Skill Claude CodeCodex
Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.
82 11d ago A 57 tokens
original MIT
ai-evals
26Skill Claude CodeCodex
Designs trustworthy LLM/agent evals and optimization loops. Use when building graders, calibrating judges, choosing eval/fine-tune methods, thresholds, or fixing noisy scores.
82 11d ago A 41 tokens
original MIT
Skill Claude CodeCodex
LLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when optimizing throughput, tail latency, or serving cost.
82 11d ago A 39 tokens
original MIT
ai-llm
28Skill Claude CodeCodex
Guides the LLM lifecycle from strategy to deployment. Use when planning, comparing, fine-tuning, distilling, compressing, migrating, or operating LLM systems.
82 11d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.
82 11d ago A 42 tokens
original MIT
Skill Claude CodeCodex
ML and data science workflows - EDA, feature engineering, modelling, evaluation, and production handoff. Use when exploring data or building models.
82 11d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Time-series forecasting with temporal validation, panel models, probabilistic forecasts, and TS foundation models. Use when modeling ordered observations.
82 11d ago A 31 tokens
original MIT
ai-mlops
32Skill Claude CodeCodex
Operates production MLOps for ML, LLM, and agent systems. Use when designing deployment, monitoring, retraining, incident response, or GenAI security workflows.
82 11d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.
82 11d ago A 53 tokens
original MIT
Skill Claude CodeCodex
Builds a transformer/GPT and BPE tokenizer from scratch. Use when implementing autograd, self-attention, a nanoGPT-style pretraining loop, or a byte-level tokenizer.
82 11d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.
82 11d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.
82 11d ago A 43 tokens
original MIT
ai-rag
37Skill Claude CodeCodex
Designs retrieval-augmented generation and search systems. Use when choosing retrieval, chunking, hybrid search, grounding, or RAG evaluation patterns.
82 11d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.
82 11d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Builds vector-brain implementations for repos, docs hubs, and compliance corpora. Use when creating pgvector retrieval brains with scripts, SQL, manifests, and evals.
82 11d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Builds production voice bots and IVR with Python STT/TTS pipelines. Use when designing telephony, streaming audio, latency budgets, or voice quality monitoring.
82 11d ago A 39 tokens
original MIT
Skill Claude CodeCodex
Builds analytics engineering layers for metrics, contracts, and BI-ready models. Use when shaping dbt or SQLMesh marts, metric governance, lineage, or data quality.
82 11d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Designs lakehouse platforms across Iceberg, Delta, Hudi, and Paimon. Use when choosing catalogs, CDC paths, query engines, governance, or cost controls.
82 11d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Automates Metabase cards, dashboards, Remote Sync, embedding, tenants, and the Agent API/MCP server for AI workflows. Use when scripting, promoting, or embedding Metabase content.
82 11d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Diagnoses and tunes SQL for OLTP workloads on PostgreSQL, MySQL, and SQL Server. Use when tuning queries, reading plans, indexing, or fixing lock contention.
82 11d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Designs streaming platforms for Kafka, Flink, CDC, and lakehouse ingestion. Use when planning event backbones, CDC pipelines, schema governance, or real-time lakehouse delivery.
82 11d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Measures AI coding impact and extension robustness. Use when tracking delivery, quality trajectories, cost, experience, pilots, scorecards, or leadership reporting.
82 11d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Designs durable API contracts across REST, GraphQL, gRPC, tRPC, and AsyncAPI. Use when specifying interfaces, auth, versioning, errors, rate limits, or agent APIs.
82 11d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Builds per-repo code graphs in JSON and markdown-ready derived artifacts. Use when you need blast radius, symbol-level maps, import graphs, inheritance, or test links.
82 11d ago A 41 tokens
original MIT