NeVibeCode · 2,385 items
Skills for AI and ML
Skills for AI and ML: what each one does, an install command and example prompts.
video-summarizer skill Downloads video and audio via yt-dlp, extracts subtitles or transcribes speech with faster-whisper, and generates an AI summary in Markdown.
CX Codex +1
524installs
gpu-kubernetes-operations skill A skill for running GPU-backed Kubernetes clusters: pod scheduling, MIG partitioning, time-slicing, DCGM monitoring and cost controls.
CX Codex +1
329installs
mlflow-onboarding skill The skill figures out whether your project is GenAI or classic ML and walks you through the matching MLflow quickstart. Handy when you need tracking or tracing but don't know where to begin.
CX Codex +1
1,100installs
character-design skill Create character images and video while keeping a character’s defining features consistent. The skill covers reference sheets, expression sets, outfit changes, and edits based on existing images.
CX Codex +1
449installs
llm-app-security skill Security controls and validation rules to protect chatbots, RAG pipelines, and SaaS AI features from prompt injection, leaks, and abuse.
CX Codex +1
327installs
model-serving-kubernetes skill Deploys ML models and LLMs on Kubernetes using KServe and NVIDIA Triton Inference Server. Handles canary rollouts, traffic splitting, and GPU scheduling.
CX Codex +1
327installs
ai-sre-incident-response skill An SRE skill for LLM systems: provider outages, quality regressions, token cost spikes and guardrail violations.
CX Codex +1
328installs
ai-security-hardening skill Hardens production LLM deployments against prompt injection, data exfiltration, and supply chain attacks. Useful when securing model endpoints or preparing for SOC2 compliance.
CX Codex +1
326installs
llmquant-macro skill A router skill for macro work: builds cross-indicator dashboards, prepares central-bank meeting previews, and maps macro data onto portfolio impact.
CX Codex +1
531installs
ai-pipeline-orchestration skill A skill that helps the agent build pipelines for data ingestion, model training, batch inference and RAG indexing on Prefect, Airflow or Dagster.
CX Codex +1
325installs
rag-infrastructure skill A skill for building RAG infrastructure: document ingestion, embeddings, vector stores, hybrid search and grounded LLM answers.
CX Codex +1
325installs
databricks-dbsql skill Equips your coding agent with advanced Databricks SQL patterns, pipe syntax, H3 geospatial functions, and embedded LLM queries.
CX Codex +1
364installs
extension-inference skill The skill spells out the only supported way to wire an LLM into a Caffeine app: the caffeineai-inference-client package with Config.fromEnv, no user-pasted key.
CX Codex +1
11,900installs
openrouter-generations skill Inspect OpenRouter requests by generation ID to review token costs, latency, fallback routing, and saved prompts.
CX Codex +1
302installs
generate-image skill Generates images from text prompts using OpenAI or Stability AI. Useful when your coding agent needs to create logos, banners, or illustrations directly in the project.
CX Codex +1
343installs
fal-recipes skill Ready-made multi-step pipelines for producing commercials, cinematic shots, photoreal portraits, lip-sync videos, and image restoration through fal.ai.
CX Codex +1
440installs
openrouter-analytics skill Inspects OpenRouter costs, token counts, and latency through natural-language prompts. Useful when auditing API bills or finding expensive models.
CX Codex +1
300installs
kelly-criterion skill A skill that works out position size with the Kelly criterion: the formula, fractional variants, edge estimation and a correlation adjustment.
CX Codex +1
532installs
neo4j-graphrag-skill skill A skill that walks you through building GraphRAG retrieval pipelines on Neo4j with the neo4j-graphrag package: retriever choice, Cypher fragments, LLM wiring.
CX Codex +1
1,100installs
llm-fine-tuning skill Configures infrastructure for fine-tuning open LLMs with QLoRA, LoRA, and DeepSpeed. Useful when training models on proprietary domain datasets.
CX Codex +1
318installs
llm-caching skill Adds multi-layer LLM request caching across Redis, GPTCache, and provider APIs. Reduces API costs by 30–70% when queries repeat often.
CX Codex +1
317installs
rag-observability-evals skill A skill for monitoring and evaluating RAG systems: retrieval quality metrics, groundedness checks, hallucination detection and regression testing.
CX Codex +1
318installs
migrating-ai-sdk-to-common-ai skill Moves Airflow projects off airflow-ai-sdk onto the official apache-airflow-providers-common-ai 0.4.0+ provider. Useful when LLM decorators and model config have to move to connections.
CX Codex +1
348installs
llmops-platform-engineering skill A skill for building an internal LLM platform: CI/CD with evaluation gates, model promotion, canary deploys and rollback.
CX Codex +1
315installs
vllm-server skill Deploys and configures vLLM inference servers with continuous batching and tensor parallelism. Use it to host open-source LLMs behind an OpenAI-compatible API.
CX Codex +1
314installs
llmquant-data skill A router skill for LLMQuant Data requests: it reads the task and opens the right workflow for SEC filings, 13F holders or macro snapshots.
CX Codex +1
511installs
feature-engineering skill Builds features from market data for ML trading models: price, volume, microstructure, on-chain. Useful when a model trained on raw candles keeps overfitting.
CX Codex +1
518installs
signal-classification skill A skill that builds ML trading signal classifiers on XGBoost and LightGBM, with walk-forward validation, SHAP importance and threshold tuning.
CX Codex +1
517installs
prompt-injection skill This skill audits apps with AI features for prompt injection, permission bypass and system prompt leaks. Useful once an LLM or agent lands in your codebase.
CX Codex +1
372installs
literature-review skill Runs a systematic literature review on an academic topic: searches papers, triages results, reads key works and writes a themed report.
CX Codex +1
732installs
llmquant-etfs skill Router skill that sends ETF questions to the right workflow: holdings, overlap, concentration, issuer snapshot, theme exposure.
CX Codex +1
507installs
ai-inference-service-mesh skill A skill that wires Istio and Linkerd into your inference stack: mTLS, canary releases, access policies and GPU backend protection.
CX Codex +1
310installs
vector-database-ops skill A skill for deploying and tuning vector databases: Qdrant, Weaviate, pgvector, Pinecone. Useful once RAG or semantic search hits production.
CX Codex +1
310installs
mac-mini-llm-lab skill Sets up an Apple Silicon Mac mini as an always-on local LLM inference server with Ollama, MLX, launchd auto-start, and remote networking.
CX Codex +1
309installs
multi-tenant-llm-hosting skill A skill that walks your agent through building shared LLM inference for several teams or customers: tenant isolation, quotas, billing attribution and noisy-neighbor protection.
CX Codex +1
309installs
financial-analysis-agent skill Helps build agents for fundamental stock evaluation and risk calculation. Practical for developing robo-advisors or investment trackers.
CX Codex +1
1,300installs
trading-visualization skill Builds trading charts: candlesticks, equity curves, drawdowns, correlation heatmaps and return distributions. Useful when you need to review a strategy or put together a report.
CX Codex +1
509installs
inkos-multi-agent-novel-writing skill Coordinates a multi-agent CLI pipeline to draft, validate, and audit novel chapters. Useful for managing long-form fiction projects with strict continuity.
CX Codex +1
2,800installs
langgraph skill A skill with 41 rules for LangGraph 1.x in Python: state schemas, node timeouts, routing, supervisors, checkpoints. Useful when you build a pipeline or a multi-agent system.
CX Codex +1
359installs
faster-whisper skill Run local speech-to-text with CTranslate2 Whisper without API charges. It generates subtitles, diarizes speakers, and transcribes YouTube clips.
CX Codex +1
1,800installs
1,641–1,680 of 2,385
