'stateful' 검색 결과

Create an Estuary derivation with custom SQLite state (internal tables) to make per-document decisions based on accumulated history — account balances, inventory levels, approval workflows, deduplication. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this. Use when user says "stateful derivation", "derivation to track balance", "transformation to approve based on state", "derive an approval workflow", "deduplication derivation", or "build a stateful derivation".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan and build AI agents through selected stages of design, implementation, tool integration, memory, and evaluation. The workflow points to specialized skills for single agents, coordinated agent teams, and stateful workflows using CrewAI or LangGraph.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing an autonomous AI agent
• Building a team of agents with distinct roles
• Creating stateful workflows with LangGraph

Build AI agents with LangGraph by connecting processing steps into a graph. Define shared state, conditional paths, tool calls, saved checkpoints, and human review points to create workflows that retain information as they run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an agent that calls tools in a loop
• Sharing accumulated findings between multiple agents
• Routing requests to different processing paths

Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Applies data-grid architecture for high-traffic stateful workloads. Use when a single database cannot scale and in-memory partitioning is needed.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fix "ref.listen can only be used within the build method of a ConsumerWidget" assertion error in Flutter Riverpod 3.x. Use when: (1) ConsumerStatefulWidget crashes with "Failed assertion: line 492 pos 7: 'debugDoingBuild'" in flutter_riverpod consumer.dart, (2) ref.listen is called inside initState, addPostFrameCallback, or any lifecycle method other than build(), (3) All widget tests fail with this assertion from scheduler callback. Applies to flutter_riverpod 3.0+ with ConsumerStatefulWidget.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fix Riverpod "Using ref when widget is unmounted is unsafe" error in ConsumerStatefulWidget. Use when: (1) Error thrown in dispose() when calling ref.read(), (2) Need to call a service method during widget cleanup, (3) ConsumerStatefulWidget needs to perform actions on provider when user navigates away. Solution: cache the service/notifier in initState with late final.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when "langgraph, langchain agent, stateful agent, agent graph, react agent, agent workflow, multi-step agent, langgraph, langchain, agents, state-machine, workflow, graph, ai-agents, orchestration" mentioned.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Testing patterns for simulating sequential calls and race conditions using Moq stateful callbacks

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manages local UI state and side effects in Flutter using the flutter_hooks package (v0.21.x) with HookWidget, useState, useEffect, useMemoized, useAnimationController, and custom hooks. Use this skill when replacing StatefulWidget boilerplate with hooks, reusing stateful UI logic across widgets, managing controller lifecycles (TextEditingController, AnimationController, ScrollController) without manual dispose, implementing countdown timers or subscriptions in widgets, mixing flutter_hooks with Riverpod via HookConsumerWidget, or any time the words 'flutter hooks', 'useEffect', 'useState', 'HookWidget', or 'flutter_hooks' appear in the request.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentDB로 대화 기록과 사용자 선호를 저장하고 검색하는 단기·장기 기억을 구현해, AI 에이전트가 다음 세션에서도 해당 정보를 참조하도록 돕습니다.

• 채팅에 대화 기록 추가
• 세션 간 사용자 선호 기억
• 성공한 상호작용 패턴 재사용

Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add conversation history to a chat system
• Remember user preferences across sessions
• Reuse patterns from successful interactions

Build and edit OBS Studio scene collections from the command line. Arrange visual sources, adjust filters and audio, configure transitions and output settings, and save the setup as JSON with undo and redo support.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create or duplicate streaming scenes
• Adjust source positions and cropping
• Configure audio volume and mute settings

Create and edit Shotcut video projects through commands. Arrange and trim clips, adjust audio, add effects and transitions, then export a video. Preview files let agents review cuts, pacing, and visual changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Arrange clips at specified times
• Lower background audio during selected sections
• Add transitions and picture-in-picture

Create and edit text documents, spreadsheets, and presentations from the command line. Import existing Office or ODF files, update content and styles, and export documents, with JSON project files and undo and redo support.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a document with headings, lists, and tables
• Update spreadsheet cells and sheet names
• Add slides or revise their content

Manage JumpServer hosts, users, accounts, and access permissions through commands. Agents can inspect active connections and audit logs, preview changes before execution, and receive structured results for further processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inventory hosts and inspect asset details
• Create users and configure asset access
• Review failed logins and operation logs

Build and edit audio projects through an Audacity command-line interface: arrange and trim clips, adjust tracks, configure effects, add labels, and render audio files while retaining project state and undo history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trim, split, and arrange audio clips
• Adjust track volume, pan, mute, and solo
• Configure effects and add timeline labels

Manage a Calibre e-book library through commands: find and organize books, edit titles and other book details, and convert formats. Agents can also export EPUB chapters as separate PDFs and generate library catalogs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search books by author, tags, or rating
• Edit titles, series details, and other book metadata
• Convert e-books between formats

Build Blender 3D scenes through text commands, adjusting objects, materials, lights, cameras, and animation keyframes. Render the scene or generate preview images to check its appearance, with scene state saved in JSON for later editing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a 3D scene from basic shapes
• Adjust materials, lighting, and camera settings
• Set animation keyframes and frame ranges

Create and edit QGIS map projects from the terminal. Add geographic features and attributes, arrange maps and labels in print layouts, export PDFs or images, and run QGIS algorithms for processing geographic data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a map project and adding points
• Adding geographic features and attributes
• Exporting labeled maps as PDFs or images