All authors
Claude Skills by mdbabumiamssm
github.com/mdbabumiamssm1,578 skills3 installs3,530 views
- TestTimeKnowledgeClinicalLlm Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'test-time-knowledge-clinical-llm' description: 'Use test-time knowledge acquisition to retrieve, vet, inject, and cite current clinical evidence for LLM-assisted medical decision support without 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: 6
- 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: 6
- 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: 6
- Virtual Lab Agent--> --- name: 'virtual-lab-agent' description: 'AI-powered virtual laboratory orchestrating multi-agent scientific research teams for autonomous hypothesis generation, experimental design, and validation in biomedical research.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Virtual Lab Agent** orchestrates AI-powered virtual scientific research teams consisting of specialized agents (Princi...Votes: 0GitHub stars: 6
- Wearable Analysis--> --- name: wearable-analysis-agent description: 'SOTA Wearable Analysis Agent for longitudinal sensor data, aligned with OpenAI and Anthropic healthcare initiatives.' keywords: - wearable - sensor-data - health-monitoring - anomaly-detection - longitudinal-analysis measurable_outcome: 'Detects atrial fibrillation and sleep anomalies with >98% accuracy using continuous PPG and accelerometer data in real-time.' license: MIT metadata: author: Biomedical AI Team version: "2.0.0" compatibility:...Votes: 0GitHub stars: 6
- Data Visualization--> --- name: data-visualization-expert description: Generate insightful, publication-quality visualizations from complex datasets. keywords: - charts - plots - analysis - pandas - matplotlib - seaborn measurable_outcome: Create 3 high-resolution (300dpi) statistical plots (volcano, heatmap, scatter) within 15 minutes. license: MIT metadata: author: AI Agentic Skills Team version: "2.0.0" compatibility: - system: linux, macos allowed-tools: - run_shell_command - write_file - read_file --- A d...Votes: 0GitHub stars: 6
- SQL Generation Agent--> --- name: sql-generation-agent description: Generates and evaluates grounded Text-to-SQL queries using schema context, production monitoring, and constrained decoding patterns. keywords: - sql-generation - text-to-sql - data-science - schema-grounding - constrained-decoding measurable_outcome: Generate schema-grounded SQL and evaluate production Text-to-SQL outputs with documented semantic checks. license: Proprietary compatibility: - system: Python 3.10+ allowed-tools: - read_file - run_...Votes: 0GitHub stars: 6
- Circos Plots--> --- name: bio-data-visualization-circos-plots description: Create circular genome visualizations with Circos and pyCircos. Display multi-track data including ideograms, genes, variants, CNVs, and interaction arcs. Use when creating circular genome visualizations. tool_type: mixed primary_tool: Circos measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Circular genome visualizations for displaying m...Votes: 0GitHub stars: 6
- Color Palettes--> --- name: bio-data-visualization-color-palettes description: Select and apply colorblind-friendly palettes for scientific figures using viridis, RColorBrewer, and custom color schemes. Use when selecting colorblind-friendly palettes for figures. tool_type: mixed primary_tool: viridis measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Genome Browser Tracks--> --- name: bio-data-visualization-genome-browser-tracks description: Generate genome browser visualizations using pyGenomeTracks or IGV batch scripting for publication figures. Use when creating publication figures of genomic regions with multiple data tracks. tool_type: mixed primary_tool: pyGenomeTracks measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Genome Tracks--> --- name: bio-data-visualization-genome-tracks description: Create genome browser-style visualizations showing multiple data tracks (coverage, peaks, genes) using pyGenomeTracks, Gviz, and IGV. Use when visualizing genomic data at specific loci with multiple aligned tracks. tool_type: mixed primary_tool: pyGenomeTracks measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Ggplot2 Fundamentals--> --- name: bio-data-visualization-ggplot2-fundamentals description: Create publication-quality scientific figures with ggplot2 including scatter plots, boxplots, heatmaps, and multi-panel layouts. Use when creating static figures for papers, presentations, or reports in R. tool_type: r primary_tool: ggplot2 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Heatmaps Clustering--> --- name: bio-data-visualization-heatmaps-clustering description: Create clustered heatmaps with row/column annotations using ComplexHeatmap, pheatmap, and seaborn for gene expression and omics data visualization. Use when visualizing expression patterns across samples or identifying co-expressed gene clusters. tool_type: mixed primary_tool: ComplexHeatmap measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_co...Votes: 0GitHub stars: 6
- Interactive Visualization--> --- name: bio-data-visualization-interactive-visualization description: Create interactive HTML plots with plotly and bokeh for exploratory data analysis and web-based sharing of omics visualizations. Use when building zoomable, hoverable plots for data exploration or web dashboards. tool_type: mixed primary_tool: plotly measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Multipanel Figures--> --- name: bio-data-visualization-multipanel-figures description: Combine multiple plots into publication-ready multi-panel figures using patchwork, cowplot, or matplotlib GridSpec with shared legends and panel labels. Use when combining multiple plots into publication figures. tool_type: mixed primary_tool: patchwork measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Specialized Omics Plots--> --- name: bio-data-visualization-specialized-omics-plots description: Reusable plotting functions for common omics visualizations. Custom ggplot2/matplotlib implementations of volcano, MA, PCA, enrichment dotplots, boxplots, and survival curves. Use when creating volcano, MA, or enrichment plots. tool_type: mixed primary_tool: ggplot2 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Upset Plots--> --- name: bio-data-visualization-upset-plots description: Create UpSet plots to visualize set intersections as an alternative to Venn diagrams using UpSetR or upsetplot. Use when comparing overlapping gene sets, peak sets, or sample groups with more than 3 sets. tool_type: mixed primary_tool: UpSetR measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Volcano Customization--> --- name: bio-data-visualization-volcano-customization description: Create publication-ready volcano plots with custom thresholds, gene labels, and highlighting using ggplot2, EnhancedVolcano, or matplotlib. Use when visualizing differential expression or association results with gene annotations. tool_type: mixed primary_tool: ggplot2 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- AgentD Drug Discovery--> --- name: agentd-drug-discovery description: Use the AgentD workflow to mine evidence, design molecules, and rank candidates with SAR plus ADMET annotations for early drug discovery tasks. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- MAGE--> --- name: mage-antibody-generator description: Ab seq forge keywords: - antibody - antigen - FASTA - generation - validation measurable_outcome: Generate the requested number of antibody sequences (default ≥5) with metadata (model checkpoint, seed) and deliver FASTA files within 10 minutes. license: MIT metadata: author: MAGE Team version: "1.0.0" compatibility: - system: Python 3.9+ / GPU allowed-tools: - run_shell_command - read_file --- Run the MAGE antibody generation workflow to prop...Votes: 0GitHub stars: 6
- Antibody Design--> --- name: 'antibody-design-agent' description: 'An advanced agent for de novo antibody design and optimization using state-of-the-art protein language models (MAGE, RFdiffusion).' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill brings together cutting-edge tools for antibody engineering, including MAGE (Monoclonal Antibody Generator) and RFdiffusion for Antibodies. It enables the de ...Votes: 0GitHub stars: 6
- BiomedMultiAlignmentFoundationModel Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'biomed-multi-alignment-foundation-model' description: 'Use IBM biomed.omics.bl.sm.ma-ted-458m, a 458M-parameter foundation model trained on 2B+ biological samples across proteins, small molecules, and single-cell gene data, for cross-modal drug discovery tasks.' 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
- CheMatAgent--> --- name: chematagent-drug-discovery description: Chemical Lab Agent keywords: - chemistry - drug-discovery - tools - synthesis - property-prediction measurable_outcome: Plan a synthesis route and predict ADMET properties for a candidate molecule with >80% validity. license: MIT metadata: author: CheMatAgent Team version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - read_file --- A two-tiered agent system with access to 137 Python-wrapped chemical tool...Votes: 0GitHub stars: 6
- ChemCrow Tools--> --- name: 'chemcrow-drug-discovery' description: 'An LLM chemistry agent with expert-designed tools for organic synthesis, drug discovery, and materials design.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- ChemCrow is an open-source package for the accurate integration of Large Language Models (LLMs) with chemistry tools. It is designed to autonomously plan and execute chemical syntheses, r...Votes: 0GitHub stars: 6
- Chemical Property Lookup--> --- name: chemical-property-lookup description: Compute RDKit-driven molecular properties (MW, logP, TPSA, QED, Lipinski) for a SMILES string to support downstream drug discovery tools. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Admet Prediction--> --- name: bio-admet-prediction description: Predicts ADMET properties using ADMETlab 3.0 API or DeepChem models. Estimates bioavailability, CYP inhibition, hERG liability, and 119 toxicity endpoints with uncertainty quantification. Filters for PAINS and other structural alerts. Use when filtering compounds for drug-likeness or prioritizing leads by predicted safety. tool_type: python primary_tool: ADMETlab measurable_outcome: Execute skill workflow successfully with valid output within 15...Votes: 0GitHub stars: 6
- Molecular Descriptors--> --- name: bio-molecular-descriptors description: Calculates molecular descriptors and fingerprints using RDKit. Computes Morgan fingerprints (ECFP), MACCS keys, Lipinski properties, QED drug-likeness, TPSA, and 3D conformer descriptors. Use when featurizing molecules for machine learning or filtering by drug-likeness criteria. tool_type: python primary_tool: RDKit measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_...Votes: 0GitHub stars: 6
- Molecular Io--> --- name: bio-molecular-io description: Reads, writes, and converts molecular file formats (SMILES, SDF, MOL2, PDB) using RDKit and Open Babel. Handles structure parsing, canonicalization, and full standardization pipeline including sanitization, normalization, and tautomer canonicalization. Use when loading chemical libraries, converting formats, or preparing molecules for analysis. tool_type: python primary_tool: RDKit measurable_outcome: Execute skill workflow successfully with valid o...Votes: 0GitHub stars: 6
- Reaction Enumeration--> --- name: bio-reaction-enumeration description: Enumerates chemical libraries through reaction SMARTS transformations using RDKit. Generates virtual compound libraries from building blocks using defined chemical reactions with product validation. Use when creating combinatorial libraries or enumerating products from synthetic routes. tool_type: python primary_tool: RDKit measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file...Votes: 0GitHub stars: 6
- Similarity Searching--> --- name: bio-similarity-searching description: Performs molecular similarity searches using Tanimoto coefficient on fingerprints via RDKit. Finds structurally similar compounds using ECFP or MACCS keys and clusters molecules by structural similarity using Butina clustering. Use when finding analogs of a query compound or clustering chemical libraries. tool_type: python primary_tool: RDKit measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed...Votes: 0GitHub stars: 6
- Substructure Search--> --- name: bio-substructure-search description: Searches molecular libraries for substructure matches using SMARTS patterns with RDKit. Filters compounds by pharmacophore features, functional groups, or scaffold matches with atom mapping. Use when finding compounds containing specific chemical moieties or filtering libraries by structural features. tool_type: python primary_tool: RDKit measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tool...Votes: 0GitHub stars: 6
- Virtual Screening--> --- name: bio-virtual-screening description: Performs structure-based virtual screening using AutoDock Vina 1.2 for molecular docking. Prepares receptor PDBQT files, generates ligand conformers, defines binding site boxes, and ranks compounds by predicted binding affinity. Use when screening chemical libraries against a protein structure to find potential binders. tool_type: python primary_tool: vina measurable_outcome: Execute skill workflow successfully with valid output within 15 minut...Votes: 0GitHub stars: 6
- DeepsemsOceanBiosyntheticLlmAgent Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'deepsems-ocean-biosynthetic-llm-agent' description: 'Agent that applies the DeepSeMS large language model to mine biosynthetic gene clusters and secondary metabolite potential from global ocean microbiome metagenomes.' 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
- Molecular Glue Discovery Agent--> --- name: 'molecular-glue-discovery-agent' description: 'AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Molecular Glue Discovery Agent** enables AI-driven discovery of molecular glue degraders that induce prot...Votes: 0GitHub stars: 6
- Molecule Design--> --- name: 'molecule-evolution-agent' description: 'Evolve Molecules' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Molecule Evolution Agent** acts as an autonomous medicinal chemist. It takes a starting molecule (or uses a default like Aspirin) and iteratively modifies its structure to optimize binding for a specific protein target.Votes: 0GitHub stars: 6
- PROTAC Design Agent--> --- name: 'protac-design-agent' description: 'AI-powered PROTAC (Proteolysis Targeting Chimera) design for targeted protein degradation, integrating ternary complex prediction, linker optimization, and ADMET modeling.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **PROTAC Design Agent** provides AI-assisted design of Proteolysis Targeting Chimeras (PROTACs) for targeted protein degradati...Votes: 0GitHub stars: 6
- PolymerAgentLlmDesign Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'polymer-agent-llm-design' description: 'LLM-driven agent for polymer design that proposes, evaluates, and iterates candidate polymer structures against target property constraints.' 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
- Protein Structure--> --- name: 'protein-structure-prediction' description: 'Predicts 3D protein structures from amino acid sequences using ESMFold or AlphaFold3 (mock).' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Protein Structure Prediction Skill** provides an interface to state-of-the-art folding models. It takes an amino acid sequence and returns a PDB file or structure metrics (pLDDT).Votes: 0GitHub stars: 6
- TPD Ternary Complex Agent--> --- name: 'tpd-ternary-complex-agent' description: 'AI-powered ternary complex prediction for targeted protein degradation, modeling POI-degrader-E3 ligase assemblies to optimize PROTAC and molecular glue efficacy.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **TPD Ternary Complex Agent** specializes in predicting and modeling ternary complex formation for targeted protein degradation (...Votes: 0GitHub stars: 6
- ChromfoundScatacFoundationModel Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'chromfound-scatac-foundation-model' description: 'Apply ChromFound, a genome-wide foundation model for single-cell chromatin accessibility, to scATAC embedding, annotation, regulatory discovery, and validation.' 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
- Atac Peak Calling--> --- name: bio-atac-seq-atac-peak-calling description: Call accessible chromatin regions from ATAC-seq data using MACS3 with ATAC-specific parameters. Use when identifying open chromatin regions from aligned ATAC-seq BAM files, different from ChIP-seq peak calling. tool_type: cli primary_tool: macs3 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Atac Qc--> --- name: bio-atac-seq-atac-qc description: Quality control metrics for ATAC-seq data including fragment size distribution, TSS enrichment, FRiP, and library complexity. Use when assessing ATAC-seq library quality before or after peak calling to identify problematic samples. tool_type: mixed primary_tool: deeptools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Differential Accessibility--> --- name: bio-atac-seq-differential-accessibility description: Find differentially accessible chromatin regions between conditions using DiffBind or DESeq2. Use when comparing chromatin accessibility between treatment groups, cell types, or developmental stages in ATAC-seq experiments. tool_type: r primary_tool: DiffBind measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Footprinting--> --- name: bio-atac-seq-footprinting description: Detect transcription factor binding sites through footprinting analysis in ATAC-seq data using TOBIAS. Use when identifying TF occupancy patterns within accessible regions, as TF binding protects DNA from Tn5 cutting. tool_type: cli primary_tool: tobias measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Motif Deviation--> --- name: bio-atac-seq-motif-deviation description: Analyze transcription factor motif accessibility variability using chromVAR. Use when identifying which TF motifs show variable accessibility across samples or conditions in ATAC-seq data. tool_type: r primary_tool: chromVAR measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Measure per-sample variability in transcription factor motif accessibili...Votes: 0GitHub stars: 6
- Nucleosome Positioning--> --- name: bio-atac-seq-nucleosome-positioning description: Extract nucleosome positions from ATAC-seq data using NucleoATAC, ATACseqQC, and fragment analysis. Use when analyzing chromatin organization, identifying nucleosome-free regions at promoters, or characterizing nucleosome occupancy patterns from ATAC-seq fragment size distributions. tool_type: mixed primary_tool: NucleoATAC measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: ...Votes: 0GitHub stars: 6
- Chipseq Qc--> --- name: bio-chipseq-qc description: ChIP-seq quality control metrics including FRiP (Fraction of Reads in Peaks), cross-correlation analysis (NSC/RSC), library complexity, and IDR (Irreproducibility Discovery Rate) for replicate concordance. Use to assess experiment quality before downstream analysis. Use when assessing ChIP-seq data quality metrics. tool_type: mixed primary_tool: deepTools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allo...Votes: 0GitHub stars: 6
- Chipseq Visualization--> --- name: bio-chipseq-visualization description: Visualize ChIP-seq data using deepTools, Gviz, and ChIPseeker. Create heatmaps, profile plots, and genome browser tracks. Visualize signal around peaks, TSS, or custom regions. Use when visualizing ChIP-seq signal and peaks. tool_type: mixed primary_tool: deepTools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Differential Binding--> --- name: bio-chipseq-differential-binding description: Differential binding analysis using DiffBind. Compare ChIP-seq peaks between conditions with statistical rigor. Requires replicate samples. Outputs differentially bound regions with fold changes and p-values. Use when comparing ChIP-seq binding between conditions. tool_type: r primary_tool: DiffBind measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_comm...Votes: 0GitHub stars: 6
- Motif Analysis--> --- name: bio-chipseq-motif-analysis description: De novo motif discovery and known motif enrichment analysis using HOMER and MEME-ChIP. Identify transcription factor binding motifs in ChIP-seq, ATAC-seq, or other genomic peak data. Use when finding enriched DNA motifs in peak sequences. tool_type: cli primary_tool: HOMER measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Identify DNA sequence mot...Votes: 0GitHub stars: 6