Unified access to Azure AI services: Search, Speech, OpenAI, and Document Intelligence. AI Search supports full-text, vector, hybrid, and semantic search with AI enrichment capabilities like entity extraction and OCR Speech service enables speech-to-text transcription (real-time and batch), text-to-speech with neural voices, speaker diarization, and custom models MCP server integration provides direct tool access via azure__search and azure__speech commands; falls back to CLI and SDK when MCP is unavailable Includes OpenAI model access, DALL-E image generation, embeddings, and Document Intelligence for form extraction and OCR
Quick reference for ADK Python patterns: agents, tools, callbacks, and state management. Covers agent creation with model and instruction configuration, basic tool definition via FunctionTool, and callback patterns for state initialization and lifecycle hooks Includes built-in tool imports, agent orchestration (SequentialAgent, ParallelAgent, LoopAgent), and state management through CallbackContext ADK 2.0 Workflow API available as opt-in experimental feature for graph-based pipelines with conditional routing and parallel processing; requires Python 3.11+ and explicit user consent before use Requires an existing scaffolded project; use agents-cli scaffold create or scaffold enhance before writing agent code
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly…
Evaluate ADK agents with metrics, evalsets, and the iterative eval-fix loop. Run evaluations with agents-cli eval run using configurable criteria (tool trajectory, response matching, rubric-based scoring, hallucination detection, safety checks) and match types (EXACT, IN_ORDER, ANY_ORDER) Build evalsets with multi-turn conversation cases, expected tool trajectories, intermediate responses, and session state overrides Iterate through 5-10+ eval-fix cycles: diagnose failures, fix agent instructions or tool logic, rerun, and track progress with task lists Avoid common pitfalls: don't lower thresholds to hide failures, handle extra tool calls with IN_ORDER matching, ensure app name matches directory, and initialize state with callbacks to prevent KeyError crashes
End-to-end AI Runway setup on AKS from bare cluster to running model deployment. Walks through six sequential steps: cluster verification, controller installation, GPU assessment, inference provider setup, first model deployment, and summary Includes cost awareness warnings for GPU node pools and error handling for common deployment failures Supports resuming from any step via skip-to-step N argument if setup is partially complete Uses only kubectl and make CLI tools; no MCP tools required
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
One API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a user wants…
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
Generate comprehensive Product Requirements Documents that translate business vision into technical specifications. Follows a strict three-phase workflow: discovery interview to fill knowledge gaps, analysis and scoping to identify dependencies, and technical drafting using a standardized PRD schema Requires concrete, measurable success criteria and acceptance criteria; explicitly avoids vague language like "fast" or "intuitive" in favor of quantifiable benchmarks Covers executive summary, user personas and stories, technical architecture, AI system requirements with evaluation strategies, and phased rollout planning with risk analysis Includes discovery questions on core problems, success metrics, and constraints before generating any document; presents drafts for iterative feedback on specific sections
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating…
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals,…
Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an…
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic…
Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music…