Total 32,191 skills, AI & Machine Learning has 5192 skills
Showing 12 of 5192 skills
Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AnalyzeDocument/Markdown APIs, custom models, containers/Docker, SAS/managed identity, or VNets, and other Azure AI Document Intelligence related development tasks. Not for Azure AI services (use microsoft-foundry-tools), Azure AI Search (use azure-cognitive-search), Azure AI Language (use azure-language-service), Azure AI Immersive Reader (use azure-immersive-reader).
Expert knowledge for Azure AI Search development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing indexes, skillsets, vector/semantic search, indexers, private endpoints, or RAG apps, and other Azure AI Search related development tasks. Not for Azure Cosmos DB (use azure-cosmos-db), Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics).
Write, review, and improve prompts for any LLM — Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Cohere, Qwen, Grok, Nova, and more. Use when the user asks to "write a system prompt", "improve this prompt", "review my prompt", "make a prompt for", "optimize my prompt", "fix my prompt", "why isn't my prompt working", or wants help writing better prompts for any AI model. Also use when building agents, chatbots, or AI assistants that need system-level instructions, or when the user has a bad prompt they want rewritten. Covers system prompts, task prompts, tool descriptions, and general prompt improvement across all major model families.
Orchestrate multiple specialized agents working in parallel to debug independent problems. Use when encountering 3+ unrelated bugs or test failures in isolated modules. Matches each problem to the right expert agent and launches them concurrently via the Agent tool with worktree isolation. Supports all available subagent types.
TensorLake SDK for building agentic workflows, sandboxed code execution, and document parsing/extraction. Use when the user mentions tensorlake, or asks about TensorLake APIs/docs/capabilities. Also use when the user is building AI agents or agentic applications that need serverless workflow orchestration (parallel map/reduce DAGs), sandboxed execution of LLM-generated code, or document parsing, structured extraction, and OCR from PDFs/images. Works with any LLM provider (OpenAI, Anthropic), agent framework (LangChain, CrewAI, LlamaIndex), database, or API as the infrastructure layer.
Search a knowledge base of recent research, news, and analysis spanning AI development, technology, business strategy, economics, and industry trends. Sources include tech blogs, X posts, podcast transcripts, earnings calls, and expert commentary. Use this skill whenever the user asks about recent developments, news, trends, what's happening in a field or with a company, technical topics in AI/ML, or wants a research briefing. Also use when the user mentions specific companies, technologies, industries, or economic topics and seems to want current information rather than general knowledge.
Use when one agent is implementing code and another agent must review the resulting changes, compare the summary against the actual files, decide whether to fix now or move on, and write the next tightly scoped prompt with context handoff guidance.
VoxFlow AI voice toolkit — text-to-speech synthesis with 200+ voices, AI podcast generation, narrated story creation, and voice search. Use this skill when users need any speech/voice/audio synthesis task.
Multi-agent systems with LangGraph - supervisor/swarm/handoff/router patterns, state coordination, Deep Agents, guardrails, testing, observability, deployment. Use when building multi-agent workflows, coordinating agents, or need cost-optimized orchestration. Uses Claude, DeepSeek, Gemini (no OpenAI).
[BETA] Execute work plans with external delegate support. Same as ce:work but includes experimental Codex delegation mode for token-conserving code implementation.
Use when batch-resolving approved todos, especially after code review or triage sessions
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.