菜单
这个仓库中的 skills
SkillsMP 已收集 hiyenwong/ai_collection 中的 4,114 个 Skill。打开任一 Skill 可查看来源和详情。
hiyenwong/ai_collection已展示 40 / 4,114 个已收集 Skill。
Coset-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…
原文语言：英语
Coset 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…
原文语言：英语
Counterfausal 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…
原文语言：英语
Statistical 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…
原文语言：英语
Covert 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,…
原文语言：英语
Framework for analyzing and ensuring computational covertness in multi-tenant quantum computers, accounting for crosstalk-based side channels and adversarial detection via quantum-strategy framework.
原文语言：英语
Resilience 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…
原文语言：英语
Criticality-Constrained Quadratic Pruning (CQP) for energy-efficient SNNs combining weight magnitude with surrogate-gradient criticality
原文语言：英语
CRiSP — 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…
原文语言：英语
Critical 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…
原文语言：英语
Criticality-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…
原文语言：英语
Cross-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)…
原文语言：英语
Multi-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…
原文语言：英语
Measuring 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…
原文语言：英语
Cross-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:…
原文语言：英语
Cross-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…
原文语言：英语
Cross-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…
原文语言：英语
Intent-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…
原文语言：英语
CSS 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,…
原文语言：英语
Factor-graph formulation of CSS quantum error correction syndrome decoding using joint belief propagation and four-state BP. Enables efficient classical decoding for CSS codes.
原文语言：英语
CTM-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…
原文语言：英语
Import 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.
原文语言：英语
Geometric 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,…
原文语言：英语
Continuous-variable photonic quantum neural networks for parameter-efficient edge AI medical imaging with room-temperature operation and extreme parameter reduction
原文语言：英语
Parameter-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…
原文语言：英语
Continuous-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…
原文语言：英语
Continuous-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…
原文语言：英语
Declining 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…
原文语言：英语
DANCE (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…
原文语言：英语
DANCE (Detect And Classify Events) — deep learning pipeline for joint event detection and classification from continuous, unaligned EEG signals. Frames neural decoding as a set-prediction problem, eliminating the need for pre-aligned event windows. Achieves…
原文语言：英语
Dark Signals framework — physics-informed complex-valued brain network dynamics using Hamiltonian mechanics. Augments observed fMRI/EEG signals with latent conjugate momenta via Hilbert transform, yielding Schrödinger-like equations for whole-brain dynamics.…
原文语言：英语
Training-free routing framework for hybrid reasoning models. Uses draft agreement signals to adaptively allocate thinking budgets without labeled data or gradient updates.
原文语言：英语
DART-Q methodology for real-time quantum error correction decoding. Deadline-driven QLDPC decoder framework with queueing theory, EDF scheduling, and admission control for fault-tolerant quantum computing. Activation: real-time decoding, quantum decoder…
原文语言：英语
Training-free evolutionary merging framework for LLMs using MRI-Trust Fusion and adaptive merge genome. Use when: merging LLMs without training, evolutionary model combination, gradient-free weight-space recombination, cross-architecture model breeding,…
原文语言：英语
Data-driven distributed controller synthesis using spatial regret optimization. For synthesizing optimal distributed controllers directly from frequency-response data without requiring a parametric system model. Use when: (1) designing distributed control…
原文语言：英语
Data-driven reachability analysis framework using matrix perturbation theory. Provides Cai-Zhang bounds for matrix zonotopes and constrained matrix zonotopes. Enables efficient reachable-set propagation with coefficient-space approximation. Use for: safety…
原文语言：英语
Data poisoning attacks on data-driven control systems - security analysis and defense strategies. Use for: securing data-driven control, attack detection, resilient control synthesis, adversarial robustness. Activation: data poisoning, control security,…
原文语言：英语
DBNN (Deep Binarized Neural Network) for hardware-efficient neural spike classification with multiplier-free inference. Achieves 98.7% accuracy with 0.014 mm² area and 122 nW power at 20 kHz. Uses sign-controlled accumulation and bit-wise logic for…
原文语言：英语
DCHO高阶脑连接预测方法论。通过分解-组合框架预测三个或更多脑区之间的相互作用，捕获比传统成对连接更丰富的组织信息。适用于脑网络预测、状态分类、脑动力学预测。触发词：高阶脑连接、HOBC、脑网络预测、分解组合、higher-order connectivity、brain dynamics。
Domain-Driven Design simulator for business logic-rich microservice systems. Isolates core business logic from communication and transactional infrastructure, evaluates identical application code under varying consistency guarantees and network constraints,…
原文语言：英语