All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Wattlytics Hpc OptimizationWattlytics: Co-Optimizing Performance, Energy, and TCO in HPC Clusters. Use for holistic what-if analysis across hardware-software stack for HPC planning and operation. Activation: HPC optimization, performance energy trade-off, TCO analysis, cluster configuration optimization.Votes: 0GitHub stars: 3
- Wrpn Training And Inference Using Wide Reducedprecision Networks**arXiv ID:** 1704.03079 **Authors:** Asit Mishra, Jeffrey J Cook, Eriko Nurvitadhi, Debbie Marr **Published:** 2017-04-10T22:54:38Z **Abstract:** For computer vision applications, prior works have shown the efficacy of reducing the numeric precision of model parameters (network weights) in deep neural networks but also that reducing the precision of activations hurts model accuracy much more than reducing the precision of model parameters. We study schemes to train networks from scratch usin...Votes: 0GitHub stars: 3
- Description Length Genetic ProgrammingDescription Length (DL) and Fractional Bayes Factor (FBF) model selection methodology for genetic programming and symbolic regression. Evaluates DL/FBF as principled alternatives to AIC/BIC for selecting compact, generalizable expressions. Use when working with symbolic regression, genetic programming model selection, Fisher-information-based complexity penalties, or preventing structural bloat in evolved expressions.Votes: 0GitHub stars: 3
- Designing Agents To Resist Prompt InjectionMethodology for defending AI agents against prompt injection using constraint-based response limiting and defense in depth. Based on OpenAI's agent security approach achieving 42% reduction in injection attempts. Use when building secure agent systems, preventing social engineering attacks, or implementing prompt validation.Votes: 0GitHub stars: 3
- Detecting Reducing Scheming AiEvaluation methodology for detecting hidden misalignment ("scheming") in AI models and concrete methods for reducing deceptive behavior.Votes: 0GitHub stars: 3
- Deterministic Cat State GenerationDeterministic generation of large cat states (100+ photons) using dynamical invariants of hybrid qubit-bosonic systems under time-dependent Hamiltonians. Universal quantum control theory for quantum metrology and fault-tolerant computation. arXiv:2606.03293.Votes: 0GitHub stars: 3
- Deterministic Retrieval Agent ReliabilityMethodology from Anthropic's "Paving the way for agents in biology" (Jun 2026). Use when building LLM agents that must query structured scientific/enterprise databases reliably. Core pattern: wrap unreliable LLM API guessing behind a deterministic retrieval layer (exemplified by the gget virus tool for NCBI Virus) to lift accuracy from ~50% to ~100%. Also covers the "click tax" cost model and designing agent-friendly databases.Votes: 0GitHub stars: 3
- Developmental Minimal Neural CircuitsDevelopmental neural circuit generation methodology from gene regulatory rules. Simulates cortical neurogenesis from single stem cell to generate domain-general topological substrates amenable to rapid learning. Use when studying developmental priors for neural network initialization, structural bias in neural architecture, or bio-inspired network topology generation.Votes: 0GitHub stars: 3
- Dfs Quantum Reservoir NetworksQuantum reservoir computing using decoherence-free subspaces (DFS) for room-temperature quantum AI. Classifies entangled vs product states without cooling. Activation: quantum reservoir, decoherence-free subspace, DFS, room temperature quantum, quantum classifier.Votes: 0GitHub stars: 3
- Dgcl Brain Network ConstructionDGCL Brain Network ConstructionVotes: 0GitHub stars: 3
- Dgn Dynamic Gated NeuronDynamic Gated Neuron (DGN) — brain-inspired gating mechanism for robust spiking neural networks. Dynamic conductance acts as biologically plausible gating for selective input filtering and adaptive noise suppression. Use when designing robust SNNs, implementing noise-resilient spike-based computation, or building biologically realistic neuron models with enhanced stochastic stability.Votes: 0GitHub stars: 3
- Diagonal Ano QnnDiagonal Adaptive Non-local Observables (ANO) methodology for quantum neural networks — reduces observable parameter complexity from O(4^k) to O(2^k) while retaining full ANO expressivity via diagonal canonical representatives. For efficient VQA measurement design.Votes: 0GitHub stars: 3
- Dicke State Ansatz VqeFeasibility-preserving mixed Dicke state ansatz for encoding equality and inequality constraints in variational quantum eigensolvers. Eliminates penalty terms by structurally encoding Hamming weight constraints into quantum circuits. Use when: (1) solving constrained combinatorial optimization with VQE/QAOA, (2) designing constraint-preserving ansatze, (3) eliminating penalty-based Lagrange multiplier tuning, (4) encoding equality/inequality constraints directly into quantum circuit structure...Votes: 0GitHub stars: 3
- Dicke State Portfolio QaoaFeasibility-preserving mixed Dicke state ansatz for Hamming weight constrained combinatorial optimization via variational quantum eigensolver (VQE). Eliminates penalty terms by structurally encoding equality and inequality constraints. Use when: building quantum circuits for portfolio optimization, constraint-preserving quantum algorithms, penalty-free QAOA, VQE for combinatorial finance.Votes: 0GitHub stars: 3
- Differentiable Biophysical Simulation NeurostimulationDifferentiable biophysical simulation framework for inferring Hodgkin-Huxley parameters from extracellular MEA data. Enables rapid biophysical inference and precise neurostimulation prediction without invasive intracellular recordings.Votes: 0GitHub stars: 3
- Differentiable Spin State Engineering MrsDifferentiable physical framework for goal-driven spin-state engineering in Magnetic Resonance Spectroscopy (MRS). Use when: designing MRS pulse sequences via automatic differentiation, navigating high-dimensional spin dynamics, engineering complex quantum spin states, improving neuroimaging spectral resolution, or overcoming traditional heuristic pulse design limitations.Votes: 0GitHub stars: 3
- Diffusing Blame Dale Principle Credit AssignmentError Diffusion (ED) methodology for biologically plausible credit assignment under Dale's principle. Dual-stream excitatory/inhibitory architecture with modulo error routing. Achieves 96.7% MNIST and 61.7% CIFAR-10 under strict Dale's constraint. Integrates with PPO for RL. Trigger words: Dale's principle, error diffusion, excitatory-inhibitory, biologically plausible learning, credit assignment, dual-stream network.Votes: 0GitHub stars: 3
- Diffusion Scores Neural CircuitInferring active neural circuits from neural activity data using diffusion scores methodology. Identifies functionally connected neural populations through diffusive signal propagation patterns. Activation: diffusion scores, neural circuit inference, active circuit detection, functional connectivity inference, neural population analysis.Votes: 0GitHub stars: 3
- Digital Quantum Reservoir ComputingDigital quantum reservoir computing (QRC) framework for time series forecasting on near-term quantum devices. Uses parametrized four-qubit reservoirs with partial measurement and reset, encoding temporal data in rotation angles. Training restricted to classical Ridge-regression readout. Use when: quantum reservoir computing, time series forecasting, near-term quantum devices, ATM cash demand prediction, quantum ML for financial data.Votes: 0GitHub stars: 3
- Digital Twin Error Propagation MdpOptimal sequential decision-making for error propagation mitigation in modular digital twins using MDP/POMDP framework. Combines HMM-based latent regime inference with MDP/POMDP intervention selection. Features: data-driven transition model, Point-Based Value Iteration, Value of Information quantification, Gillespie simulation validation. Use for: digital twin maintenance optimization, modular system error propagation, surrogate model degradation, sequential decision under uncertainty in CPS.Votes: 0GitHub stars: 3
- Dina V1 Population Activity InterpretationDINA (Dual-Tower Image-Neural Alignment) framework for interpretable contrastive analysis of V1 population activity. Aligns visual stimuli and V1 responses in shared latent space at intermediate feature map level. Activation: DINA, V1 population activity, image-neural alignment, contrastive framework, calcium imaging decoding, visual computation.Votes: 0GitHub stars: 3
- Diophantine Quantum OracleReversible quantum oracle construction for solving bounded Diophantine systems via amplitude amplification. Use when designing quantum algorithms for integer optimization, constraint satisfaction over bounded domains, or synthesizing arithmetic circuits for quantum oracles.Votes: 0GitHub stars: 3
- Direct Neural Assemblies Causal LearningDIRECT (DIRectional Edge Coupling/Training) methodology for causal learning with neural assemblies using local plasticity. Enables neural assemblies to internalize causal directionality without backpropagation. Activation triggers: neural assemblies, causal learning, directional learning, local plasticity, DIRECT mechanism, synaptic asymmetry, explainable causality.Votes: 0GitHub stars: 3
- Direct To Event Snn TransferDirect-to-Event (D2E) Spiking Neural Network Transfer methodology. Converts direct-coded SNNs trained with floating-point inputs into energy-efficient event-based representations using Self-Knowledge Distillation (SKD). Activation: SNN transfer, direct-to-event, D2E, event-based SNN, neuromorphic deployment, TTFS, self-knowledge distillation, SNN energy efficiency.Votes: 0GitHub stars: 3
- Directional Coordination Hierarchy BrainDirectional coordination hierarchy in large-scale brain dynamics — identifies three recurrent resting-state coordination regimes (feedback-dominated, feedforward-dominated, integrative), shows this framework is disrupted in schizophrenia, and links directional functional dynamics to symptom severity and cognition.Votes: 0GitHub stars: 3
- Disaggregate Secure Aggregation FlDisAgg protocol for efficient secure aggregation in federated learning using distributed aggregator committees, eliminating homomorphic encryption overhead while preserving privacy.Votes: 0GitHub stars: 3
- Discounted Mpc ControlModel Predictive Control (MPC) stability and suboptimality analysis under plant-model mismatch with discounting. Provides theoretical guarantees for infinite-horizon optimal control when using surrogate models. Use when designing robust control systems, analyzing MPC stability, or dealing with model uncertainty in control applications.Votes: 0GitHub stars: 3
- Discounted Mpc Robust ControlDiscounted Model Predictive Control (MPC) and infinite-horizon optimal control under plant-model mismatch. Unified framework for stability and suboptimality analysis with robustness guarantees. Use for: robust MPC, plant-model mismatch handling, discounted optimal control, stability analysis, surrogate model control. Activation: discounted MPC, plant-model mismatch, robust MPC, infinite-horizon control, suboptimality analysis.Votes: 0GitHub stars: 3
- Discounted Mpc RobustnessRobustness analysis for MPC and infinite-horizon optimal control under plant-model mismatch with quadratic costs. Covers discounted and undiscounted scenarios, stability guarantees, and suboptimality bounds. Use when: (1) MPC robustness analysis, (2) plant-model mismatch effects, (3) discounted infinite-horizon control, (4) model uncertainty in optimal control, (5) stability under model errors, (6) data-driven surrogate models.Votes: 0GitHub stars: 3
- Discovering Cryptographic Weaknesses ClaudeDiscovering cryptographic weaknesses using Claude AI.Votes: 0GitHub stars: 3
- Discovery By Dreaming Cross Domain RecombinationA skill for implementing cross-domain recombination inspired by dreaming, based on the paper \"Discovery by Dreaming: Cross-Domain Recombination in Artificial Memory\" (arXiv:2607.16256). This skill outlines how to implement a LoRA fine-tuning pipeline (DREAMS) and a symbolic engine (SAPIENCE) to recombine knowledge across domains, enhancing AI discovery and insight generation.Votes: 0GitHub stars: 3
- Discrete Heat Kernels SimplicialDiscrete Heat Kernels on Simplicial Complexes and Its Application to Functional Brain Networks. Unified framework for heat kernel smoothing on simplicial complexes extending classical signal processing methods to higher-order network structures.Votes: 0GitHub stars: 3
- Discrete Signaling Chaotic Regularization RnnDiscrete signaling mediates chaotic regularization in recurrent neural networks - theoretical framework linking microscopic chaos to macroscopic geometry of neural representations. Activation: chaotic regularization, discrete signaling, RNN chaos, neural representation manifold, power-law spectrum, cortical chaos.Votes: 0GitHub stars: 3
- Discrete Signaling Chaotic Regularization离散信号介导混沌正则化方法论。连接循环网络的微观混沌与神经表征的宏观几何，解释混沌网络如何维持平滑可微的群体编码。使用核方法+动态平均场理论，展示混沌诱导局部粗糙性但保持全局平滑性，产生幂律谱特征。适用于混沌SNN稳定性分析、神经表征几何、皮质记录谱分析。触发词：混沌网络、chaotic dynamics、neural representation、regularization、kernel method、mean-field theory、power-law spectrumVotes: 0GitHub stars: 3
- Dissipative Quantum ChaosDissipative quantum chaos methodology — extending Hamiltonian quantum chaos to open quantum dynamics via Lindbladian spectral analysis. Use when analyzing chaoticity of open quantum systems, distinguishing integrable from chaotic dynamics, or studying driven-dissipative quantum systems.Votes: 0GitHub stars: 3
- Distributed Hierarchical Temporal Memory DhtmDistributed Hierarchical Temporal Memory (D-HTM) neuromorphic framework enabling cross-entity preemptive warning via Shared Associative Memory (SAM) — extends HTM beyond reactive detection to distributed predictive reasoning (arXiv: 2606.31789)Votes: 0GitHub stars: 3
- Distributed Iqft CommunicationCommunication-efficient distributed Inverse Quantum Fourier Transform (iQFT) using communication horizon pruning to reduce inter-node quantum communication from O(P^2) to O(P). Use when: distributed quantum computing, iQFT across quantum networks, quantum communication optimization, distributed Shor algorithm, scalable QFT implementation, or quantum network resource allocation.Votes: 0GitHub stars: 3
- Distributed Optimization Control Vpp分布式优化控制架构用于逆变器接口虚拟电厂的大信号稳定性分析方法论。结合优化理论、控制理论、分布式系统设计，实现DER（分布式能源资源）的二次控制。Activation: distributed control, virtual power plant, VPP, inverter control, DER control, optimization-based control, large-signal stability.Votes: 0GitHub stars: 3
- Distributed Quantum Compiler SchedulingCompiler techniques for scheduling and optimizing distributed quantum computers (DQCs). Covers teleportation-aware scheduling, utility-driven lookahead scheduling, EPR-capacity-aware early scheduling, frequency allocation and transpilation co-design, and code surgery synthesis for stabilizer codes. Use when: designing DQC compilers, optimizing quantum circuit scheduling across multi-chip systems, minimizing teleportation overhead, implementing lookahead-aware quantum compilation, scheduling c...Votes: 0GitHub stars: 3
- Distributed Quantum ComputingDistributed Quantum Computing architecture and patterns. Apply when designing multi-QPU systems, quantum communication protocols, or scaling quantum computing beyond single device limitations.Votes: 0GitHub stars: 3
- Distributed Quantum Control Systems系统工程学 + 量子计算融合模式。涵盖分布式量子计算架构、量子控制理论（H∞控制、反馈控制）、量子系统工程方法论。Activation: 分布式量子控制, quantum control systems, distributed quantum computing engineering, quantum systems engineering.Votes: 0GitHub stars: 3
- Distributed Quantum Error CorrectionDesign and analyze distributed quantum error correction (QEC) systems using bivariate bicycle (BB) codes in modular quantum computing architectures. Covers qLDPC code partitioning across multiple processors, star network topology for inter-processor connectivity, BP+OSD decoding, and fault tolerance threshold analysis under circuit-level noise. Use when: designing modular quantum computers, implementing distributed QEC, partitioning qLDPC codes across processors, analyzing inter-processor ent...Votes: 0GitHub stars: 3
- Distributed System Resiliency[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]Votes: 0GitHub stars: 3
- Distributed Variational Quantum OptimizationQESTO distributed variational quantum optimization methodology using entanglement-selective transport for graph-based discrete optimization. Requires only persistent pre-shared Bell pairs for remote operations, no non-local gates after initialization. Use when: distributed quantum optimization, variational quantum algorithms, QAOA alternatives, Bell pair communication, entanglement transport, graph optimization, Wang tiling problems.Votes: 0GitHub stars: 3
- Distribution Based Brain ConnectivityDistribution-valued brain connectivity analysis using vector quantiles instead of scalar edge weights. Based on Mhanna, Achard, Petersen (2026, HAL). Use when building brain connectivity graphs from fMRI/EEG, improving connectome classification, or representing higher-order connectivity statistics. Activation: distribution-valued brain connectivity, graph brain representation, fMRI connectome classification, voxel clustering, brain network edges, vector quantile connectivity.Votes: 0GitHub stars: 3
- Distributionally Robust ControlDesign and analyze distributionally robust control systems under uncertainty with incomplete distribution information. Covers Sinkhorn ambiguity sets, convexity analysis, weak compactness, tractability guarantees, and MPC approaches. Use when designing controllers for systems with uncertain probability distributions, implementing robust MPC, or analyzing worst-case performance under distributional ambiguity.Votes: 0GitHub stars: 3
- Dmd High Frequency Eeg Brain Disorder DetectionDetecting high-frequency brain disorder signals using Dynamic Mode Decomposition (DMD) from EEG data. Extracts consistent dynamical changes in high-frequency bands to identify neurological patterns distinguishing clinical groups like alcohol-dependent patients from controls.Votes: 0GitHub stars: 3
- Do Hopfield Networks DreamStatistical-mechanical theory of dreaming in memories.Votes: 0GitHub stars: 3
- DockerDocker container management skill. Build, run, manage containers, images, networks, and volumes. Use for containerization, Docker Compose, multi-container apps, and DevOps tasks.Votes: 0GitHub stars: 3
- Dockerize Node Pnpm MonorepoDockerize Node.js pnpm workspace monorepos with native modules, multi-process runtime, and selective package builds. Triggers when containerizing Next.js/Express monorepos, writing Dockerfiles for pnpm workspaces, or handling better-sqlite3 native compilation in containers.Votes: 0GitHub stars: 3