Access Azure AI Search, Speech, OpenAI, and Document Intelligence services through unified MCP tools. AI Search supports full-text, vector, hybrid, and semantic search with built-in AI enrichment for entity extraction and OCR Speech service handles real-time and batch speech-to-text transcription, text-to-speech synthesis with neural voices, and speaker diarization MCP tools provide direct access: azure__search for index queries and azure__speech for transcription and synthesis SDK references available for Python, TypeScript, .NET, and Java across all services; enable via /azure:setup or /mcp if MCP is not active
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first…
AI SDK documentation and guidance for building AI-powered features with Vercel's framework. Covers core APIs including generateText , streamText , ToolLoopAgent , embed , and tool calling across multiple AI providers (OpenAI, Anthropic, Google, etc.) Supports building agents, chatbots, RAG systems, and text generation with structured output and streaming capabilities Includes React hooks ( useChat , useCompletion ) and framework-specific patterns for Next.js, SvelteKit, and other platforms Provides type-safe agent consumption with InferAgentUIMessage for end-to-end type safety and local DevTools for debugging
Claude API integration for building LLM-powered applications across Python, TypeScript, Java, Go, Ruby, C#, and PHP. Defaults to Claude Opus 4.6 with adaptive thinking and streaming; supports tool use, structured outputs, batches, and file uploads through a single /v1/messages endpoint Language detection automatically routes you to the correct SDK documentation; includes decision trees for choosing between single API calls, workflows with tool use, and agentic loops Tool runner (beta in most languages) handles automatic loop execution; manual loops available for fine-grained control over approval gates, logging, and conditional execution Agent SDK (Python and TypeScript only) provides built-in file, web, and terminal tools with permissions, MCP support, and safety guardrails; Claude API is the right choice for custom agent tools
Generate Excalidraw diagrams from natural language descriptions in multiple formats. Supports nine diagram types: flowcharts, relationship diagrams, mind maps, architecture diagrams, data flow diagrams, swimlane business flows, class diagrams, sequence diagrams, and ER diagrams Outputs valid .excalidraw JSON files that open directly in Excalidraw or the VS Code extension Includes layout guidelines, element count recommendations, and color schemes for consistent visual design Optional integration with icon libraries (AWS, GCP, Azure, etc.) via Python scripts for professional architecture diagrams Provides structured workflows for extracting diagram requirements, choosing appropriate types, and generating properly formatted output
Comprehensive guide for building autonomous agents in Claude Code plugins with structured frontmatter, system prompts, and triggering conditions. Agents are autonomous subprocesses defined in markdown files with YAML frontmatter; use them for multi-step independent tasks, commands for user-initiated actions Required frontmatter fields: name (3–50 lowercase-hyphenated characters), description (with 2–4 concrete triggering examples), model (inherit/sonnet/opus/haiku), color (blue/cyan/green/yellow/magenta/red), optional tools array for least-privilege access System prompt design uses second-person voice with clear responsibilities, step-by-step process, quality standards, output format, and edge case handling; keep under 10,000 characters Description field is critical: must specify triggering conditions, include <example> blocks with context, user request, assistant response, and <commentary> explaining why the agent triggers Validation rules enforce identifier format, description length (10–5,000 chars), and system prompt structure; includes AI-assisted generation templates and testing utilities for triggering verification
Image generation and editing via OpenRouter's Gemini 3 Pro model with multi-image compositing support. Supports three workflows: prompt-only generation, single-image editing, and multi-image composition (up to 3 images per request) Output resolution options: 1K, 2K, or 4K (defaults to 1K) Customizable behavior through optional system prompt template in assets/SYSTEM_TEMPLATE Requires OPENROUTER_API_KEY environment variable and uv package manager; includes troubleshooting guidance for authentication and dependency issues
Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops. Provides three core patterns: basic reflection (self-critique loops), evaluator-optimizer (separated generation and evaluation), and code-specific test-driven refinement Supports multiple evaluation strategies including outcome-based assessment, LLM-as-judge comparison, and rubric-based scoring with weighted dimensions Includes practical Python implementations with structured JSON output parsing, iteration limits, and convergence detection to prevent infinite loops Best suited for quality-critical tasks like code generation, reports, and analysis where clear evaluation criteria and success metrics exist
Generates concise, actionable meeting minutes for internal meetings under 60 minutes with standardized metadata, decisions, and assigned action items. Captures attendees, agenda, decisions with rationale, and action items with owner and due date for immediate task tracking Follows a strict schema covering metadata, decisions, action items, notes by agenda item, parking lot, risks, and follow-ups Accepts multiple input formats: transcripts, recordings, slides, raw notes, or live meeting capture Asks up to three clarifying questions upfront if critical details (title, date, organizer, source material) are missing before drafting
Interactive workflow to refine task prompts through structured questioning and clipboard delivery. Guides users through systematic prompt refinement by interrogating scope, deliverables, constraints, and technical requirements Produces polished markdown prompts and automatically copies them to the system clipboard via the Joyride extension Focuses exclusively on prompt engineering; does not generate code or implementation details Requires the Joyride extension for VSCode clipboard integration and human input requests
Polish and refine agent prompt files against proven best practices. Requires a prompt file as input; will request one if not provided Preserves front matter, encoding, and markdown structure while improving clarity and organization Corrects spelling, grammar, and wording issues without altering the original intent Applies patterns from successful prompts to strengthen structure and effectiveness
Query Microsoft 365 data with natural language to surface emails, meetings, documents, Teams messages, and people insights. Supports five data sources: emails, meetings, documents, Teams channels, and people/projects with natural-language prompts Install via Copilot CLI plugin (preferred) or standalone npm package; requires Microsoft 365 tenant admin consent on first use Core workflow: clarify intent, craft precise prompts with timeframe/source, run workiq ask --question "..." , and stream results Includes MCP server mode ( workiq mcp ) for exposing WorkIQ tools to other agents and workflows Best practices emphasize narrow, focused queries, privacy-respecting summaries, and mapping results to actionable follow-ups like blocking time or drafting messages
Ask an AI assistant what files it needs before answering your question. Prompts the assistant to identify required and optional files for context before attempting to answer Structures output into four categories: must-see files, helpful files, already-seen files, and remaining uncertainties Helps developers avoid incomplete answers by ensuring the assistant has examined relevant code upfront Reduces back-and-forth by clarifying dependencies and gaps in context before the actual question is answered
Deploy and manage MCP-based declarative agents across Microsoft 365 with admin center governance, role-based access, and organizational distribution. Supports five agent types: organization-published, creator-shared, Microsoft-native, external partner, and frontier agents, each with distinct deployment and approval workflows Provides admin controls for publishing, deploying to user groups, blocking, and removing agents; requires AI Admin role for full management Includes MCP-specific validation for server accessibility, OAuth authentication, tool imports, and security compliance before deployment Covers phased rollout strategies, user discovery through Copilot hub, compliance monitoring, and troubleshooting for authentication and performance issues
Analyze chatmode or prompt files to recommend optimal AI models based on task complexity, capabilities, and cost-efficiency. Evaluates .agent.md and .prompt.md files across eight task categories (simple repetitive, code generation, refactoring, debugging, planning, code review, domain-specific, advanced reasoning) to determine complexity and reasoning depth requirements Compares 14 available models (GPT-4.1, GPT-5, Claude Sonnet variants, Gemini, Grok, deprecated o3/o4-mini) using a decision tree that factors in context window size, vision support, code quality, and reasoning capabilities Provides primary recommendation plus alternatives with explicit trade-off analysis, cost multiplier implications for Free/Pro/Pro+ subscription tiers, and deprecation migration paths Generates structured markdown reports with model comparison tables, auto-selection suitability assessment, frontmatter update guidance, and Context7 verification for current model documentation