Explore AI Agent Skills & Claude Prompts

This skill should be used when the user asks to "scaffold a world model", "create world model project", "generate world model directory structure", "set up world model codebase", "create base classes for world model", "world model ABC hierarchy", "hot-swappable encoder/dynamics/decoder", "world model dependency injection", "generate world model configs", "Hydra config for world model", "world model pyproject.toml", "modular world model architecture", "replace encoder without changing dynamics", "world model base class contracts", "BaseEncoder interface", "BaseDynamics interface", "BaseWorldModel composition", "world model deployment structure", "world model evaluation harness scaffold", or needs guidance on structuring a production-grade world model codebase with swappable components, config management, and packaging.

multi-modal-alignment-for-shared-embedding-space

This skill should be used when the user asks to "align modality representations", "multi-modal contrastive learning", "cross-modal alignment", "CLIP-style training", "modality gap reduction", "shared embedding space", "cross-attention alignment", "vision-language alignment", "audio-text alignment", "representation binding", "cross-modal retrieval", "modality projection heads", "alignment loss function", "modal invariance", "add contrastive loss", "implement projection heads", "fix modality gap", "add uniformity loss", "implement cross-modal retrieval", "add hard negative mining", "implement curriculum alignment", "add alignment metrics", "fix representation collapse", "add gap regularization", "implement SigLIP loss", "add temporal binding", "fix spatial correspondence", or mentions InfoNCE, contrastive alignment, projection head architecture, modality gap phenomenon, cross-modal similarity, alignment temperature, or shared semantic space in the cognitive pipeline.

evaluation-benchmarks

This skill should be used when the user asks to "evaluate the model", "run benchmarks", "compute metrics", "measure accuracy", "test on MNIST", "compute F1 score", "generate confusion matrix", "evaluate few-shot", "measure anomaly detection", "run cognitive benchmarks", "compare model variants", "create evaluation report", "set up eval harness", or needs guidance on evaluation protocols, metrics computation, benchmark harnesses, or performance reporting for the brain_ai system.

brainai-spiking-core-lif-family-surrogate-gradient-training

This skill should be used when the user asks to "fix spiking neuron", "add a new neuron variant", "fix surrogate gradient", "debug SNN training", "fix SNN convergence", "add truncated BPTT", "fix state leakage", "implement explicit state", "add detach_state", "fix membrane explosion", "add refractory period", "fix gradient flow through spikes", "add learnable threshold", "add learnable beta", "fix mixed precision SNN", "validate spiking contracts", "debug firing rates", "fix dead neurons", "fix saturated neurons", "unify ConvSNN and MLP SNN unrolling", "add time unroll utility", "fix in-place ops in SNN", "clamp beta", "swap surrogate gradient", "add spike-frequency adaptation", "fix recurrent SNN", "debug membrane stats", or mentions LIFNeuron, SpikingState, surrogate gradient, snn_unroll, truncated BPTT, membrane potential, firing rate, or spike sparsity in the BrainAI cognitive architecture.

dreamerv3-style-rssm-world-model

This skill should be used when the user asks to "implement DreamerV3 RSSM", "build a recurrent state space model", "create Block GRU sequence model", "implement unimix categorical", "add symlog twohot prediction heads", "implement KL balancing loss", "free nats clipping", "world model loss function", "imagination rollout for actor-critic", "straight-through categorical estimator", "implement prior and posterior networks", "DreamerV3 world model", "symlog transform", "twohot encoding 255 bins", "prevent codebook collapse", "DreamerV3 numerical stability", "scale-invariant reward prediction", "world model imagination", "RSSM prior posterior KL divergence", "Block GRU with RMSNorm", "categorical latent state 32x32", or needs guidance on implementing DreamerV3-style world models with the full set of numerical stability techniques (symlog, twohot, unimix, KL balancing).

v-jepa-2-vision-transformer

This skill should be used when the user asks to "implement ViT for V-JEPA", "create vision transformer", "add RoPE to transformer", "implement SwiGLU", "configure ViT variant", "add cross-attention", "implement attentive pooler", "weight initialization for ViT", "sinusoidal positional embeddings", "3-axis rotary position embeddings", "transformer block with drop path", "multi-head self-attention", "patch embedding", or needs guidance on Vision Transformer architecture, positional encoding strategies, or transformer building blocks for V-JEPA 2.

continual-learning-guard-ewc-si-progressive-networks-replay

This skill should be used when the user asks to "prevent catastrophic forgetting", "elastic weight consolidation", "EWC regularization", "progressive networks", "continual learning strategy", "knowledge distillation for retention", "replay buffer memory", "task boundary detection", "fisher information matrix", "synaptic intelligence", "PackNet pruning", "memory-aware synapses", "add continual learning guard", "implement EWC penalty", "add experience replay", "implement progressive columns", "add Fisher diagonal computation", "implement reservoir sampling", "add knowledge distillation loss", "implement task-free continual learning", "add online EWC", "implement generative replay", "add PackNet iterative pruning", "implement synaptic intelligence path integral", or mentions catastrophic forgetting, continual learning, lifelong learning, sequential task training, knowledge retention, task interference, Fisher information regularization, or Phase 8 continual-learning pipeline in the cognitive architecture.

active-inference-agent-generative-model-efe-empowerment

This skill should be used when the user asks to "implement active inference", "add EFE computation", "implement expected free energy", "add empowerment estimation", "implement generative model", "add latent state encoder", "implement transition model", "add preference model", "implement planning rollouts", "add CEM planner", "implement amortized policy", "add pymdp backend", "implement offline RL", "add Minari integration", "implement pragmatic value", "add epistemic value", "implement instrumental value", "add action selection", "implement belief updating", "add world model training", "implement POMDP planning", "add rollout engine", "implement latent imagination", "add horizon normalization", "implement cross-entropy method planning", "add preference learning", "implement variational empowerment", or mentions active inference, expected free energy decomposition, POMDP planning, empowerment estimation, latent imagination, or decision-as-inference in the cognitive pipeline.

inference-optimization

This skill should be used when the user asks to "optimize inference", "speed up predictions", "add caching", "batch inference", "async inference", "reduce inference latency", "profile inference", "memory efficient inference", "inference pipeline", "warm up model", "KV cache", "inference throughput", "latency benchmark", "optimize forward pass", or needs guidance on inference performance optimization, caching strategies, batch processing, async execution, or latency profiling for the brain_ai system.

data-pipeline-loaders

This skill should be used when the user asks to "load a dataset", "create data loaders", "add data augmentation", "preprocess input data", "set up training data", "create validation splits", "register a dataset", "configure data pipeline", "handle multi-modal data loading", "load MNIST/CIFAR/ImageNet", "load event camera data", "load sequence data", "set up few-shot episodes", "create a dataset registry", or needs guidance on data loading, preprocessing, augmentation, or dataset management for the brain_ai 7-phase training pipeline.