moai-baas-vercel-ext
Enterprise Vercel Edge Platform with AI-powered deployment, Context7 integration
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Enterprise Vercel Edge Platform with AI-powered deployment, Context7 integration
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.
Comprehensive prompt engineering techniques for Claude models. Use this skill when crafting, optimizing, or debugging prompts for Claude API, Claude Code, or any Claude-powered application. Covers system prompts, role prompting, multishot examples, chain of thought, XML structuring, long context handling, extended thinking, prompt chaining, Claude 4.x-specific best practices, and agentic orchestration including subagents, agent loops, skills, MCP integration, and multi-agent workflows.
Generate new Claude Code skills with proper structure and standards. Use when the user requests skill creation, wants to generate a new skill, or mentions creating custom Claude Code functionality. Activated by phrases like "create a skill", "generate a skill", "make a new skill", or "build a skill for".
ML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vector databases (Pinecone, Chroma, Weaviate), prompt engineering, model evaluation, cost optimization, Agentic RAG, AI Agents, MCP, LLM observability. 30 methodologies.
Setup and manage Gemini CLI authentication methods including OAuth, API keys, and Vertex AI. Use when configuring Gemini access, switching auth methods, or troubleshooting authentication issues.
Comprehensive guide to implementing permission systems for AI agent tools including RBAC, approval workflows, and security policies
Add AI model authentication to any project. Supports GitHub Copilot, Anthropic, OpenAI, OpenRouter, AWS Bedrock, Google Vertex, Cloudflare, and 50+ OpenAI-compatible providers. Uses OpenCode's proven 5-tier auth priority system (env vars, stored credentials, config files, OAuth plugins, public keys). Enables users to leverage their existing paid services without new API keys.
How to write/update .claude/skills and capture durable OpenEvent learnings via retrospectives.
Package skills into web-compatible bundles. Converts any skill directory into a single .txt file containing all resources, making it usable in web-based AI chatbots. Validates skill structure and warns about script compatibility. Triggers when user mentions "skill-web-bundle", "打包skill", "web bundle", or wants to create web bundles of skills for external use.
Apply Anthropic's 4D Framework for AI delegation: Delegation (task selection), Description (instructions), Discernment (verification), and Diligence (iteration).
Implements a proactive confirmation and continuous loop mechanism for all agent interactions. Use this skill when engaging in any task (consultation, development, debugging) to ensure step-by-step user approval and maintain continuous workflow until explicit termination.
Patterns for building AI applications with Vercel AI SDK including streaming LLM responses, tool calling, structured outputs, and multi-provider support. Use when integrating LLMs into applications.
AI-powered chat assistant for Beeper Desktop. Use when user asks about: - Searching messages across platforms (/beeper-ai:search) - Summarizing conversations (/beeper-ai:summarize) - Generating replies (/beeper-ai:reply) - Analyzing communication style (/beeper-ai:analyze-style) - Checking Beeper/Fabric connectivity (/beeper-ai:status)
Fast ideation and problem exploration. Triggers on Ukrainian/English phrases like "подумай", "поміркуй", "брейнштормінг", "brainstorm", "think through", "накидай ідеї", "generate ideas". Rapid divergent thinking to uncover insights, problems, and solutions through interactive dialogue.
Multi-model consensus scoring for content ideas. Scores the same idea with Claude, GPT-4o, Gemini, and Grok in parallel, then aggregates for a balanced verdict. Reduces single-model bias and improves viral predictions.
List all available skills configured in AGENTS.md. Scan and display skills with their names, descriptions, and trigger commands. Triggers when user mentions "列出技能", "list skills", "可用技能", "show skills", "技能列表", or uses command /skill-list.