В каталоге 183 730 навыков в 14 категориях.
When the user wants to build or tune a memetic algorithm - a genetic algorithm hybridized with local search - covering L...
Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Use when se...
Cross-session shared memory for agents. Use at session start to load the persistent bias-log via `mcp__memex__recent_obs...
Execute AI-powered command-line tasks with memory, replay, and resume capabilities using memex-cli. Use when (1) Running...
Search, read, create, edit, and maintain knowledge in a Memex KB via the `mx` CLI. Use when the user asks to search the...
This skill should be used when the user asks to "search the KB", "find documentation", "add to knowledge base", "documen...
Log a bias-log / vipassana observation to the memex store the moment a reasoning pattern surfaces, mid-session or at clo...
Memex(RL)
Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, ru...
Run the local pre-commit gate for the memex repo before staging a commit: format check, clippy with warnings denied, and...
Close out a finished memex milestone slice by writing the handoff trail: update `docs/CONTINUE_HERE.md` §1 current-state...
Optimize agent long-term memory by treating it as an information bottleneck problem. Dynamically compress redundant info...
Query and analyze ACO pheromone graphs in Memgraph. Use for prime candidate queries, pheromone analysis, path validation...
Review code changes in Memgraph's storage layer, including MVCC, concurrency patterns, WAL, recovery, DDL operations, in...
Expert skill for JavaScript memory leak detection using Facebook MemLab. Configure MemLab scenarios, execute memory leak...
Install and configure memloom end to end. Daemon, config, MCP registration, Claude Code capture and recall hooks, first...
Use memloom memory well during any task. Recall before starting, save decisions and preferences as they happen, resolve...
Monitor and act on opencode memory health. Run this skill when you notice opencode feeling slow, suspect a memory leak,...
IRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH...
Wenn es um Internes Rechtsgutachten: Gutachten-Gerüst in Plugin für die studentische Rechtsberatungsstelle geht: erstell...
SQLite 기반 메모 저장, 조회, 삭제 (사용자 선호도, 중요 정보 기억)
Erstellt ein Gutachten-Gerüst nach der deutschen Gutachtenmethode (Obersatz — Definition/Norm — Subsumtion — Ergebnis) m...
Draft top-down artifacts — a written memo articulating how the world changes and why the user is uniquely positioned to...
双层结构化长效记忆专家 (Kontext-Aware)
Use when evaluating business documents for structural integrity and persuasive logic.
Capture a life story — your own or a parent's/grandparent's — into a keepsake, using good interview questions and a stru...
Operate MemoriLabs/Memori, its agent-memory SDKs, cloud/BYODB modes, runtime configuration and SQL storage integration....
Mantem o estado append-only de um caso civel — partes, vara/comarca, numero, fase processual, pedidos, prazos, atos prat...
Gerencia memoria persistente do usuario. Use para salvar/recuperar preferencias, fatos aprendidos e contexto entre sesso...
Created a new skill called "create JSON file" for generating JSON files from JavaScript/TypeScript objects with proper e...
Audit .agents/memories/ for staleness, duplicates, and orphan facts. Mark stale entries, propose archive moves, surface...
Update agent memory (Sessions, Lessons, Preferences, Checkpoint, Context) and Brief.md
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
Use this to save important implementation decisions, patterns, or context to the Nori knowledge base for future sessions...
Swift 6.2 InlineArray and Span types for zero-overhead memory access, fixed-size collections, and safe pointer alternati...
MONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substra...
Persistent memory system for preferences, facts, and notes
Route memory operations to appropriate backends (Graphiti for knowledge, AgentDB for coordination).
Memory dump analysis - process injection, credential extraction, malware
Imported skill memory from langchain
Find reviewed context, capture evidence or curate maintained claims. Use when: prior evidence can change an action, or l...
Use when working with memory components - Flash, EEPROM, SRAM, DRAM. Includes adding patterns, parsing memory MPNs, extr...
AI DevKit · Use the memory CLI as a durable knowledge layer. Search before non-trivial work, store verified reusable kno...
Store and recall long-term memory. Use when persisting facts learned during conversations or recalling stored knowledge...
Use this skill when the user wants to build or update a persistent, fast-lookup memory store for a project or directory...
Orchestrate persistent agent memory across coding sessions, repos, and tools. Load when the user asks to remember, recal...
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memor...
Semantic memory and context - store and retrieve information with embeddings for similarity search. Use for long-term me...
Execute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past de...
Persistent key-value storage for session data, conversation context, and agent state. Use this skill when the user reque...
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
Two-layer memory system with grep-based recall.
Use when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emoti...
Persistent knowledge storage using basic-memory CLI. Use to save notes, search memories semantically, and build context...
Deliberately search, add to, or curate your long-term memory with the `memory` tool — beyond the automatic recall/captur...
Persist decisions, preferences, and project state across sessions using structured memory types
Core memory system definition. Defines the persistent memory schema, operations, and self-modification rules. All memori...
Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "tod...
Filesystem-based knowledge management. Triggers on "remember", "save context", "knowledge base", "document decision".
State tracking, semantic cache, memory compaction, and agent histories.
Unified four-tier memory system for AI agents. Tier 1 Semantic (Serena+Forgetful search), Tier 2 Episodic (session repla...
Persistent, token-efficient project memory. When ON, maintains a `.shob/memory/` folder of structured `.md` files so the...
中文网文创作档案与记忆系统。当用户要记录/保存大纲人设设定、跨会话继续写之前的书、问"我写到哪了/这个伏笔回收了吗"、给书做版本快照(像git)、或管理多本书的创作进度时使用。在书的文件夹里维护持久化档案,所有写作技能共享读写。
Permanent memory using Lisa.
Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what...
SSOT/memory + cross-tool search. Guards decisions.md, patterns.md. Triggers: memory, SSOT, decisions.md, patterns.md, ha...
Memory and continuity: the RSI tree in `_memory/memora.db` — walk champions and pruned dead-ends before acting, branch a...
无限的可扩展记忆系统,通过分类存储补充代理的内置内存。
Searches and retrieves relevant memory items for context
Diagnose, explain, and fix Swift and Apple-platform memory leaks, unexpected object retention, deinit failures, heap gro...
Cross-session memory — store, recall and query project knowledge across sessions. Detects whatever persistent memory is...
Establishes a persistent "Long-Term Memory" file to prevent context amnesia across sessions.
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**:...
Expert skill for custom memory allocator design optimized for language runtime needs
Embedded memory analysis, optimization, and leak detection
对 msMemScope 显存数据做全链路处理:根据用户的显存问题诉求(OOM、显存泄漏、显存占比拆解、Step 间对比等),指导并帮助用户以最合适的 msMemScope 采集配置完成显存数据采集(支持命令行、Python 接口、mstx...
Single-skill wrapper for the 4-layer recall (durable memory → semantic DB → PostgreSQL → daily notes). Use BEFORE saying...
Cross-reference and synthesise daily memory files into patterns, insights, and carry-forward items. Use when asked to re...
Treat memory management as learnable RL policy actions (delete/insert) rather than fixed mechanisms. Enable models to au...
Audit project and global memory for bloat, stale decisions, duplicates, contradictions, unsafe content, missing provenan...
Audit embedded code for stack overflow risks, heap fragmentation, static allocation patterns, and memory leaks. Use when...
Audit the project's persistent agent memories for backfire-risk, stale/superseded state, contradictions, redundancy, and...
Comprehensive health check across CC auto-memory and agent-studio memory systems — detects orphans, duplicates, stalenes...
Audit and clean up Claude's native memory in Claude.ai: find contradictions, outdated entries, duplicates, and noise acr...
Audit and clean up Claude's file-based memory in Cowork: find contradictions, outdated entries, duplicates, and noise ac...
Development with persistent memory checks and automatic logging
Repo-committed project memory — decisions, context, solved mysteries as distilled one-fact files; recall before related...
Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to...
Use when CLAUDE.md or CLAUDE-*.md memory-bank files need creating, auditing, updating, or syncing with the codebase — af...
Memory bank rules, structure, and optimization — complete guide to Pantheon memory management.
Boot de session Claude — lit le HOT_CACHE, les patterns d'erreurs actifs et le log d'erreurs, puis log le demarrage dans...
Browse and compare wiki knowledge by which AI tool originally produced it. Use this skill when the user says "/memory-br...
Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
Explicitly retain, recall, or reflect with the optional source-governed Hindsight and Jev bridge.
Cross-session continuity through pattern compression. Use when need to bridge sessions, accumulate wisdom, or evolve wit...
Unified memory capture with routing - session compact or quick tips. Triggers on "memory capture", "compact session", "s...
Capture durable project memory from work, debates, debugging discoveries, learned conventions, deferred options, and ses...
Automatically classify, route, and retrieve agent outputs, findings, policies, or troubleshooting logs into OKF or Chrom...
Use when an agent needs to record what it learned so future runs can reuse it, or when an operator wants durable notes f...