NeVibeCode · 719 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.
agent-skill-stack
official skill Finds a small compatible set of AI Agent Skills for a multi-step goal. Use it to audit installed Skills or work out what a project still needs.
GitHub Copilot
128installs
chief-ai-officer-advisor skill Advises startup founders and CAIOs on API versus fine-tuning decisions, EU AI Act risk tiers, and self-hosting token economics.
Claude Code
418installs
litreview skill A skill that searches academic literature through PubMed and OpenAlex, builds a search plan, and produces a Word orientation guide.
Claude Code
417installs
chief-data-officer-advisor skill Advises startup founders and CDOs on AI training data rights, data product architecture, B2B customer data valuation for M&A, and hiring sequences.
Claude Code
410installs
eu-ai-act-specialist skill Classifies AI systems under Regulation (EU) 2024/1689, outlines conformity routes, and maps role obligations. Essential for teams auditing models against EU AI Act rules.
Claude Code
394installs
knowledge-synthesizer subagent Finds recurring errors and workflow patterns in logs and transcripts, then records evidence-linked findings. Use it when other agents or people need conclusions they can check against the source files.
Claude Code
276installs
iso42001-specialist skill Reviews AI management system gaps, maps risks to Annex A controls, and drafts an internal audit plan. Use it when preparing for ISO 42001 certification.
Claude Code
385installs
cdo-review skill Stress-tests data architecture, model training plans, and hiring decisions. Useful before signing long-term data infrastructure deals or training models on customer data.
Claude Code
376installs
caio-review skill Pressure-tests AI roadmaps and features as a Chief AI Officer. It demands evaluation datasets, checks EU AI Act tiers, and projects 12-month model costs.
Claude Code
371installs
patent skill This skill searches patent prior art and builds a landscape for a chosen use case. Use it for a technical assessment before filing or licensing decisions.
Claude Code
357installs
research skill Classifies a research request and hands it to the right specialist skill, or runs its own search workflow. Useful when you want a sourced briefing fast.
Claude Code
348installs
generate-image
official skill Generate images from text prompts with OpenAI or Google Gemini. Use it to create project textures, icons, sprites, artwork, or mockups.
GitHub Copilot
93installs
notebooklm skill Automates Google NotebookLM via browser control. It lets Claude Code query existing notebooks, add sources, and generate Studio outputs like summaries or audio overviews.
Claude Code
325installs
find command Searches the Meigen gallery by keywords and shows visual results with short prompt excerpts right away.
Claude Code CX Codex Cursor
210installs
foundry-agent-sync
official skill This skill creates and updates prompt-based agents in Azure AI Foundry from a local JSON manifest. Use it when agents need to be registered in the Foundry service.
GitHub Copilot
74installs
mini-context-graph
official skill Builds a knowledge base from documents, with wiki pages, a graph of entities and relations, and source text for evidence. Use it when answers should draw on material collected over time.
GitHub Copilot
72installs
resemble-detect
official skill Detects synthetic audio, images, video, and text using Resemble AI. Helpful for media verification, watermark detection, and voice provenance checks.
GitHub Copilot
68installs
qdrant-search-quality
official skill Diagnoses why Qdrant returns irrelevant matches and points to ways to improve search quality. Useful after an embedding model change or as your data grows.
GitHub Copilot
61installs
qdrant-scaling
official skill Guides Qdrant scaling decisions across data volume, query throughput, latency, and result payload sizes.
GitHub Copilot
61installs
qdrant-performance-optimization
official skill This skill maps Qdrant performance work across search speed, index building, and memory use. Use it when a deployment needs a focused performance review.
GitHub Copilot
61installs
qdrant-model-migration
official skill This skill guides Qdrant embedding-model migrations without taking search offline. Use it when changing providers, vector dimensions, or moving from dense to hybrid search.
GitHub Copilot
61installs
qdrant-deployment-options
official skill Guides the choice between Qdrant deployment types based on latency, operational overhead, and data residency needs.
GitHub Copilot
61installs
qdrant-monitoring
official skill Guides Qdrant observability setup and incident diagnostics through metrics. Useful when search requests slow down or memory usage spikes.
GitHub Copilot
60installs
agent-architecture
official skill Designs AI agent architectures from requirements or audits existing agents for flaws. Focuses purely on architectural decisions and verification without implementing code.
GitHub Copilot
42installs
workflow-builder skill Creates deterministic multi-agent workflow scripts in JavaScript for Claude Code. Useful for coordinating sub-agents in fresh contexts with budget limits and resume support.
Claude Code
119installs
verify-agent-action
official skill Audits proposed AI agent actions, deployments, and approvals before execution. It checks parameters, nonces, and telemetry, never authorizing or running actions on its own.
GitHub Copilot
29installs
foundry-hosted-agent-copilotkit
official skill Connects a CopilotKit React frontend to a Microsoft Agent Framework agent in Microsoft Foundry via the AG-UI protocol. Helps connect and deploy agentic web apps.
GitHub Copilot
29installs
webmcpify
official skill This skill turns a web app into WebMCP tools for AI agents, checks them in a real browser, and heals issues found during verification.
GitHub Copilot
27installs
from-the-other-side-quinn
official skill A collaboration profile for Ember sessions with Alison that keeps GitHub Copilot focused on practical, verifiable progress.
GitHub Copilot
25installs
pinecone-rag
official skill This skill guides Pinecone-based RAG pipelines and persistent agent memory. Use it for semantic document search, hybrid retrieval, or context shared across sessions.
GitHub Copilot
24installs
llm-cost-optimizer skill Audits token usage and cuts LLM API spend through model routing, caching, and prompt compression. Useful when API bills spike or before launching new AI endpoints.
Claude Code
73installs
markstream-install
official skill Configures Markstream streaming Markdown renderers across React, Vue, Svelte, and Angular projects. It resolves package selection, CSS ordering, and SSR boundaries.
GitHub Copilot
18installs
discernment-nudge
official plugin This plugin adds two or three short follow-up questions after a substantive answer. Use it to check facts, probe reasoning, and spot missing context.
Claude Code Claude.ai
★ 183,434repo stars
academy-guide
official plugin Recommends Claude Academy courses, tutorials, and use cases when you ask how to use Claude. It suits people learning Claude features through real tasks.
Claude Code Claude.ai
★ 183,434repo stars
claude-api
official plugin This plugin adds Claude API and SDK guidance for building LLM-powered applications. Install it when your project needs a Claude integration.
Claude Code Claude.ai
★ 183,434repo stars
example-skills
official plugin A collection of Claude skill examples for web testing, MCP work, design and documents. Use it to inspect skill structure or start a custom skill from a template.
Claude Code Claude.ai
★ 183,434repo stars
claude-coach skill This skill teaches Claude workflows and improves prompt habits through targeted tips. Use it when you want guided practice inside Claude Code.
Claude Code
50installs
behuman skill Strikes robotic habits and filler out of AI responses in personal chats. Adds an internal reflection loop so drafts sound like a real person.
Claude Code
49installs
speak-summary
official skill Rewrites written notes or summaries into listenable spoken prose and synthesises an MP3 file locally on CPU using Kyutai pocket-tts without cloud services.
GitHub Copilot
12installs
agent-memory skill Replaces bloated CLAUDE.md files with a four-tier memory store. The agent promotes facts across sessions only when they recur over multiple days.
Claude Code
42installs
601–640 of 719