productivity▌

Molfeat is a comprehensive Python library for molecular featurization that unifies 100+ pre-trained embeddings and hand-crafted featurizers. Convert chemical structures (SMILES strings or RDKit molecules) into numerical representations for machine learning tasks including QSAR modeling, virtual screening, similarity searching, and deep learning applications. Features fast parallel processing, scikit-learn compatible transformers, and built-in caching.

Use this skill when the user needs rendered visuals, not text diagrams: ERDs, UI mockups, architecture illustrations, slide-ready images, or image edits using Nano Banana Pro.

Accept Apple Pay payments for physical goods and services, and add passes to the user's Wallet. Covers payment buttons, payment requests, authorization, Wallet passes, and merchant configuration. Targets Swift 6.2 / iOS 26+.

$22

Schema validation best practices for TypeScript with 43 prioritized rules across type safety, parsing, and error handling. \n \n Covers 8 rule categories from schema definition and parsing (CRITICAL) through type inference, error handling, and performance (LOW-MEDIUM) \n Distinguishes safeParse() for user input, parseAsync() for async refinements, and parse() for trusted data; emphasizes validation at system boundaries \n Provides guidance on z.infer for type inference, z.unknown() over z.any(),

Convert documents to high-quality markdown with intelligent multi-tool orchestration.

View, manage, and troubleshoot Railway deployments with logs, redeploy, and removal commands. \n \n List deployments and view deploy or build logs with filtering by level, text search, time range, or specific deployment ID \n Redeploy the most recent deployment or restart containers without rebuilding to pick up external resource changes \n Remove deployments (stops the service but keeps it intact; use the environment skill to delete services entirely) \n Supports JSON output for all commands an

On-device LLM integration for iOS 18+ using Apple's FoundationModels framework with privacy-first text generation and structured output. \n \n Covers text generation, structured output via @Generable macro, custom tool calling, and snapshot streaming—all running locally without cloud dependency \n Requires availability checks before session creation; supports single-turn and multi-turn conversations with optional system instructions \n Guided generation with @Guide constraints (numeric ranges, a

Proactive code review tool that analyzes git diffs and conversation history to catch implementation issues. \n \n Runs via CLI with support for OpenCode, Codex, and Claude Code session history integration \n Analyzes full git diffs against a base commit and cross-references conversation context to identify misalignments between requested and implemented changes \n Configurable confidence thresholds, multiple output formats (text, JSON, GitHub), and support for custom or community-defined LLM mod

AI-driven engineering workflows with eval-first execution, task decomposition, and cost-aware model routing. \n \n Defines an eval-first loop: establish baseline evals before implementation, then re-run post-execution to measure deltas and catch regressions \n Decomposes work into 15-minute units with single dominant risks, independent verifiability, and clear done conditions \n Routes tasks by complexity: Haiku for classification and boilerplate, Sonnet for implementation, Opus for architecture