ML Ops
Machine learning operations
Brand Name Comparison
by MaxGhenis
Use this skill when the user wants to compare multiple brand name fates side-by-side to divine which is destined for success.
browser-onnx
by thongnt0208
"Implements high-performance local machine learning inference in the browser using ONNX Runtime Web. Use this skill when the user needs privacy-first, low-latency, or offline AI capabilities (e.g., image classification, object detection, or NLP) without server-side processing."
Continual Learning Guard (EWC / SI / Progressive Networks / Replay)
by sovr610
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.
m09-domain
by lywa1998
"CRITICAL: Use for domain modeling. Triggers: domain model, DDD, domain-driven design, entity, value object, aggregate, repository pattern, business rules, validation, invariant, 领域模型, 领域驱动设计, 业务规则"
ai-ethics-review
by mohitagw15856
"Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations."
wandb-weave-ft-retrospective
by Haruk1y
Analyze W&B, Weave, and local fine-tuning evaluation artifacts, then produce a concrete next-run improvement plan with data, prompt, and training actions. Use after each SFT or eval cycle.
sparse-autoencoder-training
by majiayu000
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
rwkv-architecture
by majiayu000
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.
coloring-book
by bedardandy
Create a personalized printable kids' coloring book (PDF) starring specific children, family members, and pets doing their favorite things — themed pages or a story-mode narrative for ages 3-6. Use when the user asks for a coloring book, coloring pages, or a personalized activity/story book for kids. Triggers on "coloring book", "coloring pages", "make a book for [kid]", "story coloring book".
ai-image-generation
by Jackiexiao
"Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image"
pipeline-pattern-nodejs
by progmichaelkibenko
Implements the Pipeline design pattern in Node.js for data transformation. Use when the user mentions pipeline pattern, or when you need a fixed sequence of stages that each transform data and pass to the next—ETL, parsing, data processing, or any linear transformation flow that runs to completion.
hyperparams
by uiuc-kang-lab
Guide for hyperparameter selection — learning rate formulas, LoRA rank, batch size, group size, schedules, and model-specific tuning. Use when the user asks about learning rate, batch size, hyperparameter tuning, or how to configure training parameters.
Active Inference Agent (Generative Model + EFE + Empowerment)
by sovr610
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.
mech-interp
by Pranav-Karra-3301
Mechanistic interpretability skill for understanding neural network internals. Use when: (1) Working with TransformerLens, nnsight, or SAELens (2) Analyzing attention patterns, circuits, or features (3) Training or analyzing sparse autoencoders (SAEs) (4) Activation patching, logit lens, or direct logit attribution (5) Understanding model internals ("what is this head doing?") (6) Setting up a mech interp research project Triggers: "mech interp", "mechanistic interpretability", "TransformerLens", "SAE", "sparse autoencoder", "activation patching", "logit lens", "circuits", "features", "attention heads", "residual stream", "nnsight", "nnterp", "superposition", "polysemantic", "monosemantic", "ablation", "probing", "induction head"
mle-workflow
by anavvanzin
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Compiler & Kernel Fusion (torch.compile) Integration
by sovr610
This skill should be used when the user asks to "enable torch.compile", "add compilation to training", "kernel fusion", "TorchDynamo integration", "TorchInductor optimization", "reduce-overhead mode", "max-autotune mode", "fix graph breaks", "compile health check", "shape stabilization", "dynamic shapes for compile", "bucketing for torch.compile", "compile allowlist", "compile blocklist", "compile smoketest", "CUDA graphs for training", "maybe_compile wrapper", "debug recompiles", "TORCH_LOGS compile", "compile + DDP", "compile + FSDP", "torch.compiler.disable", or needs guidance on torch.compile integration, shape management, compilation debugging, or safe fallback patterns.
xiaoyuzhou-podcast-transcriber
by nanzhipro
"Downloads Xiaoyuzhou podcasts, transcribes using FunASR, and generates raw, structured, and optimized text files. Invoke when user provides a Xiaoyuzhou episode link."
angular-component-inputs
by araujomartin
Modern function-based component inputs and models using Angular Signals API. Trigger: When defining component inputs, when migrating from decorators, when working with reactive component APIs, when implementing two-way binding.
DreamerV3-Style RSSM World Model
by sovr610
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).
circleci-config-generator
by ehtbanton
Generate CircleCI configuration files with workflows, orbs, and deployment. Triggers on "create circleci config", "generate circleci configuration", "circleci pipeline", "circle ci setup".
minimax-h3-fast-master
by RobZombAI
Champion gold execution toolkit for MiniMax H3 / H3-Max Fast Master ultra-photorealistic video generation on Apple Silicon M5 Max (128GB Unified Memory). Combines 8-step / 5-step exact DPM++ 2M Trailing Flow, 50 full layers, dynamic int8 FC2 quantization, single-chunk and multi-chunk causal temporal lattice (T = 17n + 5), and zero-loss optical macro definition.
V-JEPA 2 Data Pipeline
by sovr610
This skill should be used when the user asks to "load video dataset", "implement video transforms", "data augmentation for V-JEPA", "video decoding with decord", "clip sampling", "frame padding", "RandAugment for video", "motion shift augmentation", "random erasing", "video normalization", "YAML config parsing", "dataset registry", "distributed sampler", "weighted sampling", "multi-source dataset", "video DataLoader", "worker seeding", or needs guidance on video data loading, augmentation pipelines, configuration management, or dataset engineering for V-JEPA 2.
tinker-api
by dinequickly
Guide for using the Tinker API for LLM training. Use when working with Tinker training workflows, RL environments, supervised fine-tuning, model sampling, rendering, or any Tinker API operations.
sqlalchemy
by Nomik94
SQLAlchemy 2.0 async infrastructure pattern reference. Use when: DB model definition, Base model setup, table mapping, relationship config, session management, AsyncSession, sessionmaker, connection pool, query patterns (select, join, subquery, pagination), Mixin (Timestamp, SoftDelete), N+1 prevention (selectinload, joinedload), transaction management, nested transaction, savepoint, generic repository pattern, BaseRepository[ModelType]. NOT for: domain entity design (domain-layer skill), Alembic migrations.