All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Convolution Delay Learning SnnCombines convolutional recurrent connections with DelRec delay learning mechanism in recurrent spiking neural networks. Achieves 99% parameter savings and 52x faster inference vs standard recurrent SNN while maintaining accuracy on audio classification. Convolutional recurrent structure with learned axonal delays provides streamlined architecture for resource-constrained edge systems. Activation: convolution delay learning, DelRec, recurrent SNN audio, axonal delay learning, efficient SNN arc...Votes: 0GitHub stars: 3
- Copilot Assisted Second Thought BciCopilot-Assisted Second-Thought Framework for EEG-to-robot motion decoding. Uses LLMs as copilot to refine motor kinematics predictions from EEG signals. Improves BCI decoding accuracy through iterative refinement. Activation: BCI, brain-computer interface, EEG decoding, motor kinematics, robot control, EEG-to-robot, second-thought framework, EEG prediction, 脑机接口, 脑电解码, 运动学预测Votes: 0GitHub stars: 3
- Copilot CliGitHub Copilot CLI - Terminal-native AI coding agent with autopilot mode, plan mode, and delegated tasks. Use when user mentions copilot cli, copilot terminal, or copilot autopilot.Votes: 0GitHub stars: 3
- Coral Open Ended DiscoveryAutonomous multi-agent open-ended discovery workflow inspired by the CORAL paper. Use when the task requires sustained search, iterative improvement, multi-agent exploration, shared knowledge accumulation, asynchronous parallel attempts, periodic reflection, or heartbeat-style redirection. Best for research discovery, algorithm design, systems optimization, skill discovery, long-running coding/search tasks, and open-ended problems where a single linear attempt is likely to plateau.Votes: 0GitHub stars: 3
- Core Brain Lesion SegmentationConcept-Reasoning Expansion framework for continual brain lesion segmentation in MRI. Combines visual perception with structured medical concepts to handle pathological heterogeneity and prevent catastrophic forgetting. Activation: brain lesion segmentation, continual learning, medical image segmentation, concept-reasoning, CoRE, MRI analysis.Votes: 0GitHub stars: 3
- Core Brain Network Covid[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
- Core Brain Network OodCORE (Confounding Robustness Enhancement) framework for out-of-distribution generalization in brain network analysis. Addresses site effects and covariate confounding via causal decoupling. Use when: building cross-site classifiers, dealing with scanner/site bias, handling spurious correlations in neuroimaging data, conducting multi-center studies, applying graph neural networks to brain connectivity with domain shifts.Votes: 0GitHub stars: 3
- Core Cross Site Ood Brain NetworkCORE (Cross-site OOD Robust brain nEtwork) framework for brain network learning across unseen sites. Addresses cross-site out-of-distribution degradation in fMRI graph-based learning through site-aware confounder decoupling, transient pathway dynamics profiling, line graph organization for transferable pathway-level modeling, and prior-guided subject-adaptive gating. Use when working with cross-site fMRI brain network analysis, OOD generalization in neuroimaging, site-conditioned bias mitigat...Votes: 0GitHub stars: 3
- Corsw Sliced Wasserstein Eeg DecodingCorrelation Sliced-Wasserstein (CorSW) framework for EEG decoding with domain generalization. Use when: (1) EEG cross-subject/cross-session decoding with distribution shifts, (2) Scale-invariant correlation matrix representations for BCI, (3) Pullback Euclidean Metric Sliced Wasserstein on manifold geometries, (4) Domain generalization for EEG classification tasks. Triggers: CorSW, EEG decoding, correlation matrix, sliced Wasserstein, domain generalization, BCI, cross-subject, distribution sh...Votes: 0GitHub stars: 3
- Corteg Eeg Ecog Cross ModalityCORTEG: Cross-modality transfer framework that adapts pretrained scalp-EEG foundation models to intracranial ECoG recordings. Combines EEG FM backbone with electrode-aware KNNSoftFourier spatial adapter, dual-stream tokenizer (low-frequency + high-gamma), and leave-one-subject-out fine-tuning. Enables competitive ECoG decoding with only 10-30 minutes of calibration data per patient. Activation: CORTEG, EEG foundation model, ECoG decoding, cross-modality transfer, scalp-to-intracranial, brain-...Votes: 0GitHub stars: 3
- Cortex Continual Learning FtnFunctional Task Networks (FTN) - cortex-inspired parameter isolation for unsupervised continual learning without catastrophic forgetting. Uses dendrite-like masking over network subpopulations. Triggers: continual learning, cortex-inspired, functional task networks, FTN, catastrophic forgetting.Votes: 0GitHub stars: 3
- Cortical Geometry Rnn Inductive Biases本论文提出利用 MICrONS（Machine Intelligence from Cortical Networks）功能连接组数据集构建生物合理的循环神经网络（RNN）。通过整合皮层几何结构、神经连接和功能关系三个维度的生物约束，作为强归纳偏置指导网络学习，显著提升认知决策任务性能并涌现出类脑网络拓扑特性。Votes: 0GitHub stars: 3
- Cortical Geometry Wiring Rnn Inductive BiasHarnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks — biologically grounded RNNs using MICrONS connectomics data (spatial coordinates, anatomical connectivity, functional relationships) to achieve superior learning performance.Votes: 0GitHub stars: 3
- Cortical Microcircuit Information FluxSimulation-based reverse engineering methodology for analyzing whether cortical microcircuits are structurally organized to optimize information flux. Covers information flux quantification via mutual information, Recurrence Resonance mechanisms, core-embedding network architecture analysis, and bias-fluctuation contributions to neural dynamics. Applicable to: (1) biological neural circuit functional interpretation, (2) artificial recurrent system design including reservoir computers, (3) cor...Votes: 0GitHub stars: 3
- Cortiva Candidate Score FusionCORTIVA methodology for candidate-score fusion of complementary visual teachers for EEG- and MEG-to-image retrievalVotes: 0GitHub stars: 3
- Coset Based Qldpc CodesCoset-based quantum LDPC code construction methodology — generalizes two-block group algebra (2BGA) codes using group action on cosets of subgroups, expanding search space for new quantum LDPC codes. Use for quantum error correction code design, qLDPC code search, syndrome extraction scheduling.Votes: 0GitHub stars: 3
- Coset Ensemble Decoder QecCoset Ensemble Decoder for Quantum Error Correction with Algorithm-Hardware Co-Design methodology. Ensemble forest exploration exploiting logically equivalent cosets to improve Union-Find decoding, with domain-specific FPGA architecture reducing LUT consumption 8.2x. Use when: (1) designing QEC decoders for fault-tolerant quantum computing, (2) optimizing accuracy-latency trade-offs in real-time syndrome decoding, (3) implementing hardware-efficient QEC decoders on FPGA, (4) ensemble decoding...Votes: 0GitHub stars: 3
- Counterfactual Brain DynamicsCounterfausal causal analysis framework for brain network dynamics using Hodge theory and minimum-energy principles. Models pathological disruptions and therapeutic interventions as energy-perturbation problems on network flows. Decomposes directed communication into dissipative and persistent (harmonic) components. Use when analyzing brain network causality, counterfactual interventions, network resilience, epilepsy models, Hodge decomposition on brain graphs, or causal inference beyond Gran...Votes: 0GitHub stars: 3
- Coupling Spread Quantum Field TheoryStatistical methodology for analyzing O(1) coupling expectations in quantum field theories. Quantifies the spread (ratio of largest to smallest dimensionless couplings) and derives closed-form probability distributions for coupling ratios. Use when: analyzing naturalness in particle physics, studying coupling constant distributions, computing probability bounds for hierarchies in QFT, or applying statistical reasoning to fundamental physics parameters. Activates on keywords: O(1) couplings, c...Votes: 0GitHub stars: 3
- Covert Bosonic Sequential DetectionCovert communication over bosonic channels using blockwise sequential detection — receiver-centric framework exploiting linear vs quadratic information growth asymmetry between Bob and Willie for optimal signaling design. Use for covert quantum communication, bosonic channel analysis, sequential detection systems.Votes: 0GitHub stars: 3
- Covert Quantum Computing CrosstalkFramework for analyzing and ensuring computational covertness in multi-tenant quantum computers, accounting for crosstalk-based side channels and adversarial detection via quantum-strategy framework.Votes: 0GitHub stars: 3
- Cps Anomaly Detector EvaluationMethodology for evaluating Cyber-Physical Systems (CPS) anomaly detectors independently of decision rules using normalized residual energy and Kullback-Leibler divergence analysis.Votes: 0GitHub stars: 3
- Cpsos Resilience DynamicsResilience as a dynamical property of risk trajectories in Cyber-Physical Systems of Systems (CPSoS). Use for: resilience assessment, risk trajectory analysis, CPSoS design, recovery dynamics evaluation. Activation: resilience dynamics, risk trajectory, CPSoS resilience, dynamical resilience, recovery assessment.Votes: 0GitHub stars: 3
- Cqp Criticality Constrained Snn PruningCriticality-Constrained Quadratic Pruning (CQP) for energy-efficient SNNs combining weight magnitude with surrogate-gradient criticalityVotes: 0GitHub stars: 3
- Crisp Rl Clifford VqaCRiSP — Reinforcement learning with Neural-Guided MCTS for Clifford circuit initialization of Variational Quantum Algorithms. Uses Transformer-based policy trained via self-play to insert learned Clifford gates before fixed parameterized rotations, enabling high-quality VQA initialization through polynomial-time classical stabilizer simulation.Votes: 0GitHub stars: 3
- Critical Flicker Fusion Plasticity BoundaryFramework for using Critical Flicker Fusion Frequency (CFFF) as a falsifiable boundary between plastic and non-plastic neural systems, with explicit operational criteria and hierarchical analysis.Votes: 0GitHub stars: 3
- Critical Patch Size Brain NetworksCritical patch size problem in graph networks with applications to brain connectomes and ecology. Spectral theory for population persistence using Dirichlet eigenvalues on random graphs. Activation triggers: critical patch size, random graph, Dirichlet eigenvalue, graph Laplacian, population persistence, network viability, brain network ecology.Votes: 0GitHub stars: 3
- Criticality Constrained Snn PruningCriticality-Constrained Quadratic Pruning (CQP) methodology for energy-efficient SNN deployment on neuromorphic hardware. Combines weight magnitude with surrogate-gradient criticality into analytically exact importance metric. Identifies continuous-relaxation trap, zombie-weight failure mode, and criticality cliff phenomenon. Achieves 95.6% accuracy at 90% sparsity on MNIST; 73% energy reduction at 70% sparsity.Votes: 0GitHub stars: 3
- Cross Layer Crypto AnalysisCross-layer cryptographic security analysis skill for evaluating message transformations across network protocol stack. Analyzes encryption, authentication, and encapsulation at each layer (application, transport, network, link, physical). Use when: (1) evaluating post-quantum security of network protocols, (2) auditing cryptographic operations across OSI/TCP layers, (3) analyzing message transformation security, (4) assessing quantum vulnerability of network stack, (5) security audit of prot...Votes: 0GitHub stars: 3
- Cross Lingual Llm Brain AlignmentMulti-lingual whole-brain encoding framework examining brain-LLM alignment across three typologically distinct languages (Mandarin, English, French). Shows that transformer-based models predict activity in widely distributed cortical functional networks (limbic, ventral attention, default mode, subcortical) across languages, revealing computational roots of cross-linguistic neural alignment with LLM representations. Activation: cross-lingual brain alignment, multilingual fMRI encoding, LLM-br...Votes: 0GitHub stars: 3
- Cross Modal Convergence DispersionMeasuring cross-modal neural network convergence using single-stimulus intra-modal dispersion. Generalized Procrustes Algorithm for quantifying how stimuli with low intra-modal dispersion elicit higher cross-modal alignment. Activation triggers: cross-modal convergence, neural network alignment, vision-language alignment, representational similarity.Votes: 0GitHub stars: 3
- Cross Scale Spatial Generative NeurodegenerationCross-scale spatially-aware generative modeling for transcriptomic programs underlying neurodegenerative brain organization. Variational framework linking gene expression to cortical degeneration with graph-based spatial smoothness. Activation: spatially-aware generative, transcriptomic neurodegeneration, cross-scale brain modeling, cortical thinning prediction, gene-expression degeneration.Votes: 0GitHub stars: 3
- Cross Species Rsa Brain AlignmentCross-Species RSA methodology for comparing brain-DNN alignment across human fMRI and macaque electrophysiology. Tests five learning rules (BP, FA, PC, STDP, untrained) across species showing conserved early visual alignment but divergent higher-area rankings. Use when: comparing species in brain encoding models, evaluating learning rule biological plausibility, cross-species validation of brain-DNN alignment, RSA with electrophysiology data. Triggered by: cross-species RSA, brain-DNN alignme...Votes: 0GitHub stars: 3
- Cross Subject Eeg DecodingCross-Subject Generalization for EEG Decoding — comprehensive survey of deep learning methods addressing inter-subject variability in EEG-based BCI. Covers domain adaptation, meta-learning, data augmentation, Riemannian geometry, and subject-independent evaluation protocols. Activation: cross-subject EEG, EEG domain adaptation, BCI generalization, subject-independent EEG, EEG transfer learning.Votes: 0GitHub stars: 3
- Crypto Agility ApiIntent-Based Cryptographic API Design for Cryptographic Agility — designing APIs that support transparent post-quantum algorithm migration without code rewrites. Use when building cryptographic systems, migrating to post-quantum cryptography, designing intent-based crypto APIs, or implementing policy-driven algorithm selection. Activation: cryptographic agility, post-quantum migration, intent-based API, policy-driven selection, key rotation, cryptographic governanceVotes: 0GitHub stars: 3
- Css Factor Graph DecodingCSS quantum error correction syndrome decoding via factor-graph formulation and belief propagation. Use when: implementing CSS code decoders, comparing joint BP vs four-state BP for syndrome decoding, formulating QEC decoding as factor graph inference, designing belief propagation decoders for stabilizer codes. Keywords: CSS code, syndrome decoding, factor graph, belief propagation, QEC decoder, Tanner graph, stabilizer code.Votes: 0GitHub stars: 3
- Css Syndrome DecodingFactor-graph formulation of CSS quantum error correction syndrome decoding using joint belief propagation and four-state BP. Enables efficient classical decoding for CSS codes.Votes: 0GitHub stars: 3
- Ctm Ai Consciousness BlueprintCTM-AI: Blueprint for General AI inspired by the Conscious Turing Machine (CTM) model of consciousness. Combines formal consciousness theory with foundation models, using processor selection, integration, and exchange mechanisms for flexible multisensory intelligence. Use when designing general AI architectures, consciousness-inspired systems, multi-processor AI frameworks, or global-workspace-style architectures. Activation: CTM-AI, Conscious Turing Machine, consciousness-inspired AI, global...Votes: 0GitHub stars: 3
- Cumulant Order Block Sparse AttentionCOBS - block sparse attention selector that stores a compressed SECOND-order (cumulant) statistic per block instead of only first-order (attention mass), closing the gap to dense attention at ~15x less KV-cache read traffic. Use when building/improving block-sparse attention (NSA-style) for long-context LLMs and existing selectors under-select.Votes: 0GitHub stars: 3
- Current Injection Spiking Neural Network Image FusionCurrent Injection Spiking Neural Network (CIS-Fuse) for energy-efficient infrared and visible image fusion using membrane-potential level cross-modal integrationVotes: 0GitHub stars: 3
- Curriculum Multiple Shooting Neural OdesGeneral-purpose training strategy for fitting ordinary differential equation models to time-series data by integrating curriculum learning with multiple shooting. Accelerates and stabilizes training convergence for Neural ODEs, Universal Differential Equations, and mechanistic ODEs.Votes: 0GitHub stars: 3
- Cursor Rules ImporterImport and convert cursor.directory rules into AgentSkills. Use when user wants to import cursor rules, convert .cursorrules to skills, or mentions cursor.directory, cursor rules import.Votes: 0GitHub stars: 3
- Curvature Aware Zeroth Order OptimizationCAZO for memory-efficient test-time adaptation.Votes: 0GitHub stars: 3
- Cusped Singularity Mmo AnalysisGeometric singular perturbation analysis of mixed-mode oscillations (MMOs) in inhibitory neural networks using cusped singularities. Activation triggers: mixed-mode oscillations, MMO, cusped singularity, slow-fast neural system, mutual inhibition oscillation, singular perturbation neural, blow-up method neural, neural oscillation mechanism, slow-fast system analysis.Votes: 0GitHub stars: 3
- Cv Photonic Qnn Edge AiContinuous-variable photonic quantum neural networks for parameter-efficient edge AI medical imaging with room-temperature operation and extreme parameter reductionVotes: 0GitHub stars: 3
- Cv Photonic Qnn Edge MedicalParameter-efficient continuous-variable photonic quantum neural networks for edge medical AI. Simplified Phi-D-U1 CV-QNN architecture cuts trainable parameters 40-45%, mitigates barren plateaus, achieves 100% calibrated test accuracy with 18 parameters for oral cancer detection. Use when: CV quantum neural network design, photonic quantum ML, medical image classification on edge devices, barren plateau mitigation, parameter-efficient quantum classifiers, room-temperature quantum computing.Votes: 0GitHub stars: 3
- Cv Qnn Spatial ClassificationContinuous-variable QNN advantage for spatial classification tasks. Controlled comparison showing CV-QNN outperforms DV-QNN by 18+ percentage points on wafer-map defect classification. CV structured layer captures fine spatial distinctions that DV misses. Use when designing QNNs for image/spatial classification, semiconductor yield, or any task requiring fine spatial pattern recognition.Votes: 0GitHub stars: 3
- Cv Quantum Biomedical ImagingContinuous-variable quantum neural networks (CV-QCNN) for biomedical image classification methodology. Uses photonic circuit simulation with Gaussian gates (displacement, squeezing, rotation, beamsplitters) to emulate convolutional behavior for medical imaging tasks. Activation: continuous variable quantum, CV quantum neural network, photonic quantum imaging, biomedical image classification, CV-QCNN, MedMNIST quantum, quantum medical imaging, photonic circuit simulation, Gaussian gate convolu...Votes: 0GitHub stars: 3
- Cvar Glidepath Target Date FundDeclining CVaR glidepath framework for target-date fund design. Controls portfolio risk through explicit Conditional Value-at-Risk glidepaths linked to pension-design inputs. Use when: target-date fund design, CVaR portfolio optimization, pension fund glidepath, retirement planning, declining risk budget, explicit return objective portfolio.Votes: 0GitHub stars: 3
- Dance Eeg Event Detection ClassificationDANCE (Detect and Classify Events in EEG) — deep learning pipeline that frames neural decoding as a set-prediction problem for joint event detection and classification from raw, unaligned EEG signals. Activation triggers: DANCE, EEG event detection, set prediction, asynchronous neural decoding, event-based EEG, raw EEG decoding, event classification, Meta AI EEG.Votes: 0GitHub stars: 3