Research

--> --- name: scientific-manuscript description: "High-impact scientific manuscript preparation for journals like Nature, Blood, Cell. Use when writing abstracts, introductions, methods, results, discussions, or figure legends. Includes citation management, statistical reporting standards, ICMJE guidelines, and journal-specific formatting for hematology/oncology publications." license: Proprietary ---

--> --- name: 'cryoem-ai-drug-design-agent' description: 'AI-powered integration of cryo-EM structural data with generative AI and molecular dynamics for structure-based drug design targeting flexible proteins and membrane complexes.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Cryo-EM AI Drug Design Agent** integrates cryo-electron microscopy structural data with AlphaFold3, generative A...

--> --- name: codebase-investigator description: Expertly analyze large codebases to identify patterns, dependencies, and architectural flaws. keywords: - refactoring - analysis - architecture - discovery - search measurable_outcome: Map key components and data flows of a 50k+ LOC repo within 5 minutes, identifying 3+ potential improvements. license: MIT metadata: author: AI Agentic Skills Team version: "2.0.0" compatibility: - system: linux, macos allowed-tools: - list_directory - read_file ...

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->

--> --- name: leads-literature-mining description: Review Automator keywords: - literature-mining - systematic-review - meta-analysis - pubmed - evidence-synthesis measurable_outcome: Complete a systematic review screen of 100+ papers with >90% inclusion/exclusion accuracy compared to human baseline. license: CC-BY-4.0 metadata: author: Nature Communications 2025 version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - web_fetch --- A specialized LLM agent fo...

--> --- name: knowledge-synthesis description: Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively. keywords: - synthesis - deduplication - summarization - answers - reporting measurable_outcome: Produces a single coherent answer from >5 diverse sources with clear attribution and <10% duplication. allowed-tools: - read_file - run_shel...

--> --- name: biomni-research-agent description: Bio-Research Generalist license: MIT metadata: author: Stanford (Snap Lab) source: "https://github.com/snap-stanford/Biomni" version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - web_fetch - python_repl keywords: - biomni - automation - biomedical - reasoning - tools measurable_outcome: Execute complex research tasks with >95% success rate and validated tool usage. --- A general-purpose biomedical AI agent c...

--> --- name: 'pan-cancer-multiomics-agent' description: 'AI-powered pan-cancer analysis integrating genomic, transcriptomic, proteomic, and epigenomic data for cancer subtyping, driver identification, and cross-cancer pattern discovery.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Pan-Cancer Multi-Omics Agent** integrates multi-omics data across cancer types to identify shared oncogenic ...

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'oncology-consult-survival-llm' description: 'Guide zero-shot or fine-tuned LLM workflows for predicting cancer survival from initial oncology consultation documents with leakage control and cautious reporting.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: bio-machine-learning-model-validation description: Implements nested cross-validation and stratified splits for unbiased model evaluation on biomedical datasets. Prevents data leakage and overfitting in biomarker discovery. Use when validating classifiers or optimizing hyperparameters on omics data. tool_type: python primary_tool: sklearn measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---

--> --- name: 'variant-interpretation-acmg' description: 'Classifies genetic variants according to ACMG (American College of Medical Genetics) guidelines.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Variant Interpretation Skill** automates the classification of genetic variants (Pathogenic, Benign, VUS) using a rules-based engine derived from ACMG guidelines.

--> --- name: spatial-transcriptomics-agent description: Spatial analyst keywords: - spatial - h5ad - H&E - clustering - SVG measurable_outcome: For each sample, deliver ≥1 spatial domain map + SVG list + narrative interpretation within 30 minutes. license: MIT metadata: author: LiuLab version: "1.0.0" compatibility: - system: Python 3.9+ allowed-tools: - run_shell_command - read_file - web_fetch --- Run STAgent to align histology images with expression matrices, perform clustering/SVG detect...

--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'precision-grounded-variant-summarization' description: 'Summarize genetic variants with LLM assistance grounded in evidence databases, provenance, conflicts, and hallucination controls.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---

--> --- name: 'notion-research-documentation' description: 'Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Enables comprehensive research workf...

--> --- name: 'content-research-writer' description: 'Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- This skill acts as your writing partner, helpin...

--> --- 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...

--> --- 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 ---

--> --- 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...

--> --- 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 ---

--> <!-- 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 ---

--> --- 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...

--> --- name: deep-research-swarm description: Multi-agent research literature analysis keywords: - research - literature - swarm - multi-agent - hypothesis measurable_outcome: Generates comprehensive literature review with >50 citations in <5 minutes. license: MIT metadata: author: AI Agentic Skills Team version: "1.0.0" compatibility: - system: Python 3.10+ allowed-tools: - run_shell_command - read_file - google_web_search --- A coordinated swarm of agents designed to perform deep, parallel...

Maintain the Velaclaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.

Use when searching selected or accessible S3 buckets through npa studio, or discovering and loading run artifacts in the npa agent without workflow/type/path allowlists.