'long context' 검색 결과

Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extend an existing model to handle longer inputs
• Compare methods for representing token positions
• Plan additional training with long documents

Manage the limited information an LLM can process at once. Use importance-based summaries, selective trimming, token counting, and content placement to plan what stays in context and address information loss during long conversations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning how to handle conversations near the token limit
• Summarizing a long dialogue while preserving key information
• Reviewing the placement of important instructions and facts

Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing agents that edit their own conversation history
• Preserving exact values during long tasks
• Recovering from context overflow

Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extend an existing model to handle longer documents
• Compare context extension methods
• Implement position information in attention layers

Diagnose why an AI agent becomes less reliable as conversations and documents accumulate. Distinguish missed information, persistent false claims, irrelevant material, mixed tasks, and conflicting sources, then choose ways to clean, reorganize, or separate the context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating declining quality in long conversations
• Recovering from false claims that persist after correction
• Resolving conflicts between retrieved documents

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rotUse when "context window, token limit, context management, context engineering, long context, context overflow, llm, context, tokens, memory, summarization, optimization" mentioned.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Help manage long Claude Code sessions by suggesting when to summarize accumulated context with /compact. Uses context size and tool calls as signals, with guidance on saving plans and choosing suitable breaks between task phases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Managing long sessions near the context limit
• Summarizing research before implementation
• Switching tasks after debugging

Helps agents manage long tasks by checking for forgotten instructions and drifting conventions. It guides progress summaries, rule checks after context compaction, and handoff notes when work should continue in a fresh session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping rules consistent during long agent sessions
• Rechecking decisions after context compaction
• Preparing handoff notes for a fresh session

Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like lambda durable functions, durable execution, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, reliable serverless applications, context.step, context.wait, context.invoke, context.runInChildContext, withDurableExecution, DurableContext, UnrecoverableInvocationError, durable-execution-sdk, qualified ARN invocation, and durable handler replay.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Estenda janelas de contexto de modelos transformer usando RoPE, YaRN, ALiBi e técnicas de interpolação de posição. Use ao processar documentos longos (32k-128k+ tokens), estender modelos pré-treinados além dos limites de contexto originais ou implementar codificações posicionais eficientes. Cobre embeddings rotativos, vieses de atenção, métodos de interpolação e estratégias de extrapolação para LLMs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Estratégias para gerenciar janelas de contexto de LLMs, incluindo sumarização, recorte, roteamento e prevenção de degradação de contexto. Use quando: janela de contexto, limite de tokens, gerenciamento de contexto, engenharia de contexto, contexto longo.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan how an AI agent uses limited input space through reusable prompt prefixes, shorter tool outputs, summaries, and task splitting. Measure token use, response quality, and latency to choose optimizations that provide a net benefit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing token use from lengthy tool outputs
• Improving prompt cache reuse
• Planning context budgets for long conversations

Preserve the context of long Claude Code sessions across compaction, which shortens conversation history. Create a restore map linking decisions, files, and next steps, then use ranked readings and targeted transcript lookups to rebuild working context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a restore map before conversation compaction
• Rebuilding working context after /compact
• Preserving decision history across long-running work

[omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. Use when the user says: context-budget-review, context budget review, context budget, token budget review, token budget, prompt budget, prompt caching, prompt cache.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when starting work on a new product, client, or market — this skill creates the file `.agents/product-marketing-context-global.md` that 60+ other global skills read before they write anything: product, ICP, positioning, proof, objections, brand voice, pricing, and KPIs, with a region variant for US, EU, SEA, or LATAM. Run once, reuse forever. Trigger on 'set up marketing context', 'new client setup', 'onboard a new product', 'the AI does not know my product', 'US marketing context', 'EU GDPR setup', 'SEA market context', 'LATAM setup'. Also use when the user complains every answer comes back generic because nothing about the business was ever provided. Not for — a personal brand belonging to a founder, coach, or creator, see `22-personal-brand-context-global`; deep persona and JTBD research, see `09-customer-insight-global`; the period plan itself, see `00-marketing-plan-global`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment it happens, and run a recovery protocol when the canary trips. Use when the user mentions a "canary", "context canary", or "canary check", asks to detect context rot / compaction / drift, says "you stopped using my name" or "did you lose context", asks "how degraded is your context", or wants an early-warning system for long agent sessions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when the user mentions starting over in a long session.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. NOT for runtime context decisions (what to read, when to compact) — see mk:context-engineering. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Find context from past coding sessions in Hindsight long-term memory. Reuse memories already loaded for the session, search for missing details, and reason over accumulated records when answering questions about decisions, project context, or preferences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revisit the reasons behind past implementation decisions
• Recover project context discussed in earlier sessions
• Check previously discussed preferences

Create and maintain project documents in conductor/ covering the product, technology stack, development workflow, and work units. Extract context from existing code, check document consistency before implementation, and update documentation as the project evolves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up context documents for a new project
• Document an existing codebase for onboarding
• Check project documents before implementation

Set up the OpenViking long-term memory plugin for OpenClaw through conversation. The skill handles installation, configuration, and verification so chat facts can be saved and relevant memories recalled across sessions, using an existing OpenViking server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add long-term memory to OpenClaw
• Recall saved facts across chat sessions
• Separate memories by assistant or sender