azure-ai-services-expert
Build AI applications on Azure using Azure OpenAI, Cognitive Services, and ML services with enterprise patterns
Discover Testing & security skills, compare source repositories and read the instructions for each workflow.
Build AI applications on Azure using Azure OpenAI, Cognitive Services, and ML services with enterprise patterns
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
Create professional architecture diagrams using D2, Draw.io, Mermaid, and OCI official icons for enterprise-grade visualizations
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
Build AI applications on AWS using Bedrock, SageMaker, and AI/ML services with best practices for enterprise deployment
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
Design and deploy AI workloads across AWS, Azure, GCP, and OCI with intelligent routing, cost optimization, and cross-cloud patterns
Production-grade AI architecture patterns for enterprise - security, governance, scalability, and operational excellence
Expert in OCI Generative AI Dedicated AI Clusters - deployment, fine-tuning, optimization, and production operations
Update work_index/index.json and index.json based on recent work folder activity and work_index.db. Use at the end of a task.
Workflow for using GitHub MCP + git to create private repos, sync main via git switch, branch safely, push without touching main, and open PRs. Use for any task that needs Git branching/publishing guidance.
Guidance for responding through Slack MCP: immediate acknowledgements, progress cadence, thread discipline, message templates, and failure handling. Use whenever Codex must reply to Slack mentions or share prog...
Record per-task work logs into each work folder's SQLite DB and update the global work_index.db summary after meaningful steps. Use whenever work starts or finishes.
This skill should be used when inspecting marimo notebook execution results. Triggers include: - Checking notebook output - Viewing execution results - Reading __marimo__ HTML snapshots - Debugging notebook er...
This skill should be used when working with marimo reactive notebooks for data science and analytics. Triggers include: - Creating new marimo notebooks - Converting Jupyter notebooks to marimo - Editing existi...
This skill should be used when starting a marimo development server with hot reload. Triggers include: - Starting marimo server - Running marimo notebooks locally - Launching marimo development environment - S...
Implement AI-powered statusline with session tracking, plan detection, workspace emojis, and intelligent caching for Claude Code
This skill should be used when the user asks to "set up shell completions", "fix zsh completions", "configure tab completion", "add completions for brew/npm/cargo", "troubleshoot missing completions", or mentio...
Validate podcast RSS feed against specification standards. Checks channel metadata, episode elements, XML structure, and file metadata accuracy. Use after updating feed.xml with a new episode to ensure complian...
LEGACY SKILL - Manual NotebookLM web interface workflow. The primary workflow now uses notebooklm-enterprise-api for automated audio generation. Use this skill only when the API is unavailable.
Generate podcast audio using NotebookLM Enterprise API via Google Cloud. Automates the manual NotebookLM workflow - creates notebook, uploads sources, generates audio with custom focus prompt. Requires Google C...
DEPRECATED - Use gpt-researcher skill instead. This browser automation approach has been replaced with the local GPT-Researcher framework using OpenAI o1.
Process NotebookLM audio files: convert, transcribe, add chapters, and prepare for publishing.
Automate Perplexity Deep Research API calls using sonar-deep-research model. Use for Phase 1 academic research in podcast episodes. Handles API key verification, script execution (30-120s), and result formattin...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.