В каталоге 183 730 навыков в 14 категориях.
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and inte...
Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会...
Temporary work storage and memory patterns. Use when storing intermediate work products or managing agent workspace orga...
Gerencia persistencia de contexto, decisoes e learnings do projeto. Armazena e recupera informacoes entre sessoes para m...
Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to...
Use after completing any phase activity - updates project_state.md, project registry, ensures files are in correct locat...
Standardized workflow for discovering, reading, writing, and compacting the project's memory file (memory.instructions.m...
Automatically activates after significant decisions, pattern discoveries, or context that should persist across sessions...
Use when installing or configuring memory_map, writing CLAUDE.md session-setup instructions, choosing what to save in me...
Use and troubleshoot the Memory MCP server for episodic memory retrieval and pattern analysis. Use this skill when worki...
How to use the Memory MCP server to store and retrieve knowledge graph entities, relations, and observations.
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvem...
Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` wher...
将领域记忆文件中的成熟经验合并到其指令文件中。**自动触发**: 当记忆文件多次更新或有成熟内容时,自动建议合并。也可手动触发: `/memory-merger >领域 [作用域]`
C++ and Rust memory model skill for concurrent programming. Use when understanding memory ordering, writing lock-free da...
Node.jsアプリケーションのメモリ監視とリーク検出パターン。PM2、V8ヒープ分析、メモリプロファイリングを活用した効率的メモリ管理を提供。 Anchors: • Observability Engineering / 適用: メモリ...
Saves a note or decision to project memory; --lesson saves what a correction taught. Use when the user wants something r...
Rebalances context across Memory, Custom Instructions, knowledge files, and User Preferences in Claude Projects. Audits...
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quan...
The Release/Acquire pair the ring rests on, and what a change to any atomic ordering owes in evidence. Use when touching...
Spatial organization of knowledge in navigable directories
Hierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (deci...
Design and construct virtual memory palaces for spatial knowledge organizationusing mnemonic techniques.Triggers: memory...
Persistent memory patterns for moflo agents — session memory, long-term knowledge, pattern learning, and cross-session c...
Patterns for structuring MEMORY.md and topic-based memory files for Claude Code persistent memory. Use when the user ask...
Provide session lifecycle hooks for cross-platform context persistence. Use when maintaining state across sessions or cr...
Cross-session persistence for user preferences, implementation guide for Memory feature.
Memory Profiler Setup - Auto-activating skill for Performance Testing.Triggers on: memory profiler setup, memory profile...
Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, saf...
Audit this repo's auto-memory files and suggest promoting each one to a more persistent layer — user or repo CLAUDE.md,...
This skill should be used by the maigo orchestrator whenever a Soyo or Anon output contains a
File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize...
Instrument RAG retrieval, memory operations, and context management
Search and recall memories from claude-mem
"Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from h...
Retrieve task-relevant project and global memory without loading everything. Load when the user asks what we decided, re...
Use when an agent needs to look up what it already knows before doing new work, or when an operator wants the facts behi...
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from hi...
Use this skill when the user asks to refine Codex memory, improve Codex instructions or config, analyze session or histo...
This skill should be used when the user asks to review, consolidate, organize, or clean up memories. Triggers on request...
Tier 2 episode extraction, the reflexion write path split out of the memory router per ADR-063. Extracts an episode from...
Two-stage memory retrieval skill using semantic matching and utility filtering for higher-quality recall.
Review the file-based memory store via the Agent Monitor Config Explorer API: the user and project CLAUDE.md plus per-pr...
Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when t...
Review governed memory proposals, policy tags, tombstones, and effective memory.
Memory Safety security skill
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C....
Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentia...
Find and interpret memory, undefined-behavior and data-race bugs in C and C++ programs with Clang/GCC sanitizers (Addres...
Save current session context to claude-mem
Execute when you see "[MEMORY_KEEPER]" in hook output. Follow the numbered steps exactly to save session memory.
Advanced memory scanning strategies, selecting correct data types, unknown initial value workflows, changed/unchanged fi...
PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and cont...
Searches conversation history and semantic memory to find previous discussions, decisions, and context. Use when the use...
SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting
Semantic search over global agent memory. Use to retrieve previously learned patterns, decisions, gotchas, and workaroun...
Tier 1 semantic memory search across the Serena corpus with progressive disclosure and token-budget warnings. The focuse...
Use when running thrum memory search with RAG (--near), composing complex predicate stacks, paginating large result sets...
Review an AI system for persistent memory poisoning, unsafe episodic or long-term memory writes, retrieval scope failure...
Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish...
启用并配置 Moltbot/Clawdbot 的持久化记忆搜索功能。当用户需要设置记忆功能、修复"金鱼记忆"问题,或配置 memorySearch 时使用。涵盖 MEMORY.md、每日日志和向量搜索的设置。
Configure and initialize memory systems for persistent context.
Nightly memory consolidation for agents - reduces context drift and catastrophic forgetting between sessions. Use when s...
Append a session/state snapshot to MEMORY.md (regardless of where it lives — for this repo it's `founder/MEMORY.md`). Us...
Load bounded working context at the start of a coding session. FIRES ON EVERY FIRST USER MESSAGE in a fresh session, reg...
View statistics and recent entries from the persistent memory database. Shows session count, knowledge areas, facts, and...
Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the use...
Memory Sync Skill
Review the auto-extracted candidates in `.claude/memory/_pending.md` and commit keepers to the canonical memory files (`...
Persist and recall context between sessions
Sync the current repo's memories both ways between pi's memory store and Claude Code's auto-memory, proposing every add...
Persist new context, terms, learnings, and settled lightweight decisions. Use when the user says remember this, save thi...
Guided workflow for maintaining strategic redundancy between Serena memories and project documentation. Use after signif...
多台电脑(家里 / 公司)各有一个 Obsidian 记忆库时,用一个私有 GitHub 仓库做「最新并集」中转,实现双向同步。覆盖白名单 gitignore 设计、代理环境下 git 协议不通时改用 GitHub API 推送、PAT 的...
使用遗忘曲线管理会话记忆(SQLite):按永久记忆/衰减记忆分类写入、按时间自动更新 fresh/active/fading/blurry/forgotten 状态、按话题检索、执行遗忘删除、从周归档恢复,以及生成每周记忆汇总。适用于用户...
Sets up a file-based memory system so Cowork always knows who you are, how you work, and where your projects stand. For...
Persistent cross-session memory management. Enables agents to remember user preferences, project conventions, and past d...
AID Memory System for session feedback, learning cycles, and skill improvement. Manages state, feedback collection, and...
Automatic documentation memory system for AI agents. Ensures context is loaded at session start and documentation is upd...
当需要为 AI 设计记忆存储、检索、应用和更新机制时调用此 skill。典型场景包括:设计持久化记忆架构(用户偏好、历史上下文、项目知识)、定义记忆的创建/读取/更新/删除生命周期、实现静默记忆应用(不在回复中透露记忆内容)、管理敏感记忆边...
Complete guide to the AgenticFleet memory system. Read this first.
Tiered, low-token project memory protocol for .toh/memory/ — 7 files across 3 tiers (Tier 1 active.md + summary.md alway...
Core principle: Implement and maintain the OpenClaw Memory Stack - a layered memory system that preserves AI knowledge a...
Design short-term, long-term, and graph-based memory architectures
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across...
This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowle...
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tra...
Design short-term, long-term, and graph-based memory architectures. Use when building agents that must persist across se...
Guided setup for sharing moflo's durable learnings through a git-tracked JSONL artifact — for a whole TEAM on one repo,...
Run E2E memory pipeline test — embed text, store in Qdrant, search and retrieve. Use to validate the memory system is wo...
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memo...
Keep Claude Code's always-loaded MEMORY.md index healthy — trim over-length entries, move done work to the archive, fold...
Привести в порядок всегда-загружаемый индекс памяти MEMORY.md на этой машине (macOS/Linux) — подрезать, унести закрытое...
Automated multi-tiered memory management (HOT, WARM, COLD). Use this skill to organize, prune, and archive context durin...