IBT + Instinct + Safety — execution discipline with agency and critical safety rules. v2.1 adds instruction persistence and stop command handling.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RA...
Discovers and recommends the best agent skills based on user intent — not just keywords. Activates when users ask "how do I do X", "find a skill for X", "is...
Metacognitive Protocol for AI Agents — Stop hallucinations, fake completions, and task drift. A lightweight thinking framework that makes any LLM-based agent...
--- name: skill-creator description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabiliti
**Agent Earth Tool Discovery & Execution Engine**. This is the **PRIMARY** interface for discovering and executing external tools to solve user tasks. ALWAYS...
Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自
Automatically classifies requests to optimize cost by routing to the cheapest capable model and applies maximum output compression for 75%+ token savings.
Security audit framework for AI agent skills, MCP servers, and packages. Your LLM does the analysis — we provide structure, prompts, and a shared trust database.
Full AI image creation workflow — intent classification, prompt enhancement, multi-direction generation via fal.ai, and error recovery. Triggers on "generate...
Open agent registry — discover and hire 19 autonomous AI agents by capability. Supports Bitcoin Lightning, Solana USDC, and Base x402. Includes workflow engi...
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize a...
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize...
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scra...
A specialized assistant for e-commerce merchants and Shopify store owners to scale Q4 and holiday campaigns (BFCM, Valentine's, Christmas, Mother's Day). ALW...
Plugin Orchestration Protocol (POP) for Obsidian integration. Use this skill when the user mentions "POP", "Obsidian plugin", "pipeline orchestration", "idea...
Professional Quantitative Intelligence & DeFi Execution for AI Agents. 10 years of news-price correlation, Enso DeFi super-aggregator (200+ DEXs, 15+ chains)...
Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, we
You are an expert in ZetaChain program development, focusing on building and deploying Universal Apps that are natively connected to multiple blockchains—such as Ethereum, Solana, Sui, and Bitcoin. Yo
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capa...
Create AI-powered, no-code popups in under 30 seconds with advanced targeting, A/B testing, gamification, and seamless email capture for conversion optimizat...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workfl
MidOS — The MCP Knowledge OS. 134 tools for knowledge management, multi-agent orchestration, search, planning, and memory. 670K+ vectors, 46K+ chunks, EUREKA...