All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Astrocyte 3body PlasticityAstrocyte-centric 3-body plasticity framework — how astrocytes participate in synaptic credit assignment alongside pre- and postsynaptic neurons. Proposes astrocytes as slow modulatory agents that bridge Hebbian millisecond-timescale plasticity with memory consolidation over seconds-to-minutes. Use when: modeling tripartite synapse learning rules, synaptic credit assignment, neuro-glial co-computation, biologically plausible learning in SNNs.Votes: 0GitHub stars: 3
- Asymmetric Nonlinear Return ExtrapolationAsymmetric nonlinear return extrapolation framework for optimal portfolio choice under stochastic volatility. Extends return extrapolation with saturation in belief updating and gain/loss asymmetry. Use when: behavioral portfolio optimization, return extrapolation, asymmetric belief updating, CRRA investor, stochastic volatility portfolio, Heston model portfolio.Votes: 0GitHub stars: 3
- Async Delta Modulator BmiAsynchronous Delta Modulation (ADM) for Brain-Machine Interface (BMI) applications. Converts continuous neural signals into event-driven spike trains using adaptive delta modulation, enabling ultra-low-power, low-latency neural encoding for implantable and wearable BCI systems. Covers adaptive threshold mechanism, event-driven architecture, implementation patterns, and common pitfalls.Votes: 0GitHub stars: 3
- Asynchronous Quantum Distributed ComputingAsynchronous quantum distributed computing - implementing global quantum operations in distributed systems. Combines classical distributed algorithms (Chandy-Lamport) with quantum computing principles. Activation: quantum distributed, quantum snapshot, quantum causality, QGO algorithm.Votes: 0GitHub stars: 3
- Atlas Free Brain Network TransformerAtlas-free Brain Network Transformer using individualized functional brain network (iFBN) framework. Constructs subject-specific brain networks via spatial ICA components as nodes and functional connectivity as edges. Eliminates atlas dependency. Activation: atlas-free brain network, iFBN, brain network transformer, individualized brain network, spatial ICA brain network, parcellation-free brain network, fMRI transformer.Votes: 0GitHub stars: 3
- Atoms Of Thought Eeg MicrostatesUniversal EEG representation learning using microstate tokenizers. Builds a discrete microstate tokenizer from large-scale EEG datasets by clustering continuous signals into sequences of quasi-stable brain activity patterns. Outperforms traditional time/frequency features across sleep staging, emotion recognition, and motor imagery. Applicable to EEG representation, BCI, sleep staging, emotion recognition, neuroinformatics. Activation: EEG microstates, universal EEG tokenizer, microstate clus...Votes: 0GitHub stars: 3
- Atp Hysteresis Tripartite SynapseATP滞后现象三方突触建模方法论。星形胶质细胞释放ATP累积为腺苷，通过A1受体产生滞后反馈抑制。适用于神经胶质相互作用、突触可塑性、三方突触建模。触发词：ATP滞后、三方突触、星形胶质细胞、腺苷、突触可塑性、tripartite synapse、astrocyte、adenosine。Votes: 0GitHub stars: 3
- Attention Task Structure Cognitive FlexibilityAttention to task structure for cognitive flexibility — neural mechanisms enabling flexible switching between task rules. Demonstrates how attentional mechanisms gate task-relevant information for cognitive control. Applicable to cognitive neuroscience, neural network design, cognitive flexibility, attention mechanisms. 触发词: cognitive flexibility, attention to structure, task switching, cognitive control, attentional gatingVotes: 0GitHub stars: 3
- Attractor Metadynamics Neural神经网络吸引子元动力学方法论。研究慢适应过程如何塑造吸引子景观演化。适用于神经动力学、连续学习。触发词：吸引子、元动力学、神经动力学、attractor、metadynamics。Votes: 0GitHub stars: 3
- Aurooft Quantized Orthogonal FinetuningAuroOFT framework for expressive quantized orthogonal fine-tuning that extends QOFT with zero-start gated low-rank nonlinear residuals. Enables parameter-efficient adaptation of low-bit language models while maintaining quantization compatibility and orthogonality stability. Use when: fine-tuning quantized models, needing nonlinear corrections beyond linear rotations, or optimizing parameter efficiency in low-bit LLM adaptation.Votes: 0GitHub stars: 3
- Aurosft Adapter State Multi Task FinetuningAuroSFT framework for parameter-efficient multi-task fine-tuning using adapter-state rollback instead of full-model checkpoints. Enables compact, mergeable adapter states for overfitting-aware multi-task SFT with frozen backbones and low-rank weight factors. Use when: implementing efficient multi-task fine-tuning, reducing storage costs for checkpoint management, or needing task-wise rollback capabilities in SFT pipelines.Votes: 0GitHub stars: 3
- Auto Dsm Evaluation FrameworkBlack-box evaluation framework for assessing LLM-generated Design Structure Matrices (DSMs) from structured technical documentation. Integrates structural metrics (Completeness, Correctness, Coupling Density), classification metrics (Selective Accuracy, Abstention Coverage), and stability measures (Entropy, Fleiss' κ) into a Composite Quality Score (Q). Provides transparent benchmarking methodology for auditing Auto-DSM pipelines in MBSE workflows.Votes: 0GitHub stars: 3
- Autocog Automated Cognitive ScientistPaper analysis: AutoCog — an automated LLM-driven system for discovering cognitive theories. The system takes existing theories as seeds, generates novel hypotheses, tests them against data, and produces executable cognitive models. Validated with human participants showing superior performance over established theories. Source: arXiv:2606.26693 (q-bio.NC, cs.AI), 2026-06-24. Activation keywords: AutoCog, automated theory discovery, cognitive science, LLM-driven science, computational cogniti...Votes: 0GitHub stars: 3
- Automated Domain Model Extraction LlmExtract domain models from code using LLMs and heuristics.Votes: 0GitHub stars: 3
- Automated Neural Characterization LanguageAutomated neural characterization using natural language and digital twins. Closed-loop framework that translates neuron activation patterns into concise semantic descriptions, generates hypothesis images, and verifies them in silico. Use when studying: neural selectivity characterization, digital twin neuroscience, semantic hypothesis testing, V1/V4 visual cortex encoding, generative models for neural decoding, or combining language models with neural data. arXiv: 2605.12485 (q-bio.NC, q-bio...Votes: 0GitHub stars: 3
- Automated Research Validation WorkflowValidation workflow for automated research cron jobs when papers already have existing skills. Handles sync validation, knowledge graph schema verification, duplicate prevention, and ghost directory detection. Use when running automated arXiv paper processing that encounters pre-existing skills.Votes: 0GitHub stars: 3
- Autopoiesis Self Evolving SystemsAutopoiesis paradigm for self-evolving systems - online policy evolution for LLM serving under runtime dynamics. LLM-driven program synthesis for continuous adaptation. Activation: self-evolving systems, adaptive serving, online policy evolution, LLM serving optimization.Votes: 0GitHub stars: 3
- Autoregressive Flow Matching Neural DynamicsFramework for probabilistic prediction of neural population dynamics using autoregressive flow matching (AFM). Addresses the inherent stochasticity and nonlinearity of neural activity by leveraging transport-based generative modeling to forecast neural responses from multimodal sensory input at scale.Votes: 0GitHub stars: 3
- AutoresearchAutonomous AI research loop - let the agent run ML experiments overnight. Inspired by Karpathy's autoresearch. Use when: autonomous research, ml experiments, overnight training, self-improving models, auto-optimization.Votes: 0GitHub stars: 3
- Backprop Brain Hierarchy MisalignmentMethodology for analyzing the misalignment between backpropagation algorithms in deep neural networks and the hierarchical organization of brain responses. Extends encoding analyses from forward activations to backpropagated gradients, revealing fundamental differences in learning mechanisms. Use when studying brain-DNN alignment, computational neuroscience, or investigating whether backpropagation is biologically plausible.Votes: 0GitHub stars: 3
- Backpropagation Brain Hierarchy Misalignment反向传播算法与人脑视觉处理层级的不匹配研究。使用fMRI和MEG证明梯度虽能预测脑信号，但其时空组织与生物学反向传播机制不符。激活词：反向传播、大脑层级、brain hierarchy、backpropagation、fMRI、MEG、视觉处理、DINOv3、神经网络学习机制。Votes: 0GitHub stars: 3
- Backpropagation Brain MisalignmentBackpropagation algorithm misalignment with human brain visual processing hierarchy research. Uses fMRI/MEG to map backpropagated gradients onto neural data, showing DINOv3 gradients can predict brain signals but spatial/temporal organization diverges from biologically plausible backpropagation. arXiv: 2605.28693. Activation: backpropagation brain alignment, gradient neural correspondence, encoding analysis backprop, DINOv3 brain mapping, biological backpropagation, fMRI gradient mappingVotes: 0GitHub stars: 3
- Bakron Efficient Quantization Kron HessianEfficient quantization using Kronecker-factored Hessians.Votes: 0GitHub stars: 3
- Bandroutenet Eeg Artifact RemovalAdaptive frequency-aware neural network for EEG artifact removal using band-specific processing and routing mechanisms. Activation triggers: EEG denoising, artifact removal, BandRouteNet, EOG removal, EMG removal.Votes: 0GitHub stars: 3
- Bandrouternet Eeg ArtifactBandRouteNet adaptive frequency-aware neural network for EEG artifact removal. Jointly exploits band-specific processing and full-band contextual modeling for EOG/EMG artifact denoising. Features band-wise denoising with routing mechanism and full-band conditioner. Use for neurological diagnosis, BCI applications, and EEG signal enhancement. Keywords: EEG denoising, artifact removal, EOG, EMG, band routing, frequency-aware, brain-computer interface.Votes: 0GitHub stars: 3
- Bandwidth Reduction Packetized MpcBandwidth reduction methods for packetized Model Predictive Control over lossy networks. Multi-horizon MPC formulation with communication-rate reduction for networked control systems. Use for: networked MPC, bandwidth-efficient control, 5G/IoT control systems, packetized control, offloaded MPC. Activation: packetized MPC, bandwidth reduction, networked control, multi-horizon MPC, lossy network control.Votes: 0GitHub stars: 3
- Bara Bayesian Adaptive Rank LoraBaRA — Bayesian Adaptive Rank Allocation for LoRA fine-tuning. Dynamically allocates per-instance effective rank via sparse activation of disentangled latent factors, with complexity-theoretic generalization bounds depending on learned joint effective rank rather than max rank.Votes: 0GitHub stars: 3
- Barbell Qldpc Superconducting HardwareBarbell Codes methodology for implementing qLDPC error correction on superconducting quantum hardware with constant hardware complexity scaling.Votes: 0GitHub stars: 3
- Bayesian Adaptive Latent Mixture Brain ConnectomeBayesian adaptive latent mixture model for zero-inflated weighted brain connectome analysis. Use when analyzing structural/functional brain networks with many zero-valued edges, modeling subject-level mixture of shared connectivity templates, or performing Bayesian inference on connectome data with Hurdle likelihoods.Votes: 0GitHub stars: 3
- Bayesian Haptic Perception DynamicsBayesian dynamical framework for modeling time-order effects in sequential haptic perception. Captures perceptual biases from prior expectations and temporal structure using drift-diffusion dynamics. Activation: haptic perception, Bayesian dynamics, time-order effects, sequential stimuli, perceptual bias.Votes: 0GitHub stars: 3
- Bayesian Information Processing Pathway MapsBayesian framework for quantifying neural entrainment evidence in Information Processing Pathway Maps (IPPMs). Shifts from frequentist hypothesis testing to probabilistic model adjudication, enabling relative evidence quantification for competing computational hypotheses. Applied to auditory neuroimaging for reconstructing cortical processing pathways.Votes: 0GitHub stars: 3
- Bayesian Ippm Cortical EntrainmentBayesian framework for Information Processing Pathway Maps (IPPMs) to map cortical entrainment from EEG/MEG data. Compares Bayesian vs frequentist approaches for model adjudication in computational neuroscience. Uses temporal response functions (TRFs) and model evidence for reconstructing sensory processing pathways. Activation: IPPM, cortical entrainment, Bayesian model comparison, information processing pathway, temporal response function, auditory processing, EEG MEG analysis, model adjudi...Votes: 0GitHub stars: 3
- Bayesian Ippm Entrainment EvidenceBayesian framework for quantifying neural entrainment evidence in Information Processing Pathway Maps (IPPMs). Replaces frequentist null hypothesis testing with probabilistic model adjudication using Bayes factors. Enables robust comparison of competing computational models explaining neural data, with explicit handling of collinear models.Votes: 0GitHub stars: 3
- Bayesian Membership Inference AttackBayesian decision-making framework for membership inference attacks on statistical releases using Bayesian network population models. Reframes membership inference with respect to populations represented as Bayesian networks, enabling more effective specialized attacks by incorporating prior information about attribute dependency structures. Use when analyzing statistical disclosure risk, designing membership inference attacks, or evaluating privacy of released statistics.Votes: 0GitHub stars: 3
- Bayesian Neural Portfolio ManagementBayesian neural network methodology for robust portfolio management in dynamic financial markets. Uses Bayesian inference to quantify uncertainty in portfolio optimization, adapt to changing market conditions, and provide probabilistic risk assessments. Use when building portfolio management systems with uncertainty quantification, dynamic market adaptation, or probabilistic risk modeling.Votes: 0GitHub stars: 3
- Bci Adversarial RobustnessAdversarial robustness methodology for EEG-based Brain-Computer Interfaces (BCIs). Lightweight custom CNN architectures that outperform EEGNet/DeepConvNet/SleepEEGNet under gradient-based adversarial attacks. Use for: BCI security, adversarial defense, EEG classification robustness, medical device security.Votes: 0GitHub stars: 3
- Bci Bandwidth Scaling PerspectiveFramework for understanding the nonlinear scaling relationship between brain-computer interface bandwidth and meaningful human input/output capacity, distinguishing between raw bandwidth, decodable neural states, and information a person can actually use, confirm, and express through embodiment, learning, and subject expression constraintsVotes: 0GitHub stars: 3
- Bci Rehabilitation ProtocolsOptimized BCI rehabilitation protocols for stroke recovery. Addresses task design, training duration, and neuroplasticity-driven adaptation for maximizing post-stroke motor recovery through brain-computer interfaces.Votes: 0GitHub stars: 3
- Bci Sift Feature SelectionBCI-sift (BCI Systematic and Interpretable Feature Tuning) methodology for automated feature selection in Brain-Computer Interface applications. Integrates advanced optimization algorithms (scikit-learn compatible) to identify informative neural features across electrode, temporal, and frequency dimensions from HD ECoG and other BCI modalities. Activates on BCI feature selection, ECoG decoding optimization, neural feature tuning, automated BCI ML pipeline, brain-computer interface classificat...Votes: 0GitHub stars: 3
- Bcmi Motion Control DetectionBCMI-driven motion control detection using EEG-based machine learning and interaction entropy for high-order brain networks during music-assisted drivingVotes: 0GitHub stars: 3
- Beast3d Gaussian Splatting BehaviorBEAST3D方法论：基于3D Gaussian splatting的自监督动物行为分析与神经编码框架。从稀疏视角视频重建3D行为结构，生成视角不变特征用于神经活动预测。Votes: 0GitHub stars: 3
- Behavior Decomposed LdsBehavior-dLDS: decomposed linear dynamical systems model for neural activity partially constrained by behavior. Disentangles behavior-related neural dynamics from internal computations in large-scale neural recordings. Scales to tens of thousands of neurons. Use when modeling neural population dynamics, decomposing brain activity into behavioral vs. internal subsystems, or analyzing brain-wide recordings with behavioral correlates. Activation: behavior-dLDS, decomposed linear dynamical system...Votes: 0GitHub stars: 3
- Behavior Vlm NeuroscienceFinetuning-free behavioral understanding framework for neuroscience using vision-language models. Enables pose estimation and behavioral analysis linking neural activity to natural actions without human annotation. Use when: analyzing animal behavior from video, building neuroscience behavioral pipelines, or doing finetuning-free VLM behavioral understanding.Votes: 0GitHub stars: 3
- Beyond Neural Activity PredictionMulti-level representational probing framework for evaluating digital twins of sensory cortex beyond standard prediction accuracy. Probes latent representations (linear decodability, latent-unit tuning, population geometry) in mouse V1 digital twins. Based on arXiv:2605.23122 (May 2026). Use when evaluating brain digital twins, comparing model architectures for neural prediction, or studying latent representations in vision models.Votes: 0GitHub stars: 3
- Beyond Sycophancy Structured Resistance ComplianceFramework for distinguishing constructive belief revision from sycophantic compliance in LLM moral reasoning through three-dimensional resistance-compliance process. Based on social psychology principles of position distance, source attribution, and coalition structure. Activation: sycophancy, moral reasoning, LLM alignment, social influence, belief revision.Votes: 0GitHub stars: 3
- Bi Cap Brain Inspired CaptureBrain-Inspired Capture (BI-Cap) — neuromimetic perceptual simulation for visual decoding from neural signals. Emulates Human Visual System processing with dynamic/static transformations and MI-guided blur regulation. Evidence-driven latent space handles neural non-stationarity. Activation: bi-cap, brain inspired capture, visual decoding, neural visual reconstruction, neuromimetic simulation, brain-to-imageVotes: 0GitHub stars: 3
- Bilinear Gating Motor Primitives Dendritic ComputationBilinear gating methodology linking dendritic coincidence detection to goal-directed adaptation. Motor cortex neurons encode goal information in burst fraction (not firing rate), implementing bilinear gate G(g)·Y(s) where goal and state inputs multiply via dendritic coincidence detection. Supports zero-shot generalization and rapid online adaptation. Accepted arXiv 2606.10891.Votes: 0GitHub stars: 3
- Bimoe Brain Inspired Experts EegBrain-Inspired Mixture of Experts (BiMoE) framework for EEG-dominant affective state recognition. Uses brain-topology-aware expert partitioning with dual-stream encoders and adaptive routing for multimodal sentiment analysis combining EEG with peripheral physiological signals. Activation: BiMoE, brain-inspired MoE, EEG affective recognition, multimodal sentiment analysis, topology-aware experts, physiological signal fusion.Votes: 0GitHub stars: 3
- Binary Spiking Causal ModelsCausal analysis of Binary Spiking Neural Networks (BSNNs) using logic-based explainable AI methods. Formally defines BSNNs as binary causal models and provides tractable algorithms for computing abductive explanations.Votes: 0GitHub stars: 3
- Bio Inspired Computational Mapping[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