# Skills for AI and ML Skills for AI and ML: what each one does, an install command and example prompts. 2465 cards · page 14 of 62 - HTML: https://affpapa.org/en/nevibecode/skills/topic/ai-ml?page=14 - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [pathway-enrichment](https://affpapa.org/en/nevibecode/skills/pathway-enrichment.md) — skill · K-Dense-AI · Claude Code, Codex, Cursor +3 · 1400 installs — Runs pathway and gene-set enrichment analysis on gene lists or ranked data, finds over-represented GO terms, KEGG, Reactome, MSigDB. - [experimental-design](https://affpapa.org/en/nevibecode/skills/experimental-design.md) — skill · K-Dense-AI · Claude Code, Codex, Cursor +3 · 1400 installs — Helps you plan an experiment before collecting data: pick a design, randomize, block nuisance variation and lay out factor combinations. - [liteparse](https://affpapa.org/en/nevibecode/skills/k-dense-ai-liteparse.md) — skill · K-Dense-AI · Claude Code, Codex, Cursor +3 · 1400 installs — Local document parser that returns text with bounding boxes. - [huggingface-datasets](https://affpapa.org/en/nevibecode/skills/huggingface-datasets.md) — skill · huggingface · Claude Code, Codex, Cursor +3 · 2400 installs — Guides Dataset Viewer API work for inspecting Hugging Face datasets, rows, statistics, and parquet links. - [Agent Cost Report](https://affpapa.org/en/nevibecode/skills/agent-cost-report.md) — skill · thedotmack · Claude Code, Codex, Cursor +3 · 381 installs — Turns Claude Code transcripts into a cost and failure report: tokens measured, dollars priced at OpenRouter list rates, output as HTML, PDF, JSON and CSV. - [langgraph](https://affpapa.org/en/nevibecode/skills/sickn33-langgraph.md) — skill · sickn33 · Claude Code, Codex, Cursor +3 · 1300 installs — A skill for building production-grade agents with deliberate structure. - [ai-engineer](https://affpapa.org/en/nevibecode/skills/ai-engineer.md) — skill · sickn33 · Claude Code, Codex, Cursor +3 · 1300 installs — A skill that puts the agent in the role of an LLM engineer, then works from success metrics to RAG pipelines, agent orchestration and the production plumbing around them. - [marimo-pair](https://affpapa.org/en/nevibecode/skills/marimo-pair.md) — skill · marimo-team · Claude Code, Codex, Cursor +3 · 12700 installs — Connects an agent to a live marimo notebook runtime to inspect variables and commit cell updates safely. - [huggingface-gradio](https://affpapa.org/en/nevibecode/skills/huggingface-gradio.md) — skill · huggingface · Claude Code, Codex, Cursor +3 · 2300 installs — This skill helps you build and modify Python Gradio interfaces for machine learning demos. - [skill-creator](https://affpapa.org/en/nevibecode/skills/tldraw-skill-creator.md) — skill · tldraw · Claude Code, Codex, Cursor +3 · 431 installs — A guide the agent follows while building a skill: what belongs in SKILL.md, what goes into scripts/, references/ and assets/, and how to keep the whole thing short. - [statistical-power](https://affpapa.org/en/nevibecode/skills/statistical-power.md) — skill · K-Dense-AI · Claude Code, Codex, Cursor +3 · 1300 installs — Calculates how many observations your study needs to reliably detect a meaningful effect. - [cli-anything-notebooklm](https://affpapa.org/en/nevibecode/skills/cli-anything-notebooklm.md) — skill · HKUDS · Claude Code, Codex, Cursor +3 · 811 installs — Experimental harness to manage Google NotebookLM through a local CLI. - [phoenix-tracing](https://affpapa.org/en/nevibecode/skills/phoenix-tracing.md) — skill (official GitHub) · oss@arize.com · GitHub Copilot · 1000 installs — This skill guides OpenInference tracing for LLM apps with Phoenix. - [phoenix-evals](https://affpapa.org/en/nevibecode/skills/phoenix-evals.md) — skill (official GitHub) · oss@arize.com · GitHub Copilot · 1000 installs — Build and run evaluators for AI and LLM applications with Phoenix. - [phoenix-cli](https://affpapa.org/en/nevibecode/skills/phoenix-cli.md) — skill (official GitHub) · arize-ai · GitHub Copilot · 1000 installs — A GitHub Copilot skill that drives the Phoenix CLI to pull traces, spans and sessions, then turns what it finds into a failure taxonomy for your LLM app. - [autonomous-agents](https://affpapa.org/en/nevibecode/skills/sickn33-autonomous-agents.md) — skill · sickn33 · Claude Code, Codex, Cursor +3 · 1200 installs — A skill about building autonomous agents that stay reliable: ReAct and plan-execute loops, goal decomposition, reflection, and the math of compounding step failures. - [ai-prompt-research](https://affpapa.org/en/nevibecode/skills/ai-prompt-research.md) — skill · every-app · Claude Code, Codex, Cursor +3 · 874 installs — This skill discovers questions people ask ChatGPT about your niche, shows how the model answers them, and reveals which sites it cites. - [huggingface-papers](https://affpapa.org/en/nevibecode/skills/huggingface-papers.md) — skill · huggingface · Claude Code, Codex, Cursor +3 · 2200 installs — Pulls the paper ID out of a Hugging Face or arXiv link, reads the page as markdown, and fetches authors, models and datasets from the papers API. - [huggingface-llm-trainer](https://affpapa.org/en/nevibecode/skills/huggingface-llm-trainer.md) — skill · huggingface · Claude Code, Codex, Cursor +3 · 2200 installs — Runs language and vision model fine-tuning on Hugging Face Jobs with TRL or Unsloth and converts checkpoints to GGUF without local GPUs. - [vision-sft](https://affpapa.org/en/nevibecode/skills/vision-sft.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — This skill configures supervised fine-tuning for vision-language models on image and text data. - [trace-to-training-data](https://affpapa.org/en/nevibecode/skills/trace-to-training-data.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Turns graded traces and production logs into SFT examples and DPO pairs. - [quantized-export](https://affpapa.org/en/nevibecode/skills/quantized-export.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. - [preference-optimization](https://affpapa.org/en/nevibecode/skills/preference-optimization.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Selects and tunes model alignment methods: DPO, ORPO, KTO, or SimPO. - [lora-qlora-recipes](https://affpapa.org/en/nevibecode/skills/lora-qlora-recipes.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — This skill configures LoRA and QLoRA supervised fine-tuning, from target modules to rank and learning rate. - [grpo-rlvr-training](https://affpapa.org/en/nevibecode/skills/grpo-rlvr-training.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. - [finetuning-method-selection](https://affpapa.org/en/nevibecode/skills/finetuning-method-selection.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — This skill decides whether fine-tuning is needed and routes the task to a method based on its data and goal. - [eval-harness-first](https://affpapa.org/en/nevibecode/skills/eval-harness-first.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Builds the evaluation harness before fine-tuning with goldens, graders, judge calibration, and a base-model baseline. - [dataset-curation](https://affpapa.org/en/nevibecode/skills/dataset-curation.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — This skill formats and checks datasets for model fine-tuning. - [checkpoint-promotion](https://affpapa.org/en/nevibecode/skills/checkpoint-promotion.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2600 installs — Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model. - [gke-ai-troubleshooting-node-unresponsive-timeout](https://affpapa.org/en/nevibecode/skills/gke-ai-troubleshooting-node-unresponsive-timeout.md) — skill (official Google) · google · Claude Code, Gemini CLI, Codex · 810 installs — Diagnoses unresponsive GKE TPU and GPU nodes stuck in NodeStatusUnknown. - [mmx-cli](https://affpapa.org/en/nevibecode/skills/minimax-ai-mmx-cli.md) — skill · MiniMax-AI · Claude Code, Codex, Cursor +3 · 1600 installs — Teaches your agent to use the MiniMax CLI directly from the terminal. - [minimax-music-gen](https://affpapa.org/en/nevibecode/skills/minimax-music-gen.md) — skill · MiniMax-AI · Claude Code, Codex, Cursor +3 · 1600 installs — A Claude Code skill that turns a description into an MP3 — vocals, instrumental or a cover — through the MiniMax Music API and the mmx tool. - [spark-training-gotchas](https://affpapa.org/en/nevibecode/skills/spark-training-gotchas.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2500 installs — Diagnoses ten known ML training failure modes on NVIDIA DGX Spark GB10. - [spark-memory-thermal-ops](https://affpapa.org/en/nevibecode/skills/spark-memory-thermal-ops.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2500 installs — This skill plans memory headroom and tracks heat on NVIDIA DGX Spark during long ML jobs. - [spark-environment-setup](https://affpapa.org/en/nevibecode/skills/spark-environment-setup.md) — skill · Seth Hobson · Claude Code, Codex, Cursor · 2500 installs — Sets up ML training and inference environments on NVIDIA DGX Spark with GB10, aarch64, and CUDA 13. - [transformers-js](https://affpapa.org/en/nevibecode/skills/transformers-js.md) — skill · huggingface · Claude Code, Codex, Cursor +3 · 2100 installs — This skill helps run machine learning models from JavaScript and TypeScript for text, images, audio, and multimodal tasks in browser or server-side code. - [arbor](https://affpapa.org/en/nevibecode/skills/arbor.md) — skill · K-Dense-AI · Claude Code, Codex, Cursor +3 · 1200 installs — Runs an autonomous optimization loop using hypothesis trees for models, code, and harnesses. - [videoagent-video-studio](https://affpapa.org/en/nevibecode/skills/videoagent-video-studio.md) — skill · pexoai · Claude Code, Codex, Cursor +3 · 10500 installs — Generates short clips from a text prompt or an image. - [ask](https://affpapa.org/en/nevibecode/skills/yeachan-heo-ask.md) — skill · Yeachan-Heo · Claude Code, Codex, Cursor +3 · 721 installs — Skill to route prompts through local CLIs of different models (Claude, Codex, Gemini, Cursor and others) and save results as artifacts. - [game-ai](https://affpapa.org/en/nevibecode/skills/game-ai.md) — skill · gamedev-skills · Claude Code, Codex, Cursor +3 · 7700 installs — Designs NPC decision-making, behavior trees, steering forces, and A* pathfinding. Next: https://affpapa.org/en/nevibecode/skills/topic/ai-ml.md?page=15 ## Refine [python](https://affpapa.org/en/nevibecode/tag/python.md) · [llm](https://affpapa.org/en/nevibecode/tag/llm.md) · [image-generation](https://affpapa.org/en/nevibecode/tag/image-generation.md) · [video](https://affpapa.org/en/nevibecode/tag/video.md) · [research](https://affpapa.org/en/nevibecode/tag/research.md) · [rag](https://affpapa.org/en/nevibecode/tag/rag.md) · [cli](https://affpapa.org/en/nevibecode/tag/cli.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [machine-learning](https://affpapa.org/en/nevibecode/tag/machine-learning.md) · [audio](https://affpapa.org/en/nevibecode/tag/audio.md) · [pytorch](https://affpapa.org/en/nevibecode/tag/pytorch.md) · [api](https://affpapa.org/en/nevibecode/tag/api.md) ## Narrow this list Parameters: `?platform=`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md