В каталоге 183 730 навыков в 14 категориях.
Check system memory usage, available memory, and identify cleanup opportunities. Use this skill when the user asks to ch...
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 su...
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) a...
Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory...
Execute and troubleshoot memory-cli commands for episode management, pattern analysis, and storage operations. Use this...
Compact current session memory into structured text for session recovery. Supports custom descriptions and tagging.
MEMORY.md 크기 점검 및 압축. 비대해진 메모리를 정리하여 성능 저하를 방지합니다. /memory-compact로 실행. 대상은 프로젝트 루트 MEMORY.md 전용 — Claude 네이티브 auto-memo...
Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and activ...
Review and sharpen persistent memory so it compounds instead of accumulating. Use when pruning pi-hermes-memory entries,...
Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summariza...
Consolida de forma determinista observations.jsonl, deduplicando, filtrando ruido y archivando entradas antiguas, sin LL...
Background process that proactively maintains memory hygiene. Scans for obsolescence to prune irrelevant data and synthe...
Use when you need reliable context with minimum token load through progressive disclosure.
Recall past conversations and facts from agent memory
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session sta...
Ingest a large dataset into memory as a skimmed map. Cold-store the raw files under a workspace imports directory, censu...
指导 AI 生成简洁的记忆内容描述。触发:"记住这个"、"创建记忆"、"记录一下"、"帮我记住"、"memory"。
Use when writing or editing a memory file that relates to 2+ other memories: add See also: [[stem]] wikilinks so mem-gra...
在 Codex Memories、AGENTS.md、项目文档和临时 handoff 之间整理持久上下文,并管理来源、作用域、失效时间和冲突。适用于用户要求 remember/forget、重复纠正需要长期生效、长任务需要紧凑交接,或已有记...
Review staged memory, help with promotion or rejection, and suggest durable memory updates.
Curate durable, evidence-backed project memory in `.notebook/MEMORY.md`. Use when the user requests memory curator or in...
Manage architectural decisions and insights in memory.jsonl. Use when you need to document strategic decisions, lessons...
Use when a project contains docs/memory/, or when the user asks to remember, retrieve, update, compact, forget, or audit...
Diagnose data-corruption failures in tt-emule operations (wrong values, partial zeros, off-by-N row/col writes). Use whe...
Debug TraitorSim agent memory systems including profile.md, diary entries, trust matrices (suspects.csv), and SKILL.md f...
Record durable project decisions with rationale, alternatives, assumptions, status, and revisit triggers. Load when the...
Interpretive guidance for Claude Code memory management system. Helps choose between memory locations, organize modular...
Best practices for memory architecture design including user vs agent vs session memory patterns, vector vs graph memory...
根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件,并在用户确认后生成可追溯的回忆故事。
Turn travel or lifestyle photos into 4:5 memory-diary pages pairing real photography with a watercolor and colored-penci...
memory/{gotchas,learned}/observations.jsonl raw 관찰을 정제 .md로 변환하는 사용자 트리거 스킬. 핸드오프 의존이 약할 때 의지로 호출. Dreaming-like rebuild...
Audit the current project's agent-memory and, block by block, relocate each entry into a user-controlled home (project d...
Generate evidence-based documentary reports by searching across all 4 memory systems (Claude-Mem, Forgetful, Serena, Dee...
Avoid creating unnecessary intermediate objects in hot paths Use when optimizing code performance. Performance category...
Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-c...
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, che...
End-of-session pass that persists durable facts from the CURRENT session into .claude/memory/. Runs IN-SESSION in the ma...
Keep your AI memory/context file (MEMORY.md, AGENTS.md, custom instructions) healthy over time — pruning the stale, addi...
Workflow for checking memory before code exploration. Auto-loaded when answering questions about code, architecture, or...
Analyzes volatile memory dumps to detect malware, rootkits, and security breaches in digital forensics.
Master memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatil...
Beginner-friendly reverse-engineering workflow for Memory Forensics. Use it to collect evidence, choose static or dynami...
Triages supplied Windows, Linux, or other volatile-memory images while preserving acquisition provenance, image integrit...
Continuous learning system that forges knowledge from work sessions into permanent memory. Use when: (1) after completin...
Delete, redact, or archive project and global memories when the user says forget this, delete memory, remove that prefer...
Memory management and FreeRTOS context for the Megahub ESP32 project. Use when dealing with heap allocation, stack size,...
Prune and merge learnings.md files, memory-bank, handover notes, and memory indexes so knowledge compounds without bloat...
Memory-First Gate (BLOCKING) and the Chesterton's Fence investigation protocol, split out of the memory router per ADR-0...
Session-end memory garbage collector. Promotes valuable L2 session facts to L1 atomic memory, wipes L2, and rotates over...
Generate CLAUDE.md project memory files by exploring codebases. Use when user asks to "generate memory", "create CLAUDE....
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entri...
Creates or updates a compact handoff or checkpoint for a later session, and resumes work from a user-named or repository...
Write concise next-agent handoff summaries across sessions, tools, and coding agents. Load when the user says handoff, n...
Use at the end of any session that discovered durable knowledge (architecture decisions, root causes, setup gotchas, wor...
Complete reference for Claude Code's memory management system including all file types, locations, import syntax, and be...
Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consol...
Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high...
Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against...
Use when the memory store needs a health check: removing duplicates safely, resolving contradictory entries, decaying st...
Inherit memories from another workspace. Reads .claude/memory/ from a source path and imports its memories into the curr...
Initializes project memory by scanning the current project structure, asking targeted questions, and writing structured...
Manages Bob's persistent memory across sessions. Use when learning something new, having a meaningful conversation, refl...
Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task compl...
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 archiv...
Persistent context/memory management MCP server. Stores and retrieves context across AI sessions.
Persistent cross-session memory using the Knowledge Graph MCP server already configured in .mcp.json. Use to save decisi...
Automatically recall and save project memory using the Knowledge Graph MCP server at session start and end. Use by defau...
Persistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.m...
Memory leak detection and analysis for Node.js, Python, and browsers
Detect, isolate, and fix memory leaks in long-running React Single Page Applications.
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks...
Diagnose a service whose memory keeps growing or only goes up, with a fixed checklist: confirm it is a real leak and not...
Detect memory leaks in desktop applications through heap analysis and object tracking
Analyze heap and GC behavior.
Detect and fix memory leaks in Python and PyTorch code, especially matplotlib figures and unreleased tensors. This skill...
Identify and diagnose memory leaks in web applications using heap snapshots, allocation timelines, and automated leak de...
Create semantic links between related memories and entities; use when asked to connect projects, goals, or artifacts acr...
Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency...
This skill should be used by all maigo agents at startup, before beginning work, to load relevant cross-project memory e...
Cross-session memory with SQLite+FTS5 backend. Triggers on errors, pattern discoveries, corrections, task completions.
Use when an agent needs to update, delete, supersede or audit an existing memory entry, or manage its edges, comments an...
Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory...
Use when the user asks to "remember project context"; manages the SEO/GEO memory lifecycle — hot-cache, active work, arc...
Use when the user asks to "remember project context"; manages SEO/GEO memory, hot-cache, active work, archive tiers, and...
Memory persistence operations using claude-mem
Two-tier memory that makes the agent a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal...
Use when saving or retrieving important patterns, decisions, and learnings across sessions. Triggers on keywords like "r...
Manage AI conversation memory, context window optimization, long-term memory strategies, and memory-efficient conversati...
> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. Th...
两级记忆系统,让 aily 成为真正的工作协作者。解码速记、缩写、昵称和内部用语,让 aily 像同事一样理解请求。aily.md 用于工作记忆,memory/ 目录用于完整知识库。
Guide for managing Claude Code memory effectively. Use when setting up project memory, optimizing CLAUDE.md files, confi...
Resolves project shorthand, acronyms, nicknames, and internal names using durable memory and docs. Use when the goal con...
AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and s...
This skill should be used when the user asks to "remember project context", "save SEO data", "track campaign progress",...
Persist and retrieve architectural context, user preferences, and project milestones across sessions. Use for crash-safe...
Framework-agnostic project memory infrastructure for engineering tasks. Use for sparse recall, stale-memory handling, se...
Recall, checkpoint, and audit durable Laravel project knowledge across sessions when prior context materially affects th...