🧠Memory and Context Management Skills
Browse skills in the Memory and Context Management category.
Cc Skill Continuous Learning
A powerful skill for Claude agents.
Session Handoff
A powerful skill for Claude agents.
session-continuation
Project-agnostic guidance for continuing work across Claude sessions. Ensures context recovery, task resumption, and state reconciliation.
smith-ctx
Universal context management with proactive recommendations. Agent checks context levels and recommends compaction/summarization to users. Always active as foundation for context optimization.
context-advisor
Provides feedback and suggestions for improving AI context files (CLAUDE.md, context.md, commands, agents, references). Use when discussing context engineering, reviewing AI instructions, or optimizing template files for AI coding assistants.
wrap
Session wrap-up workflow. Use when user asks to "wrap up session", "end session", "/wrap", or wants to analyze completed work before ending.
smith-ctx-cursor
Cursor context management with /summarize command, @ mentions for file inclusion, and @codebase discovery. Use when operating in Cursor IDE or when context exceeds 60%. Activate for context optimization in Cursor sessions.
context-manager
Maintain, retrieve, and normalize shared project context: decisions, constraints, standards, and task state for multi-skill workflows.
smith-ctx-kiro
Kiro-specific context management with terminal limitations, Serena MCP as mandatory tool, and file operation workarounds. Use when operating in Kiro IDE. LOAD FIRST in all Kiro sessions - critical platform constraints that prevent hangs and failures.
planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
session-behavior
Core behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should communicate and behave across all interactions. Use this skill to establish consistent behavior patterns at the beginning of a session. The skill defines tone, proactivity level, and request handling strategies that should be applied throughout the session. THIS SKILL HAS HIGH PRIORITY - always load at session start and re-trigger periodically to avoid behavioral drift. During context compaction, these rules should remain at the top priority.
autoskill
Analyze coding sessions to detect corrections and preferences, then propose targeted improvements to Skills used in the session. Use this skill when the user asks to "learn from this session", "update skills", or "remember this pattern". Extracts durable preferences and codifies them into the appropriate skill files.
smith-ctx-claude
Claude Code context management with /compact and /clear commands, CLAUDE.md persistence, and Tool Search optimization. Use when operating in Claude Code IDE or when context exceeds 60%. Activate for context optimization in Claude sessions.
smith-ralph
Ralph Loop integration patterns for iterative AI development. Use when starting Ralph loops, managing iterations, or recovering from context compaction. Covers TDD, debugging, context management, and memory persistence.
retrieval
Search past Claude Code sessions for relevant context. Use when historical decisions, implementations, or discussions might inform the current task - especially during planning or when the user references something done before.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) The agent realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
distill
Distill session episodes into persistent memory patterns
memory
Add new instruction to the global CLAUDE.md file
ctx
View and manage hierarchical context for the current directory
context-manager
Manages context across multiple agents and long-running tasks. Use when coordinating complex multi-agent workflows or when context needs to be preserved across sessions. Essential for projects exceeding 10k tokens.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific...
agent-memory
ユーザーが「記憶して」「思い出して」などのメモリ操作を指示した時に使用。重要な調査結果、アーキテクチャの決定、問題の解決策を発見した時にも積極的に保存を提案する。
health-context
Retrieve health history for informed decisions. Use when discussing medications, supplements, skincare, diet, fitness, or any health-related product evaluation.
do-workflow-jit-docs
사용자 의도와 프로젝트 컨텍스트를 기반으로 관련 문서를 지능적으로 발견, 로드, 캐싱하는 Just-In-Time 문서 로딩 시스템
memory
Manage transaction memory to view patterns, add quick notes, search for merchants, and clean up outdated entries. Use when you need to check what's in memory, add new learnings, or maintain the memory file.
feedback-loop
Update CLAUDE.md or rules when patterns of errors emerge
agent-assistant
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agentsTrigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extractionUse when: User reports agent is stuck, looping, or needs memory/learning management
smart-context
**SMART CONTEXT v1.0** - '컨텍스트', '관련 코드', '참조', '토큰 절약', '효율적 분석' 요청 시 자동 발동. codebase-graph 기반으로 필요한 컨텍스트만 선택적 추출. 토큰 72% 절감, 정확도 92% 달성. 모든 코드 분석 작업의 기반 레이어.
conversation-management
Build conversation history UI with sidebar, thread switching, and conversation CRUD operations. Implements conversation list, rename, delete, and persistence. Use when adding conversation management features for Phase 3.
graphiti
Comprehensive skill for Graphiti and Zep - temporal knowledge graph framework for AI agents with dynamic context engineering
context-constellation
Map non-linear connections across files, thoughts, and projects. Reveal hidden patterns in seemingly unrelated work. Use when feeling scattered, when working across multiple domains, or when sensing connections but unable to articulate them.
qdrant-manager
Manage Qdrant Cloud collections, including vectorization of textbook chapters and metadata tagging for RAG retrieval.Agent: AIEngineer
context-manager
Manage conversation context and memory for optimal AI performance
memory-system
Use when persisting learnings, loading previous context, or searching past decisions - covers memory file structure, tools, and when to update each file
recall
Search the AI-ready vault memory system by keyword or concept. Use when needing to retrieve previously stored information, find past decisions, or locate relevant context from earlier sessions.
implement-subtask-rules
container-workerがSubtask実装時に参照する詳細ルール（設計書参照、粒度、TDD、品質レビュー、出力形式）を定義
reflect
End-of-session consolidation for AI-ready vaults. Use before ending a work session to capture learnings, store important memories, and preserve context for future sessions. Counterpart to /hydrate.
context-prep
Prepare optimal context package before delegating tasks to sub-agents
filesystem-context-manager
Maintain context across Claude Code sessions using filesystem persistence. Prevents context loss, enables plan continuity, and supports multi-session workflows.
optimizing-context
Audits and optimizes context, memory, and skill use for projects. Reviews CLAUDE.md files, .claude/rules/, and skill configurations for efficiency. Use when context feels bloated, skills aren't triggering correctly, or memory needs organization.
remembering-conversations
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
session-manager
Manage named Claude Code sessions for CircleTel workflows. Use when starting feature work, resuming previous sessions, organizing multi-day tasks, or switching between different work contexts like admin, dashboard, or payment features.
retraction-handler
Handles message retraction psychology for relationship simulation
claude-md-writer
CLAUDE.md 파일을 best practices에 맞게 수정/관리. Use when updating project instructions, adding new sections, or refactoring CLAUDE.md for clarity and conciseness. (project)
save-to-memory
Save current conversation to persistent memory. Use when user says "save this", "remember this", "store this for later", or wants to preserve context for future sessions.
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.
init-memory
Initialize the memory system in an AI-ready vault. Creates the folder structure, Memory.md dashboard, and example files needed for cross-session memory persistence. Use when setting up a new vault or adding memory capabilities to an existing vault.
agi-memory
Use when working with the AGI Memory System - creating memories, querying, testing, database operations, or understanding the memory architecture.
momentum-anchor
Create rich resumption points when hyperfocus breaks. Capture energy state, not just tasks. Use at the end of work sessions, when interrupted, or when sensing focus shifting.
remember
Store a memory in the AI-ready vault memory system. Use when encountering information worth preserving across sessions—decisions made, patterns discovered, facts learned, or significant events. Creates properly formatted memory files with metadata.