AI & LLM App Development Skills for Claude Code, Codex & AI Agents

Yao Meta Skill

YAO

Create, revise, package, and evaluate agent Skills from workflows, prompts, SOPs, and scripts using a routed review process.

• skills
• workflow-design
• evaluation

Skill Optimizer

Matteo Collina

Improve Skill activation and clarity using scenario comparisons and regression checks.

• agent skills
• evaluation

AI Evals Skills

AI Evals Course

Practical workflows for assessing and improving product-specific LLM evaluations.

• ai evaluation

Free LLM API Setup

mnfst

Find free LLM API options and follow provider-specific key and endpoint setup instructions.

• llm
• api-configuration

Eval Audit

AI Evals Course

Audit an LLM evaluation pipeline for missing error analysis, unvalidated judges, data leakage and stale checks.

• llm evaluation
• ai evaluation

TimesFM Forecasting

google-research

Forecast univariate time series with Google TimesFM, including uncertainty estimates and optional covariates.

• data-analysis
• machine-learning

Ml Engineering

stas00

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference…

• machine-learning
• development

ML Engineering Skills

stas00

Apply practical large-model training and operations guidance, and evaluate GPU cluster performance and readiness.

• machine-learning
• benchmarking

Evaluate Cluster

stas00

Evaluates an ML GPU cluster for a cloud trial or acceptance test: environment dump, isolated newest PyTorch, matmul FLOPS (MAMF/MSMF) on every GPU while the others compute, intra-node all-reduce bandwidth and per-call latency of every collective, the same inter-node on every node you were given (omit those sections if there is only one node), fio on local disk and shared FS, dated markdown report.

• benchmarking
• machine-learning