Claude Skills by majiayu000

Unified memory capture with routing - session compact or quick tips. Triggers on "memory capture", "compact session", "save session", "quick tip", "memory tips", "记录", "压缩会话".

Manages memory, SSOT files, and Plans.md operations. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, or migration. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.

在對話被 Summarize 壓縮前，主動將詳細記憶外部化到 Memory Bank，避免重要上下文遺失。

在對話被 Summarize 壓縮前，主動將詳細記憶外部化到 Memory Bank，避免重要上下文遺失。

在對話被 Summarize 壓縮前，主動將詳細記憶外部化到 Memory Bank，避免重要上下文遺失。

Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.

Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".

Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under ~/.claude/projects/*/memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke with /memory-cleanup.

Store and recall long-term memory. Use when persisting facts learned during conversations or recalling stored knowledge about projects and preferences.

Compact current session memory into structured text for session recovery. Supports custom descriptions and tagging.

Recall past conversations and facts from agent memory

Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid.

Workflow for checking memory before code exploration. Auto-loaded when answering questions about code, architecture, or patterns.

Continuous learning system that forges knowledge from work sessions into permanent memory. Use when: (1) after completing non-trivial debugging or investigation, (2) discovering patterns not obvious from documentation, (3) finding workarounds worth preserving, (4) "what did we learn?", (5) "save this pattern", (6) "extract a skill". Supports monorepos with distributed context files. CLI-agnostic (works with Claude Code, OpenCode, Codex, Cursor, and any tool supporting the Agent Skills standard).

Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.

Complete reference for Claude Code's memory management system including all file types, locations, import syntax, and best practices. Use when planning or managing CLAUDE.md and related memory files.

Persistent key-value storage for session data, conversation context, and agent state. Use this skill when the user requests storing or retrieving memory entries such as "Store this in memory", "Remember this preference", "Recall the previous conversation", or "List all memory entries".

Persistent memory across sessions. Save project state and user preferences. Never save secrets.

Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts

Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts

Capture discoveries, fixes, solutions, and patterns into a searchable knowledge graph for future reference

Copy and snapshot all important agent context (MEMORY.md, memory/*.md, AGENTS.md, SOUL.md, etc.) into a dedicated archive directory or repo. Use this skill when you want to back up your memories, context, or configuration files in preparation for maintenance, corruption recovery, or transferring to another host.

Persistent context/memory management MCP server. Stores and retrieves context across AI sessions.

Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with acti...

Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory manage", "update claude", "update memory", "generate docs", "更新记忆", "生成文档".

Use when the user asks to "remember project context"; manages SEO/GEO memory, hot-cache, active work, archive tiers, and privacy cleanup. 项目记忆/跨会话

'> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE

Gerencia persistencia de contexto, decisoes e learnings do projeto. Armazena e recupera informacoes entre sessoes para manter continuidade. Use quando: salvar decisoes, recuperar contexto, persistir learnings.

Use after completing any phase activity - updates project_state.md, project registry, ensures files are in correct locations, maintains lean memory

Automatically activates after significant decisions, pattern discoveries, or context that should persist across sessions. Saves decisions to org memory, patterns to pattern library, and context to user memory. Activates when important architectural choices are made, new patterns are discovered, or valuable context emerges.

Use and troubleshoot the Memory MCP server for episodic memory retrieval and pattern analysis. Use this skill when working with MCP server tools (query_memory, analyze_patterns, advanced_pattern_analysis), validating the MCP implementation, or debugging MCP server issues.

Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`.

Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.

Designs memory palace structures with spatial layouts and domain organization. Use when creating a new palace or planning knowledge architecture by hand.

- What It Is

Hierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (decisions). Semantic search across all memories with zero cloud dependency.

Patterns for structuring MEMORY.md and topic-based memory files for Claude Code persistent memory. Use when the user asks about remembering things across sessions, wants to organize project knowledge, or needs guidance on what to save vs not save.

Provide session lifecycle hooks for cross-platform context persistence. Use when maintaining state across sessions or creating handoff documents. Not for in-memory variables or temporary state.

Filesystem-based knowledge management. Triggers on "remember", "save context", "knowledge base", "document decision".

File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize project memory. Activate when starting tasks, encountering errors, making decisions, or when context may be lost between sessions.

Use this skill when the user asks to refine Codex memory, improve Codex instructions or config, analyze session or history patterns, optimize context efficiency, or update global or project-local Codex guidance based on repeated interaction patterns.

Unified four-tier memory system for AI agents. Tier 1 Semantic (Serena+Forgetful

记忆检索服务。让 Agent 自主决定是否需要回忆过去的对话。 **使用场景**： 1. 用户问"之前我们讨论过什么"、"上次说的那个..." 2. 需要参考之前的上下文来回答当前问题 3. 用户提到某个之前讨论过的主题 **不要滥用**：简单问题（如写代码、解释概念）不需要检索记忆

Configure and initialize memory systems for persistent context.

View statistics and recent entries from the persistent memory database. Shows session count, knowledge areas, facts, and recent activity.

Automated multi-tiered memory management (HOT, WARM, COLD). Use this skill to organize, prune, and archive context during memory operations or compactions.

Permanent memory using Lisa.

Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".

維護和更新專案的 Memory Bank 記憶系統，確保專案狀態在對話間持久化。

更新 Memory Bank 檔案。觸發：memory、記憶、進度、存檔、sync、做到哪。