# Skills for AI and ML Skills for AI and ML: what each one does, an install command and example prompts. 2385 cards · page 3 of 60 - HTML: https://affpapa.org/en/nevibecode/skills/topic/ai-ml?page=3 - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [gpt-image-2-style-library](https://affpapa.org/en/nevibecode/skills/gpt-image-2-style-library.md) — skill · freestylefly · Claude Code, Codex, Cursor +3 · 4000 installs — Converts user ideas into production-ready GPT-Image2 prompts using the awesome-gpt-image-2 catalog. - [gemini-live-api-dev](https://affpapa.org/en/nevibecode/skills/gemini-live-api-dev.md) — skill (official Google) · google-gemini · Claude Code, Codex, Cursor +3 · 10200 installs — Guides real-time bidirectional streaming development with the Gemini Live API and migration to Gemini 3.8 Live. - [agent-development](https://affpapa.org/en/nevibecode/skills/agent-development.md) — skill (official Anthropic) · Anthropic · Claude Code · 7353 installs — This skill guides you through creating agents for Claude Code plugins, from trigger conditions to system prompts and tool access. - [knowledge-agent](https://affpapa.org/en/nevibecode/skills/knowledge-agent.md) — skill · thedotmack · Claude Code, Codex, Cursor +3 · 5700 installs — Builds focused knowledge corpora from claude-mem observations and lets you query them in an AI session. - [prompt-optimizer](https://affpapa.org/en/nevibecode/skills/yannjy02-prompt-optimizer.md) — skill · YannJY02 · Claude Code, Codex, Cursor +3 · 5300 installs — Analyzes draft prompts, finds missing project context, and matches ECC commands. - [context-budget](https://affpapa.org/en/nevibecode/skills/context-budget.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 5000 installs — Routes live context checks to Codex or Claude Code meters and runs a bounded configuration audit only when you explicitly ask for one. - [build-mcp-server](https://affpapa.org/en/nevibecode/skills/build-mcp-server.md) — skill (official Anthropic) · Anthropic · Claude Code · 6711 installs — This skill helps design an MCP server for Claude Code by clarifying the use case, choosing deployment, and shaping the tool interface. - [strategic-compact](https://affpapa.org/en/nevibecode/skills/strategic-compact.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4900 installs — Tells you when to run /compact during a session so context survives task phases. - [ai-research-explore](https://affpapa.org/en/nevibecode/skills/ai-research-explore.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 337400 installs — Governs deep learning research exploration on top of an existing baseline. - [analyze-project](https://affpapa.org/en/nevibecode/skills/analyze-project.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 337200 installs — Reads a deep learning repository and maps its structure, entrypoints and suspicious spots. - [ai-research-reproduction](https://affpapa.org/en/nevibecode/skills/ai-research-reproduction.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 337100 installs — This skill guides a repository-grounded reproduction run from its README to an evidence bundle. - [explore-code](https://affpapa.org/en/nevibecode/skills/explore-code.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 336700 installs — A skill for cautious code experiments in deep learning repositories: it transplants modules and adapts architectures on an isolated branch, with rollback-aware records. - [safe-debug](https://affpapa.org/en/nevibecode/skills/safe-debug.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 335000 installs — Conservative failure diagnosis for deep learning research: narrows down root causes and drafts minimal patches without touching code without approval. - [explore-run](https://affpapa.org/en/nevibecode/skills/explore-run.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 336500 installs — Plans bounded exploratory machine learning runs with comparability caveats and saves summaries to explore_outputs. - [run-train](https://affpapa.org/en/nevibecode/skills/run-train.md) — skill · lllllllama · Claude Code, Codex, Cursor +3 · 336500 installs — Runs a selected training command and organizes the resulting evidence. - [eval-harness](https://affpapa.org/en/nevibecode/skills/eval-harness.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4700 installs — A skill for eval-driven development: it sets pass/fail criteria before you write code and tracks agent reliability with pass@k and pass^k. - [agent-architecture-audit](https://affpapa.org/en/nevibecode/skills/agent-architecture-audit.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4800 installs — This skill checks agent and LLM applications across 12 layers. - [pytorch-patterns](https://affpapa.org/en/nevibecode/skills/pytorch-patterns.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4800 installs — This skill guides PyTorch model, training-loop, and data-loading work with practical patterns. - [search-first](https://affpapa.org/en/nevibecode/skills/search-first.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4800 installs — A skill that makes the agent search npm, PyPI, MCP servers and GitHub for existing tools before it writes custom code. - [migrate-ai-sdk-v6-to-v7](https://affpapa.org/en/nevibecode/skills/migrate-ai-sdk-v6-to-v7.md) — skill · vercel · Claude Code, Codex, Cursor +3 · 5500 installs — Migrates applications from Vercel AI SDK 6.x to 7.0. - [microsoft-docs](https://affpapa.org/en/nevibecode/skills/github-microsoft-docs.md) — skill (official GitHub) · github · GitHub Copilot · 14881 installs — Finds official Microsoft documentation, tutorials, and code samples for Azure, .NET, VS Code, and GitHub work. - [cost-aware-llm-pipeline](https://affpapa.org/en/nevibecode/skills/cost-aware-llm-pipeline.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — A skill for apps that call LLM APIs: picks a model by task complexity, tracks spend, caches prompts. - [fal-ai-media](https://affpapa.org/en/nevibecode/skills/fal-ai-media.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — This skill connects Claude Code to fal.ai MCP for generating images, video, speech, and audio. - [council](https://affpapa.org/en/nevibecode/skills/council.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — Runs four advisors over an ambiguous call so the disagreement is visible before you pick. - [mcp-server-patterns](https://affpapa.org/en/nevibecode/skills/mcp-server-patterns.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4700 installs — Teaches AI agents how to build MCP servers with the TypeScript SDK. - [agent-introspection-debugging](https://affpapa.org/en/nevibecode/skills/agent-introspection-debugging.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4700 installs — Provides a structured self-debugging loop for AI agent runs that loop on tools, hit context limits, or fail repeatedly. - [token-budget-advisor](https://affpapa.org/en/nevibecode/skills/token-budget-advisor.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4700 installs — This skill offers response-depth choices with token estimates before generation. - [ai-regression-testing](https://affpapa.org/en/nevibecode/skills/ai-regression-testing.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4700 installs — A skill for regression testing code that AI wrote. - [iterative-retrieval](https://affpapa.org/en/nevibecode/skills/iterative-retrieval.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4500 installs — This skill lays out a four-phase loop that narrows context retrieval so a subagent gets the files it needs instead of the whole repo. - [exa-search](https://affpapa.org/en/nevibecode/skills/affaan-m-exa-search.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4500 installs — Wires Exa neural search into your agent: fresh web pages, code examples, company and people lookups. - [agent-eval](https://affpapa.org/en/nevibecode/skills/agent-eval.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4500 installs — Compares AI coding agents head-to-head on custom tasks using pass rate, cost, and time metrics. - [inventory-demand-planning](https://affpapa.org/en/nevibecode/skills/inventory-demand-planning.md) — skill · evos · Claude Code, Codex, Cursor +3 · 4500 installs — This skill helps forecast demand, set safety stock, and plan replenishment for multi-location retailers. - [continuous-learning](https://affpapa.org/en/nevibecode/skills/continuous-learning.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4500 installs — A stop-hook skill that reviews a session at its end and saves reusable patterns as learned skills. - [continuous-agent-loop](https://affpapa.org/en/nevibecode/skills/continuous-agent-loop.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4500 installs — A skill that lays out a continuous agent loop: mode selection, quality gates, evals and recovery. - [agentic-os](https://affpapa.org/en/nevibecode/skills/agentic-os.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — Turns Claude Code into a persistent operating runtime with an orchestrator kernel, specialist agents, slash commands, and file-based state. - [llm-trading-agent-security](https://affpapa.org/en/nevibecode/skills/llm-trading-agent-security.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — This skill reviews autonomous trading agents with wallet or transaction authority. - [autonomous-loops](https://affpapa.org/en/nevibecode/skills/autonomous-loops.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — This skill covers autonomous development loops, from sequential claude -p pipelines to multi-agent DAG orchestration. - [data-scraper-agent](https://affpapa.org/en/nevibecode/skills/data-scraper-agent.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — This skill walks you through building an agent that scrapes public sources on a schedule, enriches results with Gemini Flash, and stores them in Notion, Sheets or Supabase. - [mle-workflow](https://affpapa.org/en/nevibecode/skills/mle-workflow.md) — skill · affaan-m · Claude Code, Codex, Cursor +3 · 4600 installs — A skill for turning model work into a production system: data contracts, reproducible training, evaluation, deployment and rollback. - [mmx-cli](https://affpapa.org/en/nevibecode/skills/mmx-cli.md) — skill · MiniMax-AI · Claude Code, Codex, Cursor +3 · 32000 installs — This skill gives an agent access to mmx for MiniMax text, image, video, speech, audio transcription, and web search tasks. Next: https://affpapa.org/en/nevibecode/skills/topic/ai-ml.md?page=4 ## 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) · [cli](https://affpapa.org/en/nevibecode/tag/cli.md) · [rag](https://affpapa.org/en/nevibecode/tag/rag.md) · [machine-learning](https://affpapa.org/en/nevibecode/tag/machine-learning.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [audio](https://affpapa.org/en/nevibecode/tag/audio.md) · [api](https://affpapa.org/en/nevibecode/tag/api.md) · [pytorch](https://affpapa.org/en/nevibecode/tag/pytorch.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