Explore skills

Molecular ML with diverse featurizers and pre-built datasets for property prediction (ADMET, toxicity) using traditional ML or GNNs. Ideal for quick experiments with pre-trained models, diverse molecular representations, and MoleculeNet benchmarks, offering extensive featurization options.

A multiagent AI system for scientific research assistance, automating research workflows from data analysis to publication. It supports end-to-end research pipelines, including generating research ideas, developing methodologies, executing experiments, performing literature searches, and creating publication-ready papers in LaTeX format.

Sets up deployment, analytics, and health monitoring for projects. Use when user mentions デプロイ, deploy, Vercel, Netlify, 公開, アナリティクス, analytics, GA, Google Analytics, 環境診断, health check. Do NOT load for: 実装作業, ローカル開発, レビュー, セットアップ.

Drizzle ORM patterns for PostgreSQL.

Processes incoming emails for Unite-Hub, extracting sender data, identifying communication intents, linking to CRM contacts, analyzing sentiment, and updating contact records with AI insights.

Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.

Add Sentry v8 error tracking and performance monitoring to your project services. Use this skill when adding error handling, creating new controllers, instrumenting cron jobs, or tracking database performance. ALL ERRORS MUST BE CAPTURED TO SENTRY - no exceptions.

Comprehensive knowledge about vulnerability exploitation and initial access. Provides expertise on finding and adapting exploits, adapting proof-of-concepts, gaining shells, and capturing user flags. Covers reverse shells, file uploads, SQL injection, and RCE vulnerabilities.

Safely extend or refine AFI signal schemas and closely-related validators in afi-core, while preserving determinism, respecting PoI/PoInsight design, and obeying the AFI Droid Charter and AFI Core AGENTS.md boundaries.

This skill should be used when extracting structured data from scientific PDFs for systematic reviews, meta-analyses, or database creation. Use when working with collections of research papers that need to be converted into analyzable datasets with validation metrics.

This skill enables universal dataset import for FiftyOne, supporting all media types and label formats, including multimodal grouped datasets. It's ideal for importing any dataset regardless of format, automatically detecting folder structures, and handling complex autonomous driving data.

Find duplicate or near-duplicate images in FiftyOne datasets using brain similarity computation. Use when users want to deduplicate datasets, find similar images, cluster visually similar content, or remove redundant samples. Requires FiftyOne MCP server with @voxel51/brain plugin installed.