Prepare for meetings by gathering attendee context and related topics

Schedule, coordinate, and optimize meetings with agenda creation and follow-up automation

Search through past session context and observations. Use when asking about past work, previous implementations, how something was done before, or recalling decisions. Keywords: remember, recall, last time, before, history, what did we, how did we

meme-trader

Execute AI tasks (codex/claude/gemini) with memory and resume support via memex-cli stdin protocol.

Save and retrieve memories or embeddings via the repo helpers or API. Use when working with embedding config or memory storage.

**"Read First, Write Last."**

memory-coordination

Manage architectural decisions and insights in memory.jsonl. Use when you need to document strategic decisions, lessons learned, fixed problems, or architectural insights. Append-only audit trail for project knowledge.

Best practices for memory architecture design including user vs agent vs session memory patterns, vector vs graph memory tradeoffs, retention strategies, and performance optimization. Use when designing memory systems, architecting AI memory layers, choosing memory types, planning retention strategies, or when user mentions memory architecture, user memory, agent memory, session memory, memory patterns, vector storage, graph memory, or Mem0 architecture.

memory-forge

Persistent memory graph skill using the MCP Memory server

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.

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

This Skill replaces passive staleness warnings ("Your context is 11 hours old") with **proactive maintenance**. Instead of warning you context is stale, it:

Detect, isolate, and fix memory leaks in long-running React Single Page Applications.

Detect and fix memory leaks using heap snapshots, memory profiling, and leak detection tools. Use when investigating memory growth, OOM errors, or optimizing memory usage.

Analyze heap and GC behavior.

Build and maintain a knowledge graph of patterns, decisions, and learnings across sessions.

memory-manager

Spatial organization of knowledge in navigable directories

Process file changes and update CLAUDE.md memory sections. Use when the memory-updater agent needs to analyze dirty files, update AUTO-MANAGED sections, verify content removal, or detect stale commands. Invoked after file edits to keep project memory in sync.

Reflect on recent experiences and consolidate learnings to maintain organized, useful memory.

Memory Safety security skill

**IMPORTANT:** The `scripts/` folder is in the plugin directory, NOT the current project.

Automatic documentation memory system for AI agents. Ensures context is loaded at session start and documentation is updated after changes.

**Purpose:** Lightweight persistence layer for AI-assisted development that tracks WHY decisions are made, not just WHAT changed.

Update and maintain Memory Bank files (activeContext, progress, decisionLog). Triggers: MB, memory, 記憶, 進度, 更新記憶, update memory, 記錄進度, 更新上下文, sync, 同步, 記下來, note, 筆記, context, 脈絡, 追蹤, track, 狀態, status.

Always-on MemoryManager + LearningPolicy workflow. Use when storing/retrieving memories, emitting retrieval signals, running consolidation/pruning, or when a session should default to the Atlas memory system (MemoryManager, MemoryConsolidator, LearningPolicy). Triggers: memory add/retrieve, consolidation, pruning, semantic search, or 'use the memory system by default.'

**Memory edits work for FACTS, not BEHAVIORS.**

Intelligent skill selection system that automatically routes to appropriate skills based on user intent, context, and project requirements. Enforces quality gates and optimizes development workflow.

分析和优化 Next.js 项目的元数据，包括 title、description、Open Graph、Twitter Cards。自动检测 App Router 或 Pages Router，提供长度建议、关键词优化和最佳实践指导。支持中英文双语 SEO 分析。

End-to-end metagenomics workflow from FASTQ to taxonomic and functional profiles. Covers Kraken2 classification, Bracken abundance estimation, and HUMAnN functional profiling. Use when profiling metagenomic samples.

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.

Michael Shapira's D1 swimming pathway tracking for Life OS. Manages swim times, nutrition protocol (kosher keto), recruiting outreach, and rival comparison. Events: 50/100/200 Free, 100 Fly, 100 Back. SwimCloud ID: 3250085. Use when tracking swim performance, analyzing times, managing nutrition, planning recruiting, or comparing against rivals (Soto PI:47, Gordon PI:90, Domboru PI:102).

Use when building micro-interactions between 100-200ms - tooltips appearing, dropdown opens, small feedback animations that feel quick but perceptible

Guide for implementing Grafana Mimir - a horizontally scalable, highly available, multi-tenant TSDB for long-term storage of Prometheus metrics. Use when configuring Mimir on Kubernetes, setting up Azure/S3/GCS storage backends, troubleshooting authentication issues, or optimizing performance.

Build and maintain a personal profile from therapy sessions and journal entries. Creates a living document that accumulates self-knowledge about patterns, strengths, coping strategies, and growth over time. Unlike other skills, insights updates an existing profile rather than creating new files.

>

Mixpost is a self-hosted social media management software that helps you schedule and manage your social media content across multiple platforms including Facebook, Twitter/X, Instagram, LinkedIn, Pinterest, TikTok, YouTube, Mastodon, Google Business Profile, Threads, Bluesky, and more.

ML 모델의 성능 벤치마크 및 평가를 자동화하는 스킬입니다.

ML inference latency optimization, model compression, distillation, caching strategies, and edge deployment patterns. Use when optimizing inference performance, reducing model size, or deploying ML at the edge.

Build and train machine learning models using scikit-learn, PyTorch, and TensorFlow for classification, regression, and clustering tasks

Apply appropriate type hints for ML/PyTorch code. Use when adding type annotations to ML code or addressing mypy errors.

Run LLMs on Apple Silicon with MLX/mlx_lm - unified memory, 4-bit quantization, streaming generation, prompt caching. Optimal for M-series chips.

MLX on Apple Silicon with JAX-style SplitMix64 PRNG. Deterministic color generation with GPU acceleration.

Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management, MCP optimization, strategic chunking, and quality-over-quantity principles for 200K token context windows.

AI-powered enterprise Claude Code hooks orchestrator with intelligent automation, predictive maintenance, ML-based optimization, and Context7-enhanced workflow patterns. Use when designing smart hook systems, implementing AI-driven automation, optimizing hook performance with machine learning, or building enterprise-grade workflow orchestration with automated compliance and monitoring.

This skill enables you to create "save points" (commits) for your memory and state files. Use it to prevent data loss, undo hallucinations, and manage long-term context safely.

Avoid common Kubernetes mistakes — resource limits, probe configuration, selector mismatches, and RBAC pitfalls.