ai-ml-infra
KubeAI, GPU operators, and model serving patterns for AI/ML infrastructure on Kubernetes.
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
KubeAI, GPU operators, and model serving patterns for AI/ML infrastructure on Kubernetes.
Get Gemini CLI's opinion on code, architecture, or implementation. Use when you want a second AI perspective during coding sessions.
General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.
Intelligent documentation system for AI Elements component library. Activate automatically when working with AI-native applications or when AI Elements component names are mentioned (Message, Conversation, Reasoning, Canvas, etc.). Provides context-aware documentation retrieval - fetches examples for implementation queries, component references for API lookups, and smart multi-page fetching for complex tasks.
This skill should be used when the user asks to "create a memory", "read memories", "manage memories", "document patterns", or when starting work on a Serena project with existing memories. Essential for maintaining project knowledge across conversation sessions and distinguishing documentation from agent-focused memories.
Explains step-based workflow system for Synapse plugin actions. Use when the user mentions "BaseStep", "StepRegistry", "Orchestrator", "StepResult", "BaseStepContext", "step-based workflow", "workflow steps", "rollback", "progress_weight", or needs help with multi-step action development.
Expert guidance for LangGraph Python library. Build stateful, multi-actor applications with LLMs using nodes, edges, and state management. Use when working with LangGraph, building agent workflows, state machines, or complex multi-step LLM applications. Requires langgraph, langchain-core packages.
Kailash MCP (Model Context Protocol) - production-ready MCP server implementation for AI agent integration. Use when asking about 'MCP', 'Model Context Protocol', 'MCP server', 'MCP client', 'MCP tools', 'MCP resources', 'MCP prompts', 'MCP authentication', 'MCP transports', 'stdio transport', 'SSE transport', 'HTTP transport', 'MCP testing', 'progress reporting', or 'structured tools'.
LLM-as-Judge techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation.
This skill should be used when the user asks to "create a prompt", "optimize a prompt", "improve this prompt", "engineer a prompt", "prompt engineering best practices", "make this prompt better", "recommend a model", "which model should I use", "best model for", "GPT vs Claude", "Opus vs Sonnet", "Haiku vs Sonnet", "analyze prompt quality", "fix my prompt", "prompt for Claude", "prompt for GPT", or needs help with prompt engineering techniques, model selection, or prompt optimization for any LLM (Claude Opus/Sonnet/Haiku 4.5, GPT 5.1/Codex, Gemini Pro 3.0).
Research current online documentation and information. Use when working with external libraries, frameworks, APIs, services, version-specific issues, trends, or any topic where LLM training cutoff may impact accuracy. Guides when to use websearch, codesearch, or webfetch.
Guide for storing enriched memories that capture decisions, preferences, and context. Use when making significant decisions or learning user preferences.
Turn ideas into fully formed designs through collaborative dialogue. Use BEFORE any creative work - creating features, building components, adding functionality, or modifying behavior.
Analisa sessoes do Claude Code para extrair learnings e persistir conhecimento. Le arquivos de sessao em ~/.claude/projects/ e extrai decisoes, bloqueios e resolucoes. Invocado automaticamente pelo gate-check e orchestrator. Use quando: fim de fase, retrospectiva, analise de progresso.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Use when building AI agent systems. Covers agent loops, tool calling, planning patterns, memory systems, multi-agent coordination, and safety guardrails. Apply when creating autonomous AI workflows, coding assistants, or task automation systems.
zhimeng's Agent 智能助手操作技能。 触发场景:用户提到"问知识库"、"发日报"、"检查Agent"、"重建索引"、"知识问答"等。
Test and validate agent skills against the Agent Skills Specification v1.0. Use before deploying skills to ensure spec compliance and catch structural issues.
Brainstorm and advise on technical decisions using structured process. EXCLUSIVE to brainstormer agent. Does NOT implement — only advises.