Skills your agents can run

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) a command or operation fails unexpectedly, (2) a user corrects Claude (e.g., “No, that’s wrong…”, “Actually…”), (3) a user requests a capability that doesn't exist, (4) an external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) a better approach is discovered for a recurring task. Also review learnings before major tasks.

Compress and simplify prompts to preserve meaning while reducing context usage

Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Run a local Agent Memory Service for persistent self-improvement with proper Ed25519 cryptography. Fixed signature implementation for reliable memory storage and retrieval.

Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.

Automated context health management for OpenClaw. Monitors token usage, snapshots memory, and resets sessions to maintain performance. Authored by Sophie.

Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with a plugin system and hooks for event-driven workflows. Prevents 14 documented failure modes. Use when: building coding agents, SRE systems, security auditors, or troubleshooting issues such as CLI-not-found errors, structured-output validation failures, session forking errors, MCP configuration problems, or subagent cleanup.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Comprehensive security review framework for AI agents. Covers Skill/MCP installation, GitHub repositories, URLs/documents, on-chain addresses, products/services, and social shares. Built from real-world attack patterns and incident response experience.

Practical guide to reduce token consumption, lower AI costs, and improve Claude Code performance through file organization, context management, and strategic model selection. Backed by real experiment data. Use when user mentions "optimize tokens", "reduce costs", "Claude is slow", "too many tokens", "token budget", "context window full", "organize codebase for AI", or "reduce token consumption". Do NOT use for general coding questions, debugging, or performance optimization unrelated to AI token usage.

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: "remember this", "save this", "note this", "what did we discuss about...", "check your notes", "clean up memories". Also use proactively when discovering valuable findings worth preserving.

Design and optimize an AI agent's action space, tool definitions, and observation formats to improve completion rates.

Long-term memory via ChromaDB with local Ollama embeddings. Auto-recall injects relevant context every turn. No cloud APIs required — fully self-hosted.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Universal memory architecture for AI agents. Provides long-term memory, daily logs, diary, cron inbox, heartbeat state tracking, social platform post tracking, sub-agent context patterns, and adaptive learning — everything an agent needs for identity continuity across sessions.

임의의 자동 컴팩션 대신 논리적 간격에서 수동 컨텍스트 압축을 제안하여 작업 단계를 통해 컨텍스트를 보존합니다.

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size