ML Ops
Machine learning operations
veo3-prompter
by leegonzales
Craft professional video prompts for Google Veo 3.1 using cinematic techniques, audio direction, and timestamp choreography. Use when generating AI videos, creating video prompts, or working with Veo 3.
openrouter-typescript-sdk
by OpenRouterTeam
Complete reference for integrating with 300+ AI models through the OpenRouter TypeScript SDK using the callModel pattern
codex-config
by outfitter-dev
This skill should be used when configuring Codex CLI, setting up profiles, or when "config.toml", "sandbox mode", "Codex config", or "approval policy" are mentioned.
ml-ablation-design
by dongzhuoyao
Use when designing ablation studies to compare model components, loss functions, or architectural choices. Covers synthetic data experiments, variant loops, production metrics, and W&B grouping. Triggers: "ablation", "ablation study", "variant comparison", "controlled experiment", "synthetic data experiment"
hydra-experiment-config
by dongzhuoyao
Use when structuring ML experiment configs with Hydra, adding new config groups, or debugging config resolution. Applies to any project using Hydra for hyperparameter management. Triggers: "Hydra", "config", "yaml config", "OmegaConf", "config groups", "defaults list", "config override"
slurm-gpu-training
by dongzhuoyao
Use when running ML training on HPC clusters with Slurm, including job submission, environment setup, monitoring, and failure triage. Applies to any GPU training workload on Slurm-managed clusters. Triggers: "sbatch", "srun", "Slurm", "SBATCH", "job submission", "HPC", "cluster", "walltime", "squeue"
multi-model-meta-analysis
by petekp
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.
gpu-training-acceleration
by dongzhuoyao
Use when optimizing PyTorch training speed or memory on CUDA GPUs — global flags, torch.compile, fused optimizers, mixed precision, gradient checkpointing, kernel fusion, memory layout, or latent-space training. Applies to any PyTorch training workload. Triggers: "torch.compile", "TF32", "fused optimizer", "mixed precision", "bf16", "fp16", "gradient checkpointing", "Triton kernel", "CUDA flags", "GPU slow", "GPU memory"
fail-fast-ml-engineering
by dongzhuoyao
Use when designing ML training pipelines, data loaders, or inference systems. Enforces engineering discipline — no silent fallbacks, explicit errors on critical paths, config as single source of truth. Triggers: "silent failure", "fallback", "preflight", "assertion", "error handling", "fail fast", "config truth"
model-first-reasoning
by petekp
Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.
wandb-experiment-tracking
by dongzhuoyao
Use when integrating W&B experiment tracking into ML training pipelines, including logging strategy, run configuration, and online/offline mode management. Triggers: "W&B", "wandb", "weights and biases", "experiment logging", "wandb.log", "wandb.init", "training dashboard"
generate-worldgen
by jujumelona
Generate only explicitly requested mod-owned structures, biomes, dimensions and feature resources inside the
runtime-playtest
by jujumelona
Run a disposable server/client for the approved artifact and collect bounded, observable runtime evidence.
eval
by williamwue
"Compare workflow variants with blinded outputs and a frozen rubric."
eval
by williamwue
"Run a blinded, repeatable comparison of workflow or model variants using real artifacts and a frozen rubric."
ai-engineer
by aibangjuxin
You are a highly skilled AI Engineer specializing in the practical application of machine learning models. You are an expert in Python and popular AI/ML frameworks like TensorFlow, PyTorch, and scikit-learn. You excel at data preprocessing, model training, evaluation, and deployment.
statistical-analysis
by YuukiAS
Plan and report statistical analyses: estimand framing, test/model choice, assumption checks, power/sensitivity notes, effect sizes, uncertainty, and reproducible reporting.
release-security
by jujumelona
Release only artifact-identical validated source, JAR, resources, provenance, licenses, and receipts.
generate-fabric-core
by jujumelona
Generate the approved Fabric target core project and registrations.
select-compatible-ai-technique
by jujumelona
Research, compare, and fail-closed gate request-derived AI, agent, speech, translation, or consented voice-adaptation
principle-never-block-on-the-human
by williamwue
"Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions."
principle-model-the-domain
by williamwue
"Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals."
inspect-existing-project
by jujumelona
Inventory an existing source/release archive and index its source without execution.
bayesian-modeling
by YuukiAS
Bayesian and statistical modeling workflows with PyMC, diagnostics, simulation, and model reporting.