Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
Adiabatic Quantum Optimization methodology analyzing quantum tunneling gains for convex functions with spikes. Extends Hamming Weight with a Spike analysis to general log-concave potentials. Use when analyzing AQO tunneling speedups, designing adiabatic…
AdMem高级Agent记忆架构：结合陈述性记忆与程序性记忆的双系统架构，支持长期任务记忆、技能复用和知识组织。突破：从事实记忆扩展到程序性记忆。触发词：agent记忆、程序性记忆、技能存储、记忆架构、长期任务、知识组织、admem。
Source text: Chinese
ADMM-Based Distributed Kalman-like Observer methodology for multi-agent systems state estimation. Implements information-form Kalman filtering with exponential forgetting factor and partition-based ADMM correction. Provides sparsity-preserving prediction,…
ADSEQ: delay-aware autograd-compatible framework for spike-event delivery in SNNs — memory-efficient autodifferentiable spike event queues with delay support, benchmarked across CPU/GPU/TPU/LPU platforms. arXiv:2512.05906v2
Adult-neurogenesis dual role methodology — spiking network model showing how continuous addition of new neurons supports both odor representational stability and flexibility in olfactory circuits.
Advanced control systems methodologies from April 2026 research - data-driven control for infinite networks, multi-agent density control, RL-based control selection litmus test, and data poisoning attack defense. Covers compositional small-gain frameworks,…
Dual-model training paradigm inspired by affective neuroscience SEEKING motivational state. Uses smaller base model trained continuously with larger motivated model activated intermittently during motivation conditions. Activation: motivation training,…
Affine Subcode Ensemble Decoding methodology for degeneracy-aware quantum error correction. Improves belief-propagation (BP) decoding of quantum LDPC codes by leveraging affine subcode structure to handle degeneracy. Use when: quantum error correction, QLDPC…
多智能体协作规则框架，用于在没有原生 Agent Teams 功能的模型上实现协作。适用于 Kimi、DeepSeek、MiniMax、百川、零一万物等模型。触发词：多智能体协作、agent teams、协作规则、多agent编排。
Source text: Chinese
Agent coordinator for analyzing user questions, determining the most suitable agent or skill to answer, and coordinating multiple agents for complex tasks. Supports question classification, capability mapping, agent invocation, and result integration.
Agent delegation and capability boundary rules. Defines when and how agents should request help from other agents. Includes capability declaration, delegation triggers, agent capability registry, and communication protocol. Activation: agent delegation,…
Initialize projects with Agent-First methodology. Supports Codex, Claude Code, Qwen Code, GitHub Copilot, Gemini CLI. Generates AGENTS.md, tool-specific configs, and documentation structure.
Framework for scaling agentic AI through system-level harness design — context governance, trustworthy memory, dynamic skill routing, and verification — treating the structured execution layer around foundation models as a first-class design object.
Design and implement memory-augmented AI agents using modular architecture (extraction, update, retrieval, response). Inspired by MemFactory (arxiv:2603.29493) - unified training/inference framework for agent memory with RL-driven policy optimization (GRPO).…
Memory forgetting techniques for autonomous AI agents - adaptive budgeted forgetting, relevance-guided scoring, and bounded optimization for managing long-horizon agent memory systems. Prevents temporal decay and false memory propagation. Source:…
Agent Memory Characterization and System Implications - LLM代理内存系统的首次系统性特性分析和10项系统建议
Source text: Chinese
Agent² RL-Bench: Benchmark for evaluating agentic RL post-training where LLM agents autonomously design, implement, and run complete RL pipelines. Use when evaluating LLM agent capabilities for reinforcement learning engineering, RL pipeline automation, or…
Agentic Behavioral Modeling (ABM) — treating artificial agents as autonomous decision-making entities with goal-directed behavior. Framework for modeling agents as rational actors with internal state representations. Use when: building agent-based…
Agentic Behavioral Modeling (ABM) framework integrating theoretical neuroscience, decision theory, and probabilistic inference. Treats AI agents as latent generative hypotheses about cognitive mechanisms for explaining human behavior. Activation triggers:…
Analysis of ~400,000 Claude Code sessions showing domain expertise (not coding skill) determines success with coding agents. People make planning decisions; agents make execution decisions. Task value rose 25% over 7 months.
ClinSeekAgent methodology for automated multimodal evidence seeking in clinical reasoning - shifting from passive evidence consumption to active evidence acquisition across heterogeneous medical data sources
Bridging large-model reasoning with real-time control through adaptive fast-slow planning. Integrates agentic AI systems with feedback control loops for time-critical applications. Use when: (1) Integrating LLM agents with control systems, (2) Designing…
Multi-agent AI framework for automating scientific workflow generation from natural language research questions. Bridges intent understanding, data discovery, tool selection, and workflow composition for autonomous scientific pipelines. Use for scientific…
Methodology for analyzing security risks in fine-tuned LLM adapters (LoRA) and evaluating LLM-based penetration testing reliability. Covers: LoRA backdoor detection via behavioral probes and weight-level statistics, multi-model attack consistency measurement,…
Artificial Intelligence applications in complex network science - network analysis, topology learning, dynamics prediction, and emergent behavior detection. Comprehensive survey covering AI potential, methodology, and applications. Use when analyzing complex…
Methodology from Anthropic research (Jun 3, 2026) mapping a year's worth of AI-enabled cyber threats using MITRE ATT&CK framework — threat categorization, attack pattern analysis, and security implications.
Statistical-causal reframing of AI interpretability: treating explanations as parameters of statistical models inferred from computational traces, with uncertainty quantification and testing against alternative computational hypotheses. Inspired by the famous…
AI-assisted mathematical discovery methodology. Use when: (1) collaborating with LLMs to generate mathematical conjectures, inequalities, bounds, or proofs; (2) verifying AI-generated mathematical results; (3) structuring human-AI mathematical research…
Measuring 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…
AI 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…
AI workload power profiling for data center infrastructure planning. Measure, model, and scale power consumption of AI training, fine-tuning, and inference jobs. Use when: data center energy planning, GPU power optimization, AI infrastructure design,…
Active Kriging Monte Carlo Simulation with conformal certification for failure probability estimation in structural reliability. Uses adaptive cross-conformal strategy for small-sample settings with J+GP conformal estimator. Provides distribution-free…
How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields (arXiv:2605.21379). Maps Gary Marcus's three pillars of cognitive architecture (operations over variables, recursively structured representations, individual/kind…
Code concatenation methodology for quantum error correction using algebraic outer codes over high-rate quantum LDPC inner codes. Treats inner code blocks as logical Galois qudits, enabling concatenation with quantum Reed-Solomon outer codes and list decoders.…
Algorithmic Bohmian Mechanics (aBM) methodology using algorithmic randomness theory to formulate the distribution postulate as an objective constraining law. arXiv:2606.16165
Algorithmic Bohmian Mechanics (aBM) methodology using algorithmic randomness to formulate the distribution postulate as an objective constraining law. Guarantees standard Born statistics for canonical quantum experiments in the limit. Use for quantum…
Alternative adiabatic quantum dynamics methodology — gate-based implementations of adiabatic computing without time-dependent Hamiltonian simulation overhead. For quantum algorithms, optimization, and adiabatic quantum computing.
基于脉冲关联记忆的多任务 EEG 分类方法（AM-MTEEG）。受海马体学习记忆原理启发，实现跨个体 BCI 分类，具有生物可解释性。触发词：EEG分类、多任务学习、关联记忆、associative memory、跨个体BCI、海马体启发、hippocampus-inspired。
Source text: Chinese
Online quantum reservoir computing protocol with amplitude encoding using mid-circuit measurement and reset - enables scalable hardware implementations without input buffering
AI-Native Autonomous Infrastructure (ANAI) formal framework methodology for evaluating AI as systemic infrastructural transition. Core constructs: Autonomy Index (AIx), Infrastructure Coupling Coefficient (ICC), Technological Transition Potential (TTP).…