All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Can Ai Agents Conduct Open Ended Ai Research EarlyCan AI agents conduct open-ended AI research? Early evidence from two case studiesVotes: 0GitHub stars: 3
- Data Center Ai Workload PowerData center AI workload power profiling and infrastructure planning. Methods for measuring generative AI workload power consumption at high resolution, scaling to whole-facility energy demand, and planning infrastructure for grid connection, microgrids, and on-site generation. Triggers: data center power, AI energy consumption, GPU power profiling, facility infrastructure planning, generative AI workload, H100 power measurement, MLCommons benchmark power.Votes: 0GitHub stars: 3
- Datacenter Ai Workload Power Planning[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
- Ddm Time Averaged Drift InconsistencyProving time-averaged drift approximations are mathematically inconsistent for inference in Drift Diffusion Models (DDMs), with implications for computational neuroscience decision-making models. Activation: drift diffusion model, DDM, evidence accumulation, decision-making, time-varying drift, computational neuroscience, inconsistency, statistical inference.Votes: 0GitHub stars: 3
- Domain Paper ResearchConduct comprehensive domain-specific research paper discovery and compilation. Search across skills, Obsidian vault, and knowledge graph to find relevant papers, then compile into a structured collection with reading order, concept maps, and design decision matrices. Use when user asks for papers on a specific technical domain or wants to build a literature review for a project.Votes: 0GitHub stars: 3
- Evaluation Of Sessionbased Recommendation Algorithms**arXiv ID:** 1803.09587 **Authors:** Malte Ludewig, Dietmar Jannach **Published:** 2018-03-26T13:46:07Z **Abstract:** Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made sole...Votes: 0GitHub stars: 3
- Feature Life History ScaffoldFeature life history methodology for LLM training dynamics. Identifies the carrier scaffold — ~50 sparse features with stable life histories that organize the model's representational structure. Training follows two phases: selection (first 1%, features emerge/die 40x faster) and calibration (remaining 99%). Use when: analyzing LLM training dynamics, studying feature emergence, identifying core representational structure, sparse feature analysis, cross-layer ablation studies, interpretability...Votes: 0GitHub stars: 3
- Fluid Search Autonomous Research EfficiencyFluid search methodology for adaptive search efficiency in autonomous research systems. Uses portfolio bandit to dynamically allocate evaluation budget across search processes, optimizing area under Pareto frontier curve.Votes: 0GitHub stars: 3
- Getting Deep Recommenders Fit Bloom Embeddings For Sparse Binary Inputoutput Networks**arXiv ID:** 1706.03993 **Authors:** Joan Serrà, Alexandros Karatzoglou **Published:** 2017-06-13T10:50:25Z **Abstract:** Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these algorithms tend to have large input and output dimensionalities that dominate their overall size. This makes them difficult to train, due t...Votes: 0GitHub stars: 3
- Gnn Embedding Shape AnalysisNode embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. T... Activation: graph neural, learning, network, neuralVotes: 0GitHub stars: 3
- Hourly Research AutomationAutomated hourly research task execution with weekly topic rotation and daily quantum mechanics learning. Cron-driven workflow - search arxiv, import to knowledge graph, generate embeddings, analyze with PageRank/Louvain, extract patterns, create skills. Activates on cron triggers or manual execution of weekly_topics.py.Votes: 0GitHub stars: 3
- Indexed Memory索引化记忆检索系统，支持按主题、日期、效用分类检索知识，避免重复学习，提高检索效率。Votes: 0GitHub stars: 3
- Kg Research WorkflowEnd-to-end academic research workflow using knowledge graphs. Searches papers from arxiv/web, imports to KG database, generates embeddings, runs graph algorithms (PageRank, vector search), and extracts patterns for skill creation. Use for: automated research workflows, paper analysis pipelines, KG-based literature review.Votes: 0GitHub stars: 3
- Latent Rag ContinuousShift RAG reasoning and retrieval from discrete language to continuous latent space for ~90% latency reduction. Based on arXiv 2605.06285.Votes: 0GitHub stars: 3
- Matrix Spectral Data AppraisalMatrix spectral functions methodology for data appraisal, unifying neural scaling laws and Vendi Score. Shows both are submodular, with Vendi Score as a special case. Introduces secular-equation-based updates achieving 35,000x speedup for Vendi optimization. Reveals facility location outperforms Vendi Score for subset selection. Use when: data selection, dataset valuation, Vendi Score optimization, submodular data appraisal, neural scaling laws, matrix spectral functions, training subset sele...Votes: 0GitHub stars: 3
- Memory RetrievalTwo-stage memory retrieval skill using semantic matching and utility filtering for higher-quality recall.Votes: 0GitHub stars: 3
- Minimum Distortion Embedding NeuronalMinimum-Distortion Embedding (MDE) framework for analyzing evolving neuronal network dynamics. Use when dimensionality-reducing high-dimensional spiking activity, analyzing network development trajectories, or comparing stimulation effects in neuronal cultures.Votes: 0GitHub stars: 3
- Mutation Models Learning To Generate Levels By Imitating Evolution**arXiv ID:** 2206.05497 **Authors:** Ahmed Khalifa, Michael Cerny Green, Julian Togelius **Published:** 2022-06-11T10:44:57Z **Abstract:** Search-based procedural content generation (PCG) is a well-known method for level generation in games. Its key advantage is that it is generic and able to satisfy functional constraints. However, due to the heavy computational costs to run these algorithms online, search-based PCG is rarely utilized for real-time generation. In this paper, we introduce mu...Votes: 0GitHub stars: 3
- Neuroscience Research MethodCNN + Adversarial Autoencoder (AAE) for EEG signal classification — from raw EEG to image representations, latent-space regularization, and robust brain-computer interface (BCI) decoding.Votes: 0GitHub stars: 3
- Qpinn Trainable EmbeddingsQPINN Framework with Quantum Trainable Embeddings for PDE solving. Use when building quantum physics-informed neural networks, variational quantum circuits for PDEs, quantum feature maps for scientific computing, or quantum-assisted fluid dynamics simulations. Triggered by: QPINN, quantum PINN, quantum physics-informed neural network, quantum trainable embeddings, quantum PDE solver, quantum neural network for fluid dynamics.Votes: 0GitHub stars: 3
- Requests For Research 20Skill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Research Api Fallback StrategyFallback strategies for automated research when external APIs fail. Use when: (1) arXiv/semantic scholar APIs return errors, (2) scheduled research jobs encounter connectivity issues, (3) need to pivot from live search to knowledge-based skill creation, (4) automated research pipelines need resilience against external service failures.Votes: 0GitHub stars: 3
- Research Literature KgBuild and analyze knowledge graphs from research literature. Automated pipeline: arxiv search → entity extraction → KG construction → vector embeddings → semantic search → skill pattern extraction. Use when user asks to analyze papers, build research knowledge bases, find related work, or extract reusable patterns from academic literature.Votes: 0GitHub stars: 3
- Research Paper Pattern ExtractorExtract reusable research skill patterns from knowledge graph paper analysis. Uses PageRank, Louvain, and vector search to identify important papers and research clusters, then distills patterns into new skills. Activation: extract research pattern, research skill extractor, 研究模式提炼, paper pattern analysis.Votes: 0GitHub stars: 3
- Research Paper WritingEnd-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.Votes: 0GitHub stars: 3
- Research Skill Duplicate PreventionGuidelines and patterns for preventing duplicate entries in INDEX.md during automated research workflows. Provides detection methods, prevention strategies, and resolution procedures for handling duplicate skill entries in knowledge repositories.Votes: 0GitHub stars: 3
- Research Skill ExtractorMeta-skill that extracts reusable skill patterns from research papers (arxiv), scientific workflows, and knowledge graph analysis. Activates when analyzing papers for skill patterns, creating skills from research methodologies, or mining patterns from scientific literature. Keywords: extract skill from paper, research skill mining, 论文技能提炼, paper to skill, arxiv skill extractor.Votes: 0GitHub stars: 3
- Selfimproving Language Models For Evolutionary Program Synthesis A Case Study On Arcagi**arXiv ID:** 2507.14172 **Authors:** Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer **Published:** 2025-07-10T15:42:03Z **Abstract:** Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative by exploring solution spaces iteratively, but their effectiveness remain limited by the fixed capabilities of the underlying generative model. We propose SOAR, a method that...Votes: 0GitHub stars: 3
- Semantic Navigation Embedding TrajectoriesSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Sensitivityaware Mixedprecision Quantization And Width Optimization Of Deep Neural Networks Through Clusterbased Treestructured Parzen Estimation**arXiv ID:** 2308.06422 **Authors:** Seyedarmin Azizi, Mahdi Nazemi, Arash Fayyazi, Massoud Pedram **Published:** 2023-08-12T00:16:51Z **Abstract:** As the complexity and computational demands of deep learning models rise, the need for effective optimization methods for neural network designs becomes paramount. This work introduces an innovative search mechanism for automatically selecting the best bit-width and layer-width for individual neural network layers. This leads to a marked enhance...Votes: 0GitHub stars: 3
- Siren Signaware Recommendation Using Graph Neural Networks**arXiv ID:** 2108.08735 **Authors:** Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin **Published:** 2021-08-19T15:07:06Z **Abstract:** In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy. However, such attempts have focused mostly on utilizing only the information of positive user-item interactions with high ratings. Thus, there is a challenge on...Votes: 0GitHub stars: 3
- Streamindex Csa TopkMemory-bounded compressed sparse attention via streaming chunked top-k. Eliminates OOM in DeepSeek-V4 CSA indexer by avoiding full score tensor materialization.Votes: 0GitHub stars: 3
- Systems Engineering Research Aug2026August 2026 systems engineering research synthesis.Votes: 0GitHub stars: 3
- Weibull Change Point DetectionCopula-based Markov chain methodology for offline change-point estimation in financial time series with Weibull marginals. Handles nonlinear serial dependence in nonnegative financial data (volumes, durations, volatility). Use when analyzing regime changes in financial data, detecting structural breaks in trading volumes or volatility, modeling time series with copula-based dependence, or working with Weibull-distributed financial quantities.Votes: 0GitHub stars: 3
- Dbnn Spike ClassificationDBNN (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 implantable brain-computer interfaces. Activation: DBNN, spike sorting, binarized neural network, brain-computer interface, FPGA implementation, ASIC design, neural decoding, implantable devices.Votes: 0GitHub stars: 3
- Dcho Higher Order Brain ConnectivityDCHO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。Votes: 0GitHub stars: 3
- Ddd Microservice SimulatorDomain-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, and supports Sagas and Transactional Causal Consistency (TCC) transactional models. Activation: DDD microservices, saga pattern, TCC, transactional consistency, microservice simulation, aggregate modeling, distributed consistency validatio...Votes: 0GitHub stars: 3
- Decentralized Stochastic Momentum AdmmDecentralized Momentum Tracking with Biased Gradients (Biased-DMT) for large-scale distributed optimization. Handles communication compression and data heterogeneity in decentralized learning. Use for: decentralized optimization, federated learning, distributed ML, gradient compression, biased gradients. Activation: decentralized optimization, biased gradients, momentum tracking, distributed learning, federated learning, gradient compression.Votes: 0GitHub stars: 3
- Declarative Self Improvement声明式自我改进技能，通过目标驱动的方式引导 Agent 持续进化。触发词：自我改进、self-improvement、目标驱动、goal-driven improvement、声明式进化、declarative evolution、改进循环、improvement loop。Votes: 0GitHub stars: 3
- Decoded Quantum Interferometry BenchmarkComplexity-theoretic benchmarking methodology for decoded quantum interferometry (DQI) and bounded-degree constraint satisfaction problems. Analyzes quantum advantage limits, classical vs quantum decoder performance, and approximation hardness over finite fields.Votes: 0GitHub stars: 3
- Decoding Encoding Alignment CritiqueCritical analysis framework for brain-model alignment methodology. Demonstrates that representational similarity analysis (RSA) and decoding-based alignment metrics are fundamentally insensitive to encoding manifold topology. Similar decoding behavior and high representational alignment can arise from small, non-representative neuron subpopulations. Use when: evaluating brain-DNN alignment, RSA/DSA methodology, encoding vs decoding analysis, neural representation comparison, brain-model simil...Votes: 0GitHub stars: 3
- Decolle Snn Learning深度连续局部学习方法论（DECOLLE）。在脉冲神经网络中实现局部突触可塑性规则，通过合成梯度实现端到端训练。适用于事件驱动视觉、神经形态计算、在线学习、脉冲神经网络研究。触发词：DECOLLE、脉冲神经网络、突触可塑性、局部学习、神经形态计算、在线学习、spiking neural network、synaptic plasticity、neuromorphic computing。Votes: 0GitHub stars: 3
- Decorrelation Grid Cell DistanceDistance coding via de-correlation of heterogeneous grid cell populations. Mathematical theory showing how small variability in grid properties enables distance encoding through population activity de-correlation, with non-intuitive 'sweet spot' predictions and range-distinguishability trade-offs. Activation: grid cells, distance coding, de-correlation, medial entorhinal cortex, navigation, population coding, heterogeneity, spatial navigation, place cells, path integrationVotes: 0GitHub stars: 3
- Deep Binarized Photonic Reservoir ComputingUltrafast photonic neural network architecture using binary optical modulation, optical scattering, and time-multiplexed deep layers for Gb/s multimedia processing. State-of-the-art performance in video, image, and speech recognition.Votes: 0GitHub stars: 3
- Deep Photonic Reservoir ComputingDeep binarized photonic reservoir computing architecture achieving Gb/s multimedia signal processing via digital micro-mirror device (DMD), optical scattering, and CMOS photodetection. Use for ultra-fast video/image/speech recognition, neuromorphic photonic systems design, or physical reservoir computing implementation. Triggers: photonic reservoir computing, optical neural networks, ultra-fast multimedia processing, physical RC, binarized photonic, DMD neural, Gb/s inference.Votes: 0GitHub stars: 3
- Defensibility Analysis Shield SynthesisNetwork defensibility analysis using shield synthesis and adversarial game theory. Reinterprets shielded RL from runtime enforcement to design-time structural analysis. Use when: analyzing network topology security, synthesizing safety shields for RL agents, computing defensibility verdicts for cyber-physical systems, designing secure multi-agent architectures, evaluating network architecture defensibility, or combining formal verification with adversarial RL.Votes: 0GitHub stars: 3
- Delay Adaptive Snn Classifier延迟自适应脉冲神经网络分类器。基于共形预测(CP)提供可靠性保证的早停机制，让SNN在足够自信时提前决策，降低延迟和能耗。适用于神经形态计算、边缘AI、实时推理。触发词：SNN早停、延迟自适应、共形预测、脉冲神经网络、可靠性保证、delay-adaptive、early stopping、conformal prediction、spiking neural network。Votes: 0GitHub stars: 3
- Demented Brain Connectivity PatternsDifferential structural connectivity analysis in dementia and aging using the OASIS-3 dataset. Reveals both decreased connectivity (hippocampus, temporal lobe) and surprisingly increased connectivity (precuneus, cuneus, insula) in demented brains. Activation: dementia connectivity, brain network degradation, OASIS-3, structural connectivity aging, precuneus hyperconnectivity, demented brain.Votes: 0GitHub stars: 3
- Dendri Cl Single Layer SnnDendriCL methodology for dendritic in-context learning in single-layer compartmental spiking neural networks. Proves that apical dendritic subthreshold dynamics implement online leaky LMS, collapsing ICL architectural depth to one layer with frozen inference weights.Votes: 0GitHub stars: 3
- Dendricl Icl Single Layer SnnDendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. The apical compartment's subthreshold dynamics implement online Widrow-Hoff LMS, enabling general-purpose ICL without attention, depth, or inference-time plasticity. First SNN to solve Garg-2022 ICL benchmark at d≥30 where Transformers fail. Trigger: dendritic computation, in-context learning SNN, compartmental neuron, online LMS, biological ICL, neuromorphic ICL, apical dendrite, single-layer lear...Votes: 0GitHub stars: 3