Skip to main content
NeVibeCode · 2,385 items

Skills for AI and ML

Skills for AI and ML: what each one does, an install command and example prompts.

workflow Vercel Inc. skill Builds durable, resumable tasks with the Vercel Workflow SDK when operations must survive server restarts or pause for external events. CX Codex +1 5,300installs mcp-developer https://github.com/Jeffallan skill A skill for building and debugging MCP servers and clients in TypeScript or Python, with tool schemas, transport setup and protocol checks in the inspector. CX Codex +1 4,200installs fine-tuning-expert https://github.com/Jeffallan skill A skill for LLM fine-tuning: prepares datasets, configures LoRA and QLoRA adapters, runs training and evaluates the result. CX Codex +1 4,200installs langchain-middleware langchain-ai skill Adds middleware hooks for LangChain agents: pauses execution before dangerous tool calls, lets a human approve, edit or reject the action, intercepts calls for logging and retry logic. CX Codex +1 16,200installs langfuse langfuse skill Equips your coding agent to inspect traces, manage prompts, and run evaluations in Langfuse. Useful when instrumenting LLM calls or building test datasets. CX Codex +1 19,900installs deep-agents-orchestration langchain-ai skill Guides setup of orchestration in Deep Agents: subagent delegation, todo planning, and human approval interrupts. CX Codex +1 16,100installs langchain-dependencies langchain-ai skill Provides verified package versions and dependency rules for LangChain, LangGraph, and LangSmith. Helps set up clean Python or TypeScript projects without version conflicts. CX Codex +1 16,000installs deep-agents-core langchain-ai skill Skill for building multi-step agents with task planning, context management, and task delegation. Built-in filesystem tools, persistent memory across sessions, and subagent spawning—configure, don't code. CX Codex +1 16,000installs ai-agents-architect sickn33 skill A skill that breaks an agent into parts: ReAct loop, planning, memory layers, multi-agent orchestration. Useful once your agent exists and you need to decide how it fails. CX Codex +1 1,500installs business-analyst sickn33 skill A skill that turns your agent into a business analyst: KPI frameworks, unit economics, A/B tests and exec-ready write-ups. CX Codex +1 1,500installs conversation-memory sickn33 skill Architectural patterns for LLM conversation memory: session buffers, persistent storage, and entity tracking. CX Codex +1 1,500installs context-window-management sickn33 skill A skill for managing LLM context windows through token counting, history summarization, trimming, and context routing. CX Codex +1 1,600installs backtesting-trading-strategies Jeremy Longshore skill Runs a trading strategy over historical data and reports risk metrics before any real capital is on the line. CX Codex +1 4,700installs ml-pipeline https://github.com/Jeffallan skill Sets up production-grade ML pipelines: configures MLflow experiment tracking, generates Kubeflow or Airflow DAGs, and validates training datasets. CX Codex +1 3,900installs gif-sticker-maker MiniMax-AI skill A skill that converts a photo into 4 animated GIF stickers in Funko Pop style with captions. Use it to create expressive stickers, emoji packs, or animated avatars for messengers. CX Codex +1 2,000installs V3 Deep Integration ruvnet skill This skill turns claude-flow into a specialized extension of agentic-flow@alpha per ADR-001. It drops duplicate modules and wires in SONA, Flash Attention and AgentDB. CX Codex +1 1,100installs AgentDB Learning Plugins ruvnet skill Generates and trains reinforcement learning plugins for autonomous agents across 9 algorithms using AgentDB. CX Codex +1 1,100installs AgentDB Advanced Features ruvnet skill Skill for distributed AgentDB systems: QUIC-synchronized nodes, multi-database management, custom distance metrics, and hybrid vector-plus-metadata search across AI agent networks. CX Codex +1 1,100installs AgentDB Performance Optimization ruvnet skill Skill for vector database optimization in AgentDB: reduce memory 4–32x via quantization, speed up search 150x via HNSW indexing, add caching and batch inserts. CX Codex +1 1,100installs ReasoningBank with AgentDB ruvnet skill Adds adaptive memory to coding agents using the AgentDB vector engine. Useful for recording agent execution paths, judging outcomes, and distilling recurring patterns. CX Codex +1 1,100installs V3 Performance Optimization ruvnet skill Skill for optimizing claude-flow v3 with Flash Attention, HNSW indexing, and comprehensive benchmarking. Achieves 150–12,500x search improvement and 50–75% memory reduction. CX Codex +1 1,100installs AgentDB Memory Patterns ruvnet skill This skill gives AI agents persistent memory: AgentDB stores session history, learns from conversations, and restores context between runs. CX Codex +1 1,100installs AgentDB Vector Search ruvnet skill A skill for fast semantic document retrieval using AgentDB's vector database. Use it for RAG systems, search engines, and knowledge bases where you need relevant results from large text collections. CX Codex +1 1,100installs ReasoningBank Intelligence ruvnet skill Integrates adaptive learning into AI agents via ReasoningBank for pattern recognition and strategy choice. Useful for building self-improving agents and optimizing workflows. CX Codex +1 1,100installs flow-nexus-neural ruvnet skill Trains and deploys neural networks in isolated E2B sandboxes using Flow Nexus. Useful for running model training or inference directly through an AI coding agent. CX Codex +1 1,100installs remotion vercel-labs skill A skill that turns JSON timeline specs into ready-made video compositions via Remotion. Use it when you need to generate videos programmatically or assemble video clip catalogs from data. CX Codex +1 1,700installs spark-engineer https://github.com/Jeffallan skill Writes PySpark jobs and digs into why they crawl: DataFrame transforms, Spark SQL, skewed keys, streaming. Useful when a job burns itself on shuffle or runs out of memory. CX Codex +1 3,800installs audio-transcriber sickn33 skill Runs a local Whisper pass over a recording and writes a timestamped Markdown transcript, with an optional short summary from an LLM. CX Codex +1 1,400installs context-compression sickn33 skill A skill for managing context compression when agent sessions exceed token limits. Instead of naive truncation, it maintains structured summaries with file inventory, decisions, and state. CX Codex +1 1,400installs azure-text-to-speech calesthio skill Synthesizes neural voiceover audio using the Azure AI Speech REST API. Ideal for OpenMontage pipelines that need multilingual narration voices. CX Codex +1 609installs learn-reverse-engineering rohitg00 skill Interactive tutor for reading compiled programs. One lesson per invocation: from file formats and disassembly to symbolic execution and AI-assisted analysis. Requires Python 3.10+ and your own source code. CX Codex +1 488installs tavily-best-practices tavily-ai skill This skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system. CX Codex +1 20,700installs arize-prompt-optimization official arize skill This skill analyzes prompts through production traces, evaluations, and annotations. Use it when you need better model responses or want to debug a system prompt. 1,100installs arize-link official arize skill Builds deep links to the Arize UI for traces, spans, sessions, datasets, and evaluators. Convenient when sharing observability records with teammates. 1,100installs arize-instrumentation official arize skill This skill helps add Arize AX tracing to an LLM application. The agent inspects the project first, then proposes instrumentation for approval. 1,100installs arize-experiment official arize skill Runs Arize experiments with the ax CLI to benchmark models and export evaluation scores across dataset versions. 1,100installs arize-evaluator official arize skill Runs LLM-as-judge workflows in Arize for spans and experiments, with evaluator management, task control, column mapping, and continuous monitoring. 1,100installs arize-dataset official arize skill This skill manages Arize datasets and examples through ax. Use it for test sets, evaluation examples, and dataset exports. 1,100installs arize-annotation official arize skill Creates annotation schemas and review queues in Arize, then updates span labels through the Python SDK. Use it for human review workflows. 1,100installs arize-ai-provider-integration official arize skill Manage Arize AI integrations for language model providers: create connections, inspect their settings, and update or remove them. Use it when configuring models for Arize evaluators or other Arize features. 1,100installs

481–520 of 2,385

Narrow it down

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor