NeVibeCode · 2,385 items
Skills for AI and ML
Skills for AI and ML: what each one does, an install command and example prompts.
pathway-enrichment skill Runs pathway and gene-set enrichment analysis on gene lists or ranked data, finds over-represented GO terms, KEGG, Reactome, MSigDB. Needed after differential expression, CRISPR screens, or clustering.
CX Codex +1
1,400installs
experimental-design skill Helps you plan an experiment before collecting data: pick a design, randomize, block nuisance variation and lay out factor combinations. Useful while the study is still on paper.
CX Codex +1
1,400installs
liteparse skill Local document parser that returns text with bounding boxes. Use it for layout-aware RAG, OCR on scanned papers, and batch ingestion of research folders.
CX Codex +1
1,400installs
huggingface-datasets skill Guides Dataset Viewer API work for inspecting Hugging Face datasets, rows, statistics, and parquet links. Use it when an agent needs read-only dataset exploration.
CX Codex +1
2,400installs
Agent Cost Report skill 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.
CX Codex +1
381installs
langgraph skill A skill for building production-grade agents with deliberate structure. Design graph topology, manage state, add cycles and branches, persist progress via checkpoints, and loop humans back into decisions.
CX Codex +1
1,300installs
ai-engineer skill 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.
CX Codex +1
1,300installs
marimo-pair skill Connects an agent to a live marimo notebook runtime to inspect variables and commit cell updates safely.
CX Codex +1
12,700installs
huggingface-gradio skill This skill helps you build and modify Python Gradio interfaces for machine learning demos. It provides patterns for layouts, UI components, and chatbot workflows.
CX Codex +1
2,300installs
skill-creator skill 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.
CX Codex +1
431installs
statistical-power skill Calculates how many observations your study needs to reliably detect a meaningful effect. Supports protocol planning, grant submissions, and pre-registration — from basic t-tests to complex mixed models and survival analysis.
CX Codex +1
1,300installs
cli-anything-notebooklm skill Experimental harness to manage Google NotebookLM through a local CLI. It lets agents list notebooks, query sources, generate artifacts, and download files.
CX Codex +1
811installs
phoenix-tracing
official skill This skill guides OpenInference tracing for LLM apps with Phoenix. Use it to set up instrumentation, define custom spans, or prepare tracing for production.
1,000installs
phoenix-evals
official skill Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output.
1,000installs
phoenix-cli
official skill 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.
1,000installs
autonomous-agents skill A skill about building autonomous agents that stay reliable: ReAct and plan-execute loops, goal decomposition, reflection, and the math of compounding step failures.
CX Codex +1
1,200installs
ai-prompt-research skill This skill discovers questions people ask ChatGPT about your niche, shows how the model answers them, and reveals which sites it cites. Learn where your brand appears in AI responses and where competitors show up instead.
CX Codex +1
874installs
huggingface-papers skill 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.
CX Codex +1
2,200installs
huggingface-llm-trainer skill Runs language and vision model fine-tuning on Hugging Face Jobs with TRL or Unsloth and converts checkpoints to GGUF without local GPUs.
CX Codex +1
2,200installs
vision-sft skill This skill configures supervised fine-tuning for vision-language models on image and text data. Use it when adapting a VLM to a new visual domain.
CX Codex
2,600installs
trace-to-training-data skill Turns graded traces and production logs into SFT examples and DPO pairs. Use it after evaluation runs have verdicts and rewards ready for dataset conversion.
CX Codex
2,600installs
quantized-export skill Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model.
CX Codex
2,600installs
preference-optimization skill Selects and tunes model alignment methods: DPO, ORPO, KTO, or SimPO. Use it when training on preference pairs or binary thumbs-up feedback.
CX Codex
2,600installs
lora-qlora-recipes skill This skill configures LoRA and QLoRA supervised fine-tuning, from target modules to rank and learning rate. Use it when reviewing an adapter training setup.
CX Codex
2,600installs
grpo-rlvr-training skill Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. Useful when evaluating models with code execution, unit tests, or strict schemas.
CX Codex
2,600installs
finetuning-method-selection skill This skill decides whether fine-tuning is needed and routes the task to a method based on its data and goal. Use it before a training run.
CX Codex
2,600installs
eval-harness-first skill Builds the evaluation harness before fine-tuning with goldens, graders, judge calibration, and a base-model baseline. Useful for tracking regressions.
CX Codex
2,600installs
dataset-curation skill This skill formats and checks datasets for model fine-tuning. Use it to prepare data for SFT or preference training before a run.
CX Codex
2,600installs
checkpoint-promotion skill Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model.
CX Codex
2,600installs
gke-ai-troubleshooting-node-unresponsive-timeout
official skill Diagnoses unresponsive GKE TPU and GPU nodes stuck in NodeStatusUnknown. Pinpoints kernel panics and missing kubelet heartbeats when node auto-repair is disabled.
CX Codex
810installs
mmx-cli skill Teaches your agent to use the MiniMax CLI directly from the terminal. Helps generate text, images, video, speech, and music inside coding workflows.
CX Codex +1
1,600installs
minimax-music-gen skill 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.
CX Codex +1
1,600installs
spark-training-gotchas skill Diagnoses ten known ML training failure modes on NVIDIA DGX Spark GB10. It catches memory leaks, power throttling, and CUDA mismatches early.
CX Codex
2,500installs
spark-memory-thermal-ops skill This skill plans memory headroom and tracks heat on NVIDIA DGX Spark during long ML jobs. Use it for unified-memory OOMs and mid-run slowdowns.
CX Codex
2,500installs
spark-environment-setup skill Sets up ML training and inference environments on NVIDIA DGX Spark with GB10, aarch64, and CUDA 13. Resolves wheel ABI mismatches and import errors.
CX Codex
2,500installs
transformers-js skill This skill helps run machine learning models from JavaScript and TypeScript for text, images, audio, and multimodal tasks in browser or server-side code.
CX Codex +1
2,100installs
arbor skill Runs an autonomous optimization loop using hypothesis trees for models, code, and harnesses. Useful when organizing dozens of experimental trials without losing past findings.
CX Codex +1
1,200installs
videoagent-video-studio skill Generates short clips from a text prompt or an image. Handy when you need a quick video, want to animate a photo, or keep a consistent style across shots.
CX Codex +1
10,500installs
ask skill Skill to route prompts through local CLIs of different models (Claude, Codex, Gemini, Cursor and others) and save results as artifacts.
CX Codex +1
721installs
game-ai skill Designs NPC decision-making, behavior trees, steering forces, and A* pathfinding. Useful when building game enemy logic across engines.
CX Codex +1
7,700installs
521–560 of 2,385
