'long context' 검색 결과

Fetch a URL and save the body to a temp file so you can pipe it through rg / jq / awk instead of dumping the whole page into the conversation. Use this whenever a user gives you a URL to read - articles, docs, PRs, gists, README files, blog posts, anything HTTP. Returns a path on disk; the agent then greps the path for the relevant section and quotes only what matters. Strongly preferred over the built-in webfetch tool when (a) the page is more than a few KB, (b) the user wants to find a specific phrase / table / code block on the page, (c) you need to keep the long page out of context, or (d) you want to inspect raw HTML alongside rendered markdown. Triggers: 'fetch', 'fetch this URL', 'fetch and save', 'fetch the page', 'pull this', 'grab this article', 'read this URL', 'read the docs at', 'mirror this page', 'page is too long', 'save the page so I can grep it', 'put it on disk so I can rg', 'cache this URL'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for static/dynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

에이전트의 과거 대화와 자료를 Pinecone에 저장하고 관련 정보를 검색해 답변에 활용하는 시스템을 구축합니다. 세션 간 장기 기억과 의미 기반 검색의 시제품 제작을 돕습니다.

• 세션이 바뀌어도 유지되는 기억 구축
• 검색한 정보를 에이전트 답변에 활용
• 사용자별로 기억을 나누어 관리

코드 위치 조사, 한두 파일의 수정, 변경 사항 검토를 전담 보조 에이전트에 맡깁니다. 짧고 구조화된 결과를 받아 주 에이전트의 문맥 사용량을 줄입니다.

• 정의와 호출 위치를 찾을 때
• 한두 파일만 제한적으로 수정할 때
• 변경 사항의 결함을 검토할 때

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

Design how an AI agent trims long conversations and large tool outputs while retaining decisions, constraints, failed approaches, and sources. Compare summarization strategies, choose compression triggers, and consider separate subagents to keep intermediate information out of the main conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Managing large search results and tool outputs
• Preserving decisions and constraints during summarization
• Choosing compression triggers and batch processing

Save facts, decisions, preferences, and task outcomes to Hindsight long-term memory. The skill turns what was learned into short notes with context and reasons, choosing either a Bot’s own memory store or a shared store.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving a completed task’s outcome and reasoning
• Remembering a user’s stated preferences
• Recording decisions for future work

Add interactive panels to an MCP server so users can select records, view charts, or follow progress inside a conversation. The skill guides tool connections, interface implementation, sandbox restrictions, and testing in hosts that support these panels.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a searchable contact or file picker
• Display charts and previews inside a conversation
• Show live progress for a long-running job

Make focused interface changes from screenshots, annotations, or visually selected elements. Helps locate the responsible component and apply small style or markup edits while preserving existing behavior, accessibility features, and surrounding design.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adjust a button identified in a screenshot
• Change only one selected card
• Apply interface fixes from visual annotations

Creates a compact handoff from verified work status, including commits, branches, automated checks, blockers, decisions, and the next action. Saves a durable record so another session or the user can resume without reconstructing the conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Handing off work before ending a session
• Moving ongoing work into a fresh conversation
• Saving a checkpoint during a long operation

Design memory systems that help AI agents retrieve relevant past information. Choose short-term and long-term memory structures, compare vector storage options, and review document splitting and retrieval strategies for different kinds of knowledge and experience.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design memory for information used across conversations
• Choose storage for experiences, facts, and procedures
• Review retrieval when an agent misses saved information

Run a saved weekly or monthly report and combine its results with a brief business snapshot. Deliver one briefing with an XLSX workbook, using a connected data source or uploaded files, and reuse the definition for scheduled runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Receive the same weekly or monthly report on schedule
• Review report figures alongside cash and sales context
• Rerun a saved report from CSV or XLSX data

Compare assigned work from connected trackers with TASKS.md, review stale tasks, and fill gaps in stored context about people and projects. An optional comprehensive scan finds possible missed commitments in recent activity, with changes confirmed by the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review assigned tracker tasks against TASKS.md
• Triage overdue tasks and long-standing active items
• Fill missing context about people, projects, and acronyms

List Git commits linked to agent work sessions, with branch or repository filters. See each commit’s message, date, linked sessions, and observation counts to review recorded changes alongside their session context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review recent commits linked to agent sessions
• Filter linked commits by branch
• Review linked commits for a specific repository

Keep plans, research findings, and progress in Markdown files for complex agent work. Separate task plans and automatic planning reminders help the agent recover saved context, track decisions, and identify the next action.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming long research tasks
• Tracking phases and the next action
• Separating plans for concurrent tasks

Document a technical decision in an architecture decision record, or ADR. Capture its context, alternatives, and consequences, assign a record number, and distinguish a proposed decision from an accepted one so dependent work reflects its actual status.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording the reasons behind a technical choice
• Documenting alternatives and consequences of a design decision
• Creating numbered records alongside existing architecture decisions

Explore how coordinating agents can pass relevant working state to workers through KV cache, a model's internal attention memory. Covers task-specific selection, runtime requirements, and comparisons of accuracy, token use, and processing overhead.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing repeated history sent to worker agents
• Comparing internal memory sharing with text summaries
• Assessing runtime support for KV cache compaction

Use Memori through MCP, a protocol connecting agents to tools, to retrieve past decisions and preferences, summarize ongoing work, and resume after conversation compression. It also guides selective long-term memory storage and usage limit checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieve decisions and preferences from earlier sessions
• Review current work when starting a session
• Resume work after conversation context is compressed

Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore models for long sequences or streaming applications
• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations

Use MemOS Local to find past conversations, preferences, and decisions, then retrieve original messages or task context. The skill also guides sharing memories and reusable procedures with local agents or a configured team.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find preferences and decisions from past conversations
• Read original messages and surrounding dialogue
• Share memories with local agents or a team

Compare assigned work from connected trackers with TASKS.md, review stale tasks, and fill gaps in stored context about people and projects. An optional comprehensive scan finds possible missed commitments in recent activity, with changes confirmed by the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review assigned tracker tasks against TASKS.md
• Triage overdue tasks and long-standing active items
• Fill missing context about people, projects, and acronyms

Organize knowledge and specifications in OpenRig so agents can find the right context and preserve what they learn. The skill explains where files belong and how to read documents from a local role up to broader shared guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing where to record a lesson
• Preparing role knowledge for a handover
• Tracing work back to its purpose and shared practices

Translate Figma designs into SwiftUI code, or bring SwiftUI views, screens, and design tokens into Figma. The guidance preserves iOS interface patterns, semantic colors, and SF Symbols names across both directions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a Figma screen in SwiftUI
• Bringing an existing SwiftUI screen into Figma
• Mapping iOS colors and icons between design and code