automate routine clinical documentation, scheduling, or data entry tasks to save clinical staff time by over 50%. license: MIT metadata: author: OpenSource Healthcare AI Community version: "1.0.0" compatibility: - system: Pytho...Votes: 0GitHub stars: 32
- 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: 32
- Medsam2 3d SegmentationOperate MedSAM2 for promptable segmentation of 3D medical images and medical videos, including CT lesion propagation, MRI volumes, RECIST-guided prompts, efficient CPU-oriented variants, training, and 3D Slicer integration. Use when generating or validating volumetric masks from sparse prompts or propagating masks through image slices or video frames.Votes: 0GitHub stars: 32
- Monai Medical ImagingBuild reproducible healthcare imaging pipelines with Project MONAI for DICOM, NIfTI, pathology, and multidimensional imaging tasks including preprocessing, augmentation, training, sliding-window inference, evaluation, model bundles, labeling, and deployment. Use when implementing medical image classification, segmentation, registration, detection, generative, or foundation-model workflows in PyTorch.Votes: 0GitHub stars: 32
- 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. allowed-tools: - read_file - run_shell_command measurable_outcome: 'Deliver a ranked therapy list with OncoKB/NCCN citations plus data-gap checklist for every case within 10 minutes of receiving inputs.' ---Votes: 0GitHub stars: 32
- Prior Authorization--> --- name: 'prior-auth-coworker' description: 'Prior Auth Review' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill acts as an automated utilization management reviewer. It takes unstructured clinical notes and a procedure code, compares them against internal policy criteria (e.g., conservative therapy failure), and renders a decision.Votes: 0GitHub stars: 32
- PromiseAdProgressionSurvivalAgent Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'promise-ad-progression-survival-agent' description: 'Progression-aware multi-horizon survival agent that estimates calibrated 1/2/3/5-year risks of CN→MCI and MCI→AD conversion from irregular ADNI/TADPOLE tabular visit histories.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 32
- ProsthetixAiProstheticRecommendations Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'prosthetix-ai-prosthetic-recommendations' description: 'Guide evidence-based prosthetic recommendation workflows inspired by ProsthetiX-AI clinical decision support for limb-loss care with 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: 32
- PsychiatryKnowledgeFusedReasoning Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'psychiatry-knowledge-fused-reasoning' description: 'Psychiatry CDS workflow for knowledge-fused augmented reasoning across diagnosis, risk assessment, medication reasoning, 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: 32
- 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: author: MD BABU MIA 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 comp...Votes: 0GitHub stars: 32
- 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: 32
- 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: 32
- TestTimeKnowledgeClinicalLlm Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'test-time-knowledge-clinical-llm' description: 'Guide clinical LLM workflows that acquire and inject relevant medical knowledge at inference time to support safer decision-making without full fine-tuning.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 32
- Trial Eligibility Agent--> --- name: trial-eligibility-agent description: Parse trial protocols and patient data to produce criterion-level MET/NOT/UNKNOWN determinations with evidence and gaps for clinical trial screening tasks. allowed-tools: - read_file - run_shell_command measurable_outcome: 'Produce a MET/NOT/UNKNOWN matrix with supporting citations for ≥90% of inclusion/exclusion criteria within 5 minutes per trial request.' ---Votes: 0GitHub stars: 32
- TrialGPT--> --- name: trialgpt-matching description: Trial shortlist keywords: - retrieval - ranking - ClinicalTrials - patient-profile measurable_outcome: Produce ≥5 ranked trials (when available) with rationale + missing-data notes within 3 minutes of receiving a patient query. license: MIT metadata: version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - read_file --- Run the locally checked-out TrialGPT pipeline to retrieve, rank, and explain candidate trials fo...Votes: 0GitHub stars: 32
- Medgemma Health AiBuild and evaluate medical text and vision applications with Google MedGemma, including MedGemma 1.5 workflows for CT, MRI, whole-slide pathology, longitudinal chest X-rays, lab reports, and EHR text. Use when prototyping, fine-tuning, deploying, or validating MedGemma-based health AI under clinical data and safety controls.Votes: 0GitHub stars: 32