Claude Skills by luokai0

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Provides trading strategies for cryptocurrencies based on Binance market data, calculated technical analysis indicators, and aggregated market sentiment from crypto RSS news feeds. Use when users ask for trading advice, strategy recommendations, or analysis combining price data, TA, and sentiment for crypto assets like ETH, BTC, or altcoins.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

TypeScript strict mode with eslint and jest

Mobile UI patterns - React Native, iOS/Android, touch targets

Visual testing - catch invisible buttons, broken layouts, contrast

Web UI - glassmorphism, Tailwind, dark mode, accessibility

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

User experience flows - journey mapping, UX validation, error recovery

Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or ...

Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Web and news search powered by Brave Search. Use this skill when users want to search the web, find news articles, or look up current information. Pay-per-call via Vincent credit system. Triggers on "search the web", "web search", "brave search", "search news", "find information", "look up", "current events".

Secure credential management for agents. Use this skill when users need to store API keys, passwords, OAuth tokens, or SSH keys and write them to .env files without exposing values. Triggers on "store credentials", "API key", "manage secrets", "write to env", ".env file", "credential", "password", "token storage".

Use this skill to create a HyperLiquid perpetuals and spot wallet for your agent. Trade perps, manage spot balances, transfer USDC between sub-accounts, get prices, place orders — all without exposing private keys.

Strategy-driven automated trading for Polymarket and HyperLiquid. Use this skill when users want to create trading strategies, set stop-loss/take-profit/trailing stop rules, or manage automated trading. Triggers on "trading strategy", "stop loss", "take profit", "trailing stop", "automated trading", "trading engine", "trade rules", "strategy monitor".

Twitter/X.com data access for agents. Use this skill when users want to search tweets, look up user profiles, or retrieve recent tweets. Pay-per-call via Vincent credit system. Triggers on "search tweets", "twitter", "X.com", "look up user", "tweet search", "twitter profile", "recent tweets".

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

The agent's wallet for EVM chain transactions and raw signing. Use this skill when users want to create a wallet, transfer tokens, swap on DEXs, interact with smart contracts, or sign messages. Triggers on "wallet", "create wallet", "transfer ETH", "swap tokens", "send transaction", "check balance", "EVM wallet", "raw signer", "sign message".

SEO and AI discovery (GEO) - schema, ChatGPT/Perplexity optimization

Stripe Checkout, subscriptions, webhooks, customer portal

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Expert guidance on contributing to WendyOS: Yocto builds, agent internals, E2E testing, and system architecture. Use when developers mention: (1) building WendyOS images, (2) meta-wendyos layers or bitbake, (3) wendy-agent development or internals, (4) containerd or nerdctl on WendyOS, (5) E2E tests for wendy-agent, (6) Yocto recipes or bbappend files, (7) mDNS/Avahi service configuration, (8) device identity or UUID generation.

Expert guidance on building WASM apps for Wendy Lite MCU firmware on ESP32-C6. Use when developers mention: (1) Wendy Lite or wendy-lite, (2) WASM apps on ESP32 or microcontrollers, (3) WendyLite Swift package or import WendyLite, (4) building C/Rust/Swift/Zig apps for ESP32, (5) WAMR runtime on embedded devices, (6) GPIO/I2C/SPI/UART/NeoPixel from WASM, (7) Embedded Swift on WASM or wasm32-none-none-wasm, (8) BLE provisioning on ESP32-C6, (9) uploading WASM binaries to MCU, (10) TLS/networki...

Expert guidance on building and deploying apps to WendyOS edge devices. Use when developers mention: (1) Wendy or WendyOS, (2) wendy CLI commands, (3) wendy.json or entitlements, (4) deploying apps to edge devices, (5) remote debugging Swift on ARM64, (6) NVIDIA Jetson or Raspberry Pi apps, (7) cross-compiling Swift for ARM64.

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, want...

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.

WooCommerce REST API - products, orders, customers, webhooks

Dynamic multi-repo and monorepo awareness for Claude Code. Analyze workspace topology, track API contracts, and maintain cross-repo context.

Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.

Use this skill to create high-quality academic papers, literature reviews, grant proposals, clinical reports, and other research and scientific documents backed by comprehensive research and real, verifiable citations. Use this skill whenever the user asks for written output such as a report, paper...etc.

Comprehensive tool for finding and analyzing DeFi yield opportunities across protocols, chains, and asset types. Use when users want to earn yield on crypto assets (staking, lending, liquidity farming, aggregators). Supports exhaustive parallel research using librarian agents, direct web searches, and GitHub repository analysis.

Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/recency filtering - Reader: web page to markdown extraction - Repo: GitHub code search and reading via ZRead - Tools: MCP tool discovery and raw calls - Code: TypeScript tool chaining Use for visual content analysis, web search, page reading, or GitHub exploration. Requires Z_AI_API_KEY.

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

When the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions 'solo founder,' 'one-person startup,' 'solopreneur,' 'bootstrapped,' 'no team,' 'AI agents as team,' 'scaling without hiring,' 'founder-led sales,' 'lean GTM,' 'one-person company,' or 'no employees.' This skill covers the complete solo founder GTM playbook from stack selection through agent team design, revenue-stage t...

Launch and scale startups from zero. Covers idea validation, MVP scoping, market sizing, go-to-market, and fundraising strategy.

A hypothesis is a testable prediction about how a change will affect user behavior or business outcomes. It transforms assumptions into explicit statements that can be validated or invalidated through experimentation. Well-formed hypotheses prevent teams from building features based on untested beliefs and create shared understanding of what success looks like.

A Jobs to be Done (JTBD) canvas captures the complete picture of why customers "hire" products to make progress in their lives. Based on Clayton Christensen's framework, JTBD goes beyond features and demographics to understand the underlying motivations—functional, emotional, and social—that drive customer behavior.

An Opportunity Solution Tree (OST) is a visual framework for product discovery that connects business outcomes to customer opportunities and potential solutions. Developed by Teresa Torres, it prevents the common trap of jumping straight to solutions by ensuring every feature idea traces back to a customer need and measurable outcome.

A problem statement is a concise document that frames the problem you're solving, articulates the impact on users and the business, and defines clear success criteria. It serves as the foundation for all subsequent product work by ensuring alignment on *what* problem to solve before jumping to *how* to solve it.