Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking
Technical interview preparation expert for algorithms, system design, and behavioral questions
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization
TypeScript expert for type system, generics, utility types, and strict mode patterns
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.
Builds composable, pipeable function chains on the iii engine. Use when building functional pipelines, effect systems, or typed composition layers where each step is a pure function with distributed tracing.
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
MNN ARM CPU 算子性能优化。涵盖计算拆解、函数复用、多线程、数据排布、ARM 汇编编写。采用"先正确，再加速"原则，基于性能基准测试驱动优化。
为 MNN 框架添加新的 LLM 模型支持。支持从 HuggingFace/ModelScope 下载模型，分析架构，添加映射，Hook 对齐测试，导出 MNN 模型。采用 TDD 模式，分 6 步执行，每步有独立测试标准。
Implementation details for EF Core model building. Use when changing ConventionSet, ModelBuilder, IConvention implementations, ModelRuntimeInitializer, RuntimeModel, or related classes.
Implementation details for EF Core scaffolding (reverse engineering). Use when changing ef dbcontext scaffold pipeline implementation, database schema reading, CSharpModelGenerator, or related classes.
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
