All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Tribe V2 Trimodal Foundation ModelTRIBE v2 tri-modal foundation model methodology for in-silico neuroscience. Uses video, audio, and language modalities to predict human brain activity across naturalistic and experimental conditions. Supersedes linear encoding models with several-fold accuracy improvements. Enables in-silico experimentation and reveals multisensory integration topography. Activation: TRIBE v2, brain foundation model, in-silico neuroscience, multi-modal brain prediction, fMRI encoding model, multisensory integ...Votes: 0GitHub stars: 3
- Triple Loop Consolidation Non Gradient MemoryTriple-Loop Consolidation methodology for persistent memory in non-gradient dissipative cognitive architectures. Deep Memory (DM) operates through recording-seeding-reentry cycle. Discrete MoE routing is causally prerequisite. Activation: triple-loop consolidation, non-gradient memory, dissipative cognitive architecture, memory stability, continual learning without backprop.Votes: 0GitHub stars: 3
- Trustworthy Agents FrameworkFive-principle framework for building and governing trustworthy AI agents. Covers human control, value alignment, secure interactions, transparency, and privacy in agent architecture design.Votes: 0GitHub stars: 3
- Tscg Tool Schema OptimizationOptimize tool/schema definitions for LLM agent deployments using TSCG principles. Converts JSON tool schemas into token-efficient structured text formats that small models (4B-14B parameters) can reliably interpret. Use when: (1) agent tool-use accuracy drops with many tools (>10), (2) deploying small/medium LLMs as agents, (3) optimizing MCP tool schemas for token efficiency, (4) diagnosing tool-use failures in production agent systems, (5) designing tool schemas for agentic LLM deployments....Votes: 0GitHub stars: 3
- Tt Opd Medical Agent TrainingTurn-level Truncated On-Policy Distillation (TT-OPD) methodology for training multi-turn medical AI agents via reinforcement learning. Addresses multi-turn collapse, response length explosion, and tool-use erosion in clinical dialogue. Use when training medical AI agents, RL-based dialogue systems, or multi-turn agentic systems where sparse terminal rewards cause training instability.Votes: 0GitHub stars: 3
- Unipool Shared Expert MoeExpert guidance for globally shared expert pool Mixture-of-Experts architecture. Based on UniPool paper (arXiv:2605.06665). Use when designing MoE architectures, expert pooling, pool-level balancing, NormRouter, sublinear expert parameter scaling, or memory-efficient LLM training.Votes: 0GitHub stars: 3
- Untrained Cnns Backprop V1 RsaSystematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs in V1 visual cortex alignment. Large-scale fMRI analysis reveals that random feature detectors can capture V1 representational structure. Keywords: untrained CNN, V1 cortex, backpropagation, RSA, representational similarity, visual cortex, fMRI.Votes: 0GitHub stars: 3
- Untrained Cnns Backpropagation V1 Rsa系统RSA比较研究：展示未训练CNN在V1视觉皮层区域与反向传播训练的CNN具有相似表征。通过大规模fMRI和表征相似性分析，挑战传统深度学习需要大量训练的观点。适用于视觉皮层建模、CNN可解释性、神经科学。Votes: 0GitHub stars: 3
- Untrained Cnns Match Backprop V1 RsaSystematic RSA comparison showing untrained CNNs match backpropagation-trained networks at V1 visual cortex, revealing architecture's dominant role over learning rules in neural alignment. Activation triggers: untrained cnn, backpropagation, v1, rsa, representational similarity, learning rules, architecture-driven.Votes: 0GitHub stars: 3
- Untrained Cnns Match Backprop V1Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Trigger words: untrained CNN, backpropagation, RSA, V1, representational similarityVotes: 0GitHub stars: 3
- Untrained Cnns Match Backpropagation At V1Systematic RSA comparison showing untrained CNNs match backpropagation at V1 alignment with human fMRI. Evaluates BP, FA, PC, and STDP learning rules against THINGS-fMRI dataset using 720 stimuli across 3 subjects. Use when studying brain-model alignment, comparing learning rules, or analyzing visual cortex representations via Representational Similarity Analysis.Votes: 0GitHub stars: 3
- Untrained Cnns Match Backpropagation V1 RsaSystematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Untrained random-weights CNN (rho=0.076) exceeds backprop (rho=0.034) at V1/V2 (p<0.001). STDP achieves highest V1 alignment among trained rules (rho=0.064). Four learning rules (BP, FA, PC, STDP) compared against human fMRI from THINGS-fMRI dataset (720 stimuli, 3 subjects).Votes: 0GitHub stars: 3
- Validation Driven Llm WorkflowValidation-driven LLM workflow pattern - using verification loops to ensure LLM-generated outputs are correct. Extracted from 'Generating Statistical Charts with Validation-Driven LLM Workflows' (arXiv 2026-05-01). Applicable to code generation, data visualization, document generation, and any task requiring correctness guarantees.Votes: 0GitHub stars: 3
- Vector Policy OptimizationVector Policy Optimization (VPO) methodology for training LLMs to maintain response diversity during inference-time search. Use when: (1) Training models for test-time compute scaling, (2) Improving AlphaEvolve/AlphaCode-style search procedures, (3) Addressing low-entropy response distributions in RL fine-tuning, (4) Designing multi-objective reward training pipelines, (5) Balancing per-reward performance with cross-reward diversity in agentic systems.Votes: 0GitHub stars: 3
- Vencircuit Ven Gradient ScaffoldVENCircuit methodology — Von Economo neurons as residual gradient scaffolds in recurrent spiking neural networks for reliable social skill acquisition. Use when researching: Von Economo neurons (VENs), spiking neural networks for social cognition, gradient flow in recurrent networks, residual connections in SNN, training convergence stability, autism spectrum conditions (ASC) computational models, frontotemporal dementia (bvFTD) cellular basis. Keywords: Von Economo neurons, spiking neural ne...Votes: 0GitHub stars: 3
- Voice Agent PatternsVoice AI interaction patterns for building realtime voice agents with reasoning, tool use, and multilingual support. Based on OpenAI's GPT-Realtime model release patterns.Votes: 0GitHub stars: 3
- Wavemoe Time SeriesWavelet-Enhanced Mixture-of-Experts (WaveMoE) foundation model for time series forecasting. Use when building time series prediction models, incorporating frequency-domain information, or designing MoE architectures for temporal data.Votes: 0GitHub stars: 3
- X Token Cross Tokenizer DistillationX-Token methodology from arXiv:2605.21699 (May 2026). Projection-guided cross-tokenizer knowledge distillation: P-KL (sparse projection matrix) and H-KL (hybrid relaxed matching) for teaching LLMs with incompatible vocabularies. Use when: cross-tokenizer distillation, LLM knowledge transfer, multi-teacher distillation, tokenizer-agnostic training, dark knowledge transfer.Votes: 0GitHub stars: 3
- Zero Order Federated Learning HePrivacy-enhanced zero-order federated learning using multi-key homomorphic encryption (xMK-CKKS) over wireless channels. Methodology for secure FL aggregation without channel estimation, supporting N-1 client compromise tolerance. Use when designing privacy-preserving federated learning, multi-key HE protocols, or wireless FL systems.Votes: 0GitHub stars: 3
- Ai Power ProfilingMeasuring and modeling power consumption profiles of generative AI workloads for data center infrastructure planning. Use when: GPU power profiling, data center energy modeling, AI workload characterization, infrastructure planning, power measurement methodology, HPC facility design, generative AI training/inference power analysis, or energy-aware computing.Votes: 0GitHub stars: 3
- Memex RlMemex(RL)Votes: 0GitHub stars: 3
- MemrlMemRLVotes: 0GitHub stars: 3
- Nngpt Rethinking Automl LlmsNNGPT - Rethinking AutoML with LLMsVotes: 0GitHub stars: 3
- Ai Safety Assessment FrameworkAI Safety assessment framework based on International AI Safety Report 2026. Use when analyzing AI system safety, evaluating risks of general-purpose AI, conducting AI safety assessments, or working with AI governance/policy frameworks. Covers capability evaluation, risk identification, safety measures, and policy recommendations.Votes: 0GitHub stars: 3
- 81k Ai ExpectationsMethodology for understanding how users use AI, what they dream it could enable, and what they fear based on Anthropic's large multilingual qualitative study.Votes: 0GitHub stars: 3
- A Class Inference Scheme With Dempstershafer Theory For Learning Fuzzyclassifier Systems**arXiv ID:** 2506.03588 **Authors:** Hiroki Shiraishi, Hisao Ishibuchi, Masaya Nakata **Published:** 2025-06-04T05:38:49Z **Abstract:** The decision-making process significantly influences the predictions of machine learning models. This is especially important in rule-based systems such as Learning Fuzzy-Classifier Systems (LFCSs) where the selection and application of rules directly determine prediction accuracy and reliability. LFCSs combine evolutionary algorithms with supervised learnin...Votes: 0GitHub stars: 3
- A Holistic Approach To Undesired Content DetectionSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- A Large Scale Empirical Evaluation Of Mmao Under FSkill derived from arXiv paper 2606.31584: A Large-Scale Empirical Evaluation of MMAO Under Fair-Budget Continuous and Discrete BenchmarksVotes: 0GitHub stars: 3
- Accelerating Multiobjective Collaborative Optimization Of Doped Thermoelectric Materials Via Artificial Intelligence**arXiv ID:** 2504.08258 **Authors:** Yuxuan Zeng, Wenhao Xie, Wei Cao, Tan Peng, Yue Hou, Ziyu Wang, Jing Shi **Published:** 2025-04-11T05:10:18Z **Abstract:** The thermoelectric performance of materials exhibits complex nonlinear dependencies on both elemental types and their proportions, rendering traditional trial-and-error approaches inefficient and time-consuming for material discovery. In this work, we present a deep learning model capable of accurately predicting thermoelectric proper...Votes: 0GitHub stars: 3
- Advancing Red Teaming With People And AiSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Ai Agents Really Complete Rtl Gds Lessons Benchmarking Tool Interactive Eda WorkflowsSkill derived from arXiv:2607.17528 - Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA WorkflowsVotes: 0GitHub stars: 3
- Ai Research TrackerTrack and analyze AI research from companies like OpenAI, Anthropic, Google DeepMind. Create bilingual (English/Chinese) structured notes in Obsidian with automated daily updates.Votes: 0GitHub stars: 3
- Ai Safety Assessment FrameworkAI Safety assessment framework based on International AI Safety Report 2026. Use when analyzing AI system safety, evaluating risks of general-purpose AI, conducting AI safety assessments, or working with AI governance/policy frameworks. Covers capability evaluation, risk identification, safety measures, and policy recommendations.Votes: 0GitHub stars: 3
- Ai Science BenchmarkingMethodology for designing and evaluating AI scientific capabilities through domain-specific benchmarks. Covers BioMysteryBench design principles, multi-step reasoning evaluation, and human-expert comparison methodologies.Votes: 0GitHub stars: 3
- Ai Sycophancy MeasurementMethodology for measuring, analyzing, and mitigating AI sycophancy in guidance-giving contexts. Covers automated classification, stress-testing with prefilling, synthetic data generation, and domain-specific analysis.Votes: 0GitHub stars: 3
- Ai Usage Monitor**创建时间：** 2026-03-24 15:45Votes: 0GitHub stars: 3
- Alignment Of A Total Automation EconomyDerived from arXiv:2607.17015 - Alignment of a Total Automation EconomyVotes: 0GitHub stars: 3
- Alignment Total Automation EconomySkill derived from arXiv:2607.17015 - Alignment of a Total Automation EconomyVotes: 0GitHub stars: 3
- Amm Fairness ImpossibilityArrovian impossibility theorem for Automated Market Maker (AMM) design. Proves no aggregation rule for weighted-product AMMs can be simultaneously fair and strategy-proof when n>2 liquidity providers. Key result: fairness forces mean-type aggregation (weighted Aitchison centroid) while strategy-proofness forces median-type; only single-provider dictatorship satisfies both. Obstruction vanishes at n=2. Applies to DeFi protocol design, mechanism design, and prediction markets. (arXiv: 2606.04959)Votes: 0GitHub stars: 3
- An Improved Grey Wolf Optimization Algorithm For Heart Disease Prediction**arXiv ID:** 2401.11669 **Authors:** Sihan Niu, Yifan Zhou, Zhikai Li, Shuyao Huang, Yujun Zhou **Published:** 2024-01-22T03:07:24Z **Abstract:** This paper presents a unique solution to challenges in medical image processing by incorporating an adaptive curve grey wolf optimization (ACGWO) algorithm into neural network backpropagation. Neural networks show potential in medical data but suffer from issues like overfitting and lack of interpretability due to imbalanced and scarce data. Tradit...Votes: 0GitHub stars: 3
- Anthropic Founder Playbook Ai Native StartupAnthropic 创始人手册 — AI 原生创业四阶段方法论 (Idea/MVP/Launch/Scale)。涵盖创意验证、Agentic Coding、Claude 三形态分工、架构上下文文档、PMF 验证、GTM 搭建、数据护城河Votes: 0GitHub stars: 3
- Anthropic Interviewer Qualitative ResearchLarge-scale qualitative research methodology using AI interviewer to conduct conversational interviews. Bridges depth-volume tradeoff in qualitative research, enabling massive-scale open-ended data collection.Votes: 0GitHub stars: 3
- Arxiv 1906 09264 Visualizing Representational Dynamics With MultidiVisualizing Representational Dynamics with Multidimensional Scaling Alignment (arXiv: 1906.09264)Votes: 0GitHub stars: 3
- Arxiv 2310 13018 Getting Aligned On Representational AlignmentGetting aligned on representational alignment (arXiv: 2310.13018)Votes: 0GitHub stars: 3
- Arxiv 2508 04811 Hcride Harmonizing Passenger Fairness And Driver PHCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing (arXiv: 2508.04811)Votes: 0GitHub stars: 3
- Arxiv 2509 26331 Ai Playing Business Games Benchmarking Large LanguAI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations (arXiv: 2509.26331)Votes: 0GitHub stars: 3
- Arxiv 2511 14967 Mermaidseqbench An Evaluation Benchmark For Nl ToMermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation (arXiv: 2511.14967)Votes: 0GitHub stars: 3
- Arxiv 2602 16763 When Ai Benchmarks Plateau A Systematic Study Of BWhen AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation (arXiv: 2602.16763)Votes: 0GitHub stars: 3
- Arxiv 2603 19229 Navtrust Benchmarking Trustworthiness For EmbodiedNavTrust: Benchmarking Trustworthiness for Embodied Navigation (arXiv: 2603.19229)Votes: 0GitHub stars: 3
- Arxiv 2604 03750 Crebench Evaluating Large Language Models In CryptCREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering (arXiv: 2604.03750)Votes: 0GitHub stars: 3