NeVibeCode · 723 items
AI and ML: skills, plugins, subagents, slash commands and mcp servers
AI and ML for Claude Code, Codex and Cursor: skills, plugins, subagents, slash commands and mcp servers, from popular to niche.
quant-analyst subagent A subagent for quantitative trading strategies, financial models, and portfolio risk analysis. Use it for backtests, derivatives pricing, and statistical arbitrage.
Claude Code
1,366installs
agents skill The skill builds voice AI agents on ElevenLabs: sets first_message, prompt, LLM and voice through CLI or SDK. Useful for voice assistants and support bots.
Claude Code CX Codex Cursor +1
11,000installs
gke-ai-troubleshooting-tpu-slice-mig-stuck-updating
official skill Diagnoses TPU Dynamic Slice creation failures and pending JobSets when the backing MIG is unstable. Use it for GKE issues tied to MIG updates or repairs.
Claude Code Gemini CLI CX Codex
440installs
gke-ai-troubleshooting-tpu-vm-repair-stuck
official skill Diagnoses GKE TPU VMs stuck in REPAIRING after host errors or maintenance. Use it when a TPU slice cannot be scheduled because a VM remains in repair.
Claude Code Gemini CLI CX Codex
431installs
videoagent-image-studio skill This skill provides one-command access to Midjourney, Flux, Ideogram, and five other image models without storing API keys. The agent picks the best model and handles Midjourney's async workflow automatically.
Claude Code CX Codex Cursor +1
5,600installs
gpt-image-2 skill Generates and edits images via OpenAI GPT Image 2 on RunComfy. Embeds text, logos, and multilingual typography accurately — for e-commerce, ads, and UI mockups.
Claude Code CX Codex Cursor +1
83,800installs
prompt-optimizer
official skill Converts rough drafts, tasks, and half-formed ideas into finished, copy-pasteable chat prompts without placeholder variables.
GitHub Copilot
467installs
gke-ai-troubleshooting-tpu-partition-overlap
official skill Diagnoses GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap with another slice or JobSet. Pinpoints node conflicts using read-only checks.
Claude Code Gemini CLI CX Codex
378installs
gke-ai-troubleshooting-tpu-reservation-stockout
official skill Diagnoses GKE TPU node pool creation failures caused by reservation stockouts when unhealthy nodes lack auto-repair and hoard reserved capacity.
Claude Code Gemini CLI CX Codex
377installs
loop skill This skill runs recurring autoresearch experiments through CronCreate. Use it when an experiment should be checked on a schedule.
Claude Code
1,557installs
setup skill Sets up an autoresearch experiment by collecting its target file, evaluation command, metric, and optimization direction. Use it before starting an optimization loop.
Claude Code
1,480installs
mlops-engineer subagent This subagent designs ML infrastructure, model CI/CD, and versioning workflows. Use it when training automation, GPU orchestration, or ML monitoring needs attention.
Claude Code
1,009installs
customer-support subagent This subagent helps plan ticket workflows, support automation, and knowledge bases. Use it when you are shaping customer service processes for a project.
Claude Code CX Codex Cursor
1,041installs
mlops-engineer subagent Builds ML pipelines, configures experiment tracking, and automates model deployments across cloud platforms. Useful for teams standardizing ML infrastructure.
Claude Code CX Codex Cursor
1,009installs
nlp-engineer subagent Subagent for building text processing pipelines, fine-tuning models, and running production NLP tasks in Claude Code. Suited for NER, sentiment analysis, and translation.
Claude Code
927installs
harness-engineering
official skill Turns repeated coding agent mistakes into repository rules, drift checks, and regression tests. Use it when Copilot keeps repeating the same errors in your project.
GitHub Copilot
366installs
senior-computer-vision skill This skill covers computer vision pipelines for object detection, image segmentation, and model deployment. Use it when working with PyTorch, YOLO, or ONNX.
Claude Code
1,152installs
trend-analyst subagent This subagent scans change signals, finds patterns, and builds future scenarios. Use it when trend analysis needs to inform product or strategic decisions.
Claude Code
753installs
senior-prompt-engineer skill Skill for systematic prompt optimization via eval sets, RAG quality measurement, and agent validation. Works with any model, uses only stdlib Python.
Claude Code
970installs
senior-data-scientist skill A Claude Code skill that walks through A/B test design, causal analysis and model evaluation in Python, R and SQL.
Claude Code
942installs
llm-architect subagent Designs production LLM architectures: covers RAG, LoRA fine-tuning, inference serving with vLLM, and multi-model routing. Essential when managing token budgets and latency targets.
Claude Code
649installs
senior-ml-engineer skill Guides production ML deployment, MLOps pipelines, RAG systems and LLM API integration. Use it when a project needs monitoring, rollout checks or request cost controls.
Claude Code
915installs
multi-agent-coordinator subagent Plans how Claude Code subagents sequence work, share state through files, and handle failures. Use it when a task has parallel workers or hand-offs.
Claude Code
632installs
agent-organizer subagent Breaks down complex projects into subtasks, maps them to available subagents, and writes an execution plan in Markdown. Useful for coordinating multi-agent setups.
Claude Code
562installs
data-researcher subagent Gathers, verifies, and cleans raw data from web sources and local files. Ideal for preparing datasets before running statistical analysis or machine learning tasks.
Claude Code
542installs
diagnose
official skill This skill audits an AI workflow across five dimensions and returns scores with prioritized fixes. Use it before launch or after major workflow changes.
GitHub Copilot
209installs
power-platform-architect
official skill This skill turns business requirements, use cases, and meeting transcripts into a Power Platform solution architecture with component choices and Mermaid.js diagrams.
GitHub Copilot
205installs
agent-designer skill Turns written requirements into a multi-agent architecture, validated tool schemas and a read on your run logs. Worth running before you wire agents to a design you picked by gut.
Claude Code
682installs
agent-workflow-designer skill Picks a multi-agent workflow pattern and scaffolds the config before you write code, with handoff contracts and retry gates spelled out.
Claude Code
658installs
mcp-server-builder skill Turns an OpenAPI spec into an MCP server: tool manifest plus starter code in Python or TypeScript, with a validator to check it.
Claude Code
644installs
rag-architect skill Design a RAG pipeline around your documents, then measure retrieval quality. Use it to explore chunking strategies, embeddings, or vector databases.
Claude Code
629installs
prompt-engineer-toolkit skill Tests, compares, and versions marketing prompts against structured cases. Use it when prompt quality needs evidence before a rollout or model change.
Claude Code
623installs
data-quality-auditor skill This skill checks datasets for missing values, outliers, duplicates, and structural issues. Use it before analysis, model training, or quality monitoring.
Claude Code
621installs
apigee-agent-gateway-governance
official skill This skill builds an Apigee proxy that inspects LLM traffic through Agent Gateway. Use it to meter model tokens, extract caller identity, or screen prompts.
Claude Code Gemini CLI CX Codex
145installs
machine-learning-engineer subagent A subagent for deploying, optimizing, and serving ML models in production. Use it for inference infrastructure, scaling, and model monitoring.
Claude Code
431installs
agent-protocol skill This skill defines how C-suite agents call each other, return findings, and avoid loops. Use it when several roles must coordinate an analysis.
Claude Code
611installs
autoresearch-agent skill Runs repeated file experiments against a measurable metric, keeping gains and reverting failures. Use it for code, tests, prompts, or content.
Claude Code
589installs
acreadiness-assess
official skill Runs an AgentRC AI-readiness scan on your repository and generates a standalone HTML report at reports/index.html. Handy before configuring AI agent instructions.
GitHub Copilot
158installs
acreadiness-generate-instructions
official skill This skill generates instruction files for GitHub Copilot and scopes rules to repository areas. Use it when a project needs repeatable AI coding guidance.
GitHub Copilot
153installs
mcp-developer subagent Builds, tests, and optimizes Model Context Protocol (MCP) servers and clients. Connects AI models to external tools, databases, and custom services.
Claude Code
366installs
561–600 of 723