memory-checkpoint
Save comprehensive memory checkpoint before context loss or summarization. Triggers: checkpoint, save memory, 檢查點, 存檔, 記憶檢查點, save state, 保存狀態.
using-core
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
lindy-expert
Lindy is an AI agent creation and management platform focused on business process automation. It enables organizations to build sophisticated AI-powered assistants that can handle communication across...
hello-world
A simple example skill that demonstrates Claude Code skill structure
personalization-engine
Central hub for managing user preferences, learning patterns, and adapting skill behavior based on historical feedback. Enables "tell me once" paradigm where the system remembers and adapts.
llm-inference
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
cva-patterns-context
Context management patterns for multi-source AI agents in Clojure+Vertex AI. Covers 4 context types (static/query/API/previous-result), lifecycle management (load/cache/invalidate), TTL strategies, and LGPD-compliant sensitive data handling. Includes production metrics (58% cost reduction via caching). Use when designing agent contexts, implementing multi-source data integration, optimizing cache strategies, or building LGPD-compliant systems.
claude-skill-creator
Create and structure Claude Code skills with proper SKILL.md format, frontmatter, and progressive disclosure. WHEN: MUST use when creating new skills. Invoke with "/claude-skill-creator" or "create a skill", "new Claude skill", "write skill content". WHEN NOT: Creating agents (use claude-agent-creator), creating commands (use claude-command-development).
sqlite-agent-context
Detect agent capabilities and manage context intelligently
unsloth-vision
Fine-tuning multimodal vision-language models (Llama 3.2 Vision, Qwen2.5 VL) using optimized vision layers (triggers: vision models, multimodal, Llama 3.2 Vision, Qwen2.5 VL, UnslothVisionDataCollator, finetune_vision_layers).
langchain-architecture
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
memory-manager
External persistent memory for cross-session knowledge. Use when storing error patterns, retrieving learned solutions, managing causal memory chains, or persisting project knowledge.
load-conversation
Load the full content of a previous Claude Code conversation into current context. Use when user asks to "load conversation <uuid>" or "show me conversation <uuid>" or references loading/viewing a past conversation by its ID.
carlin-audit
George Carlin BS Detector. Auto-activates on: "BS", "bullshit", "jargon", "marketing speak", "what does this mean", "sounds fake", "corporate speak", "buzzwords", "overpromising", "skeptical about"
conversation-search
Search indexed conversation history to find past conversations, locate when topics were discussed, or identify which project conversations occurred in. Use when user asks questions like "when did we discuss X?", "find conversations about Y", "in which project did we talk about Z?", or "show me conversations mentioning W". Works across all projects or within current project.
phase2-5-autonomous
Phase 2-5 autonomous execution guidance - Activate when Claude needs to decide technical choices during implementation/testing/review/release phases
mcp-builder
Comprehensive guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Covers both Python (FastMCP) and Node/TypeScript (MCP SDK) implementations.
authoring-prompts
Invoke this skill first when authoring any AI agent instructions. Foundational principles for writing LLM instructions (skills, CLAUDE.md, rules, commands). Covers token economics, imperative language, formatting for LLM parsing, emphasis modifiers, terminology consistency, and common anti-patterns.
