Complete agent memory + performance system. Extracts structured facts, builds knowledge graphs, generates briefings, and enforces execution discipline via pre-game routines, tool…
Use when user says 'remember this', when deciding where to store learnings or context, when about to edit CLAUDE.md or create a skill, or when routing any persistent information.
Go application memory profiling and analysis. Use when investigating memory leaks or high memory usage.
Use when when designing or optimizing backends that handle large MS datasets (mzML, mzXML, CDF files via MsBackendMzR), to verify that claimed memory advantages of on-disk or…
Use when when benchmarking or validating the scalability of single-cell algorithms that claim linear or sublinear space complexity, particularly when processing datasets with ≥10…
Persistent role-scoped memory across sessions. The agent that worked on your codebase yesterday knows things today.
Audit project memory files for stale entries — items where the cited PR is merged, the cited bug is fixed, the cited file/function no longer exists, or the gotcha was patched out…
Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
面向AI Agent记忆文件的安全扫描系统，解决Prompt注入检测难、凭证泄漏被动发现、扫描误报高、跨文件威胁关联缺失四大痛点. 提供七大威胁类别检测、五级安全分级、本地+可选远程LLM分析、跨文件威胁关联、误报抑制、隔离与恢复、增量扫描七大核心能力.
Read Cody's temporal Neo4j memory graph. Use when drafting, briefing, or answering questions about current or historical contact/deal state.
Scan all memory files, documentation (**/docs/**/*.md), and README files (**/README.md) for drift, contradictions, and stale references.
Use when the user learns something worth remembering, makes a decision, discovers a preference, or uncovers a pattern. Auto-triggers to save to .claude/memory/ in the right file.
Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory.
Periodic memory maintenance — archive session files, convert recurring knowledge into summaries, update the memory index.
Use when long-term knowledge retention is needed (weeks to months), studying for exams or certifications, learning new job skills or technology, mastering substantial material…
Load only the minimum relevant memory for a task using 3-level progressive disclosure. Activate before context-building — never load full memory dumps.
Memory hygiene audit -- checks for stale, contradictory, low-confidence, and consolidation-candidate memories, then offers cleanup actions with user confirmation.
Reviews stored memory quality by detecting duplicates, contradictions, and stale entries with actionable recommendations.
Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C.
Scores and filters retrieved memory against trust and poisoning risk. Use for: sanitize memory, trust score retrieval, clean knowledge graph, `semantic-memory-manager`.
Save current session context and generate a handoff prompt for continuing in a new session. Use when the user says "memory-save", "세션 저장", "정리해줘", "context 저장", or when context…
Scans OpenClaw agent memory files and workspace configs for malicious content, credential leaks, 。Use when 需要生成营销文案、写作内容、标题优化、内容创作时使用。不适用于纯技术文档撰写。适用于独立开发者、企业团队和自动化工作流场景。
Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift.
Capture a conversation's essence into the active host's memory directory. Supports Codex with a Workbench project-memory convention and Claude Code project memory without assuming…
Semantic search across Ruflo AgentDB with HNSW vector indexing
Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their…
Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.
Store a memory in ourmem. Use when user says remember, save, store, or don't forget something.
Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events.
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform not...
记忆体系瘦身与管道去重。MUST trigger when the user says: "瘦身", "清理记忆", "/thin", "记忆瘦身", "memory瘦身", "记忆减肥", "索引瘦身".
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.
Agent-controlled memory plugin for OpenClaw with confidence scoring, decay, and semantic search. The agent decides WHEN to store/retrieve memories — no auto-capture noise.
Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memory_add.
Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory…
Open the agd-memory project memory in a local browser viewer. Spins up a small http server on localhost and prints the URL.
Use when capturing, recalling, reviewing, or consolidating durable project memory across sessions, especially prior decisions, constraints, procedures, and episodes that must…
Write a temporal fact into Cody's Neo4j memory graph. Use when the user explicitly corrects Cody, updates a deal, changes a recipient preference, or confirms a high-stakes fact.
Enable AI agents to interact with Memos, an open-source self-hosted note-taking tool with REST and gRPC APIs.
Crea y actualiza documentos en el vault de Mente (Obsidian) en la intranet .casa. Garantiza que todos los documentos tengan wikilinks bidireccionales para el grafo de…
Drive MeshVault over MCP to sculpt, paint, repair and reshape 3D objects, optionally performing live for human observers (observation seat).
Record a discovery, problem, or gotcha to knowledge/draft/. Use when you observe something worth remembering — a bug, a surprise behavior, an external fact, or a design decision.
Search the knowledge base before designing or implementing. Use when starting any non-trivial design or implementation task directly (not via sub-agent).
How to write frontmatter/Properties that conform to Metadata Menu (mdelobelle's Obsidian plugin) — the fileClass + field-definition system that types and validates note metadata.
Talk to My First Million Hosts about their expertise. My First Million Hosts provides authentic advice using their mental models, core beliefs, and real-world examples.
Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index.
Build or inspect a Mission Control codebase knowledge graph. Use for file/function/class maps, dependency relationships, architectural layers, guided tours, and searchable…
Build or inspect a graph-style map of docs, wiki pages, claims, entities, and relationships through Mission Control.
Define memory, state, checkpoints, resumability, and retention policy for Mission Control workflows and agents.
Гейт перед /clear — read-only проверка «всё ли записано», вердикт из exit code скрипта, а не из реплики модели.
Генерирует текст для claude.ai → Project → Instructions из шаблона + персонализирует под текущий проект. Кладёт результат в Obsidian для копипаста.
Обзор всех зарегистрированных mm-проектов одним экраном — статус, тип, GSD-фаза, последняя активность, число открытых вопросов.
Закрывает текущую Claude Code сессию — сохраняет лог в Obsidian/Claude/Sessions/, обновляет project note, обновляет INDEX.md, перегенерирует handoff.md (для Project Knowledge…
Онбординг/персонализация mm-системы под конкретного пользователя — спрашивает имя, чем занимается, стек, язык, путь к Obsidian vault, и записывает это в личный gitignored-оверлей…
Создаёт приватный vault-репозиторий памяти проекта в Obsidian и пушит его на GitHub для синхронизации с claude.ai Knowledge.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help…
Use when applying The Almanack of Naval Ravikant to turn principles into recall prompts, reflection cards, or spaced repetition items.
Creates, edits, and manages Obsidian vault content including notes, templates, daily notes, and dataview queries.