MCP App StoreMCP App Store
from claude-code-templates29,459
Provides guidance and workflows for RWKV, a Transformer+RNN hybrid that enables linear-time inference and effectively unlimited context for long-sequence and st
Detailed instructions and workflows for using RWKV (Receptance Weighted Key Value), a hybrid model that trains like a Transformer but infers like an RNN, offering O(1) memory per token and effectively infinite context. Includes installation steps, example code for GPT and RNN modes, workflows for text generation, long-context processing, fine-tuning, and comparisons versus standard Transformers.
Use this skill when you need to: process very long documents or streaming data with constant memory, build memory-efficient inference pipelines, fine-tune RWKV models, or compare RWKV versus Transformer approaches for large-context tasks. Ideal for research, production inference optimization, and low-memory deployments.
Best used by code-capable agents (Claude Code, Copilot/Codex-style agents, or any agent that can run Python snippets and manage environment setup).
This skill has not been reviewed by our automated audit pipeline yet.
Scientific Schematics & Diagrams
Generate publication-quality scientific diagrams via AI with iterative quality review and smart regeneration for journal, conference, poster, and presentation o
Writing Hookify Rules
Guides creating Hookify rule files (.claude/hookify.*.local.md) to detect patterns (dangerous commands, secrets, debug logs) and show warnings or block actions.
BRENDA Database Client
Access the BRENDA enzyme database via SOAP API to retrieve kinetic parameters, reactions, organism data, and substrate-specific enzyme information.
Hook Development for Claude Code Plugins
Guidance and patterns for creating event-driven hooks (PreToolUse, PostToolUse, Stop, SessionStart, etc.) for Claude Code plugins and projects.
ChEMBL Database Explorer
Query ChEMBL programmatically to retrieve bioactive molecule data, bioactivity measurements, targets, and perform similarity/substructure searches for drug disc
Coding Standards & Best Practices
Opinionated, language-agnostic coding standards and best practices focused on TypeScript/JavaScript/React to improve readability, safety, and maintainability.
React State Management
Practical guide to choosing and implementing modern React state solutions (Redux Toolkit, Zustand, Jotai, React Query) for local, global, and server state.
Game Design Principles
Practical game design guidance: core loop, GDD structure, player psychology, balancing, and progression patterns for prototyping and documenting games.
Zapier & Make Patterns
Guidance and patterns for building reliable no-code automations in Zapier and Make, with anti-patterns and failure modes to avoid.
LangGraph
Guides building production-grade, stateful agent graphs with LangGraph: state, reducers, routing, persistence, and human-in-the-loop patterns for robust multi-n
Microsoft Foundry Classic — Expert Guidance
Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.
Paper Writing Pipeline
Orchestrates a complete pipeline to go from a research narrative to a polished LaTeX PDF, including planning, figure generation, LaTeX writing, compilation and
TRL Training on Hugging Face Jobs
Train and fine-tune language models on Hugging Face Jobs using TRL (SFT, DPO, GRPO) with Trackio monitoring and automated Hub push. Includes scripts, cost estim
Paper Claim Audit
Zero-context auditor that verifies every numeric claim in a paper against raw result files to catch rounding, cherry-picks, and config mismatches.
Forward-Looking Training Examples (GRPO)
Worked examples and pipelines for generating forward-looking (GRPO) binary forecasting datasets: seeds → question generation → labeling → lint → split → train.
Nemotron 3 Nano Reference
Authoritative knowledge-base for Nemotron 3 Nano: architecture, training data, SFT/RL recipes, evaluation and deployment guidance.
Graphsignal GPU Profiler
Set up and manage GPU profiling, tracing, and monitoring for AI inference workloads using vLLM, SGLang, and PyTorch.