Skill UI

A robust protocol designed for multi-agent collaboration on long-running projects. It simulates a self-optimizing city where diverse AI agents (citizens) interact using decentralized markdown files (The Register, Contracts, Chronicle). This framework enables cross-vendor optimization, dynamic work routing, and constitutional evolution without requiring a centralized server or specific runtime environment.

This guide details how to effectively delegate complex, multi-step tasks to various specialized AI agents (Codex, Pi, Claude, Hermes). It covers best practices for maintaining conversation context, handling TUI prompts (e.g., avoiding newlines, using quotes), techniques for reliable polling, and choosing the optimal agent for coding, design, or general purpose work. Essential for advanced AI workflow automation.

The /goal command converts standard agent prompts into persistent, self-correcting loops (plan → act → test → review → iterate). It is designed for long-running, complex engineering tasks like migrations, coverage lifts, or refactoring, ensuring progress is tracked against a verifiable stop condition and mandated documentation.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.

This comprehensive guide outlines best practices for building reliable and robust AI agent harnesses. It covers optimizing action spaces, defining structured tools, managing observation formats, and implementing essential error recovery contracts. Use these principles to dramatically improve agent completion rates, manage context budgets effectively, and transition AI prototypes into stable, production-grade autonomous systems.

This skill provides a systematic, four-phase workflow for diagnosing and recovering from AI agent failures. It guides the agent to first capture the failure state, diagnose the root cause (e.g., loop, context overflow, state drift), apply minimal containment recovery actions, and finally generate a detailed introspection report, minimizing the need for human intervention.

Adds x402 payment execution for AI agents with task budgets, spending controls, and non-custodial wallets. Supports Base via agentwallet-sdk and X Layer via OKX payment protocols for controlled API and service payments.

This framework guides AI agents to critically assess their own output across five key axes: Accuracy, Completeness, Clarity, Actionability, and Conciseness. It provides a structured, evidence-based scorecard and concrete suggestions for improvement, turning every task completion into a deep learning opportunity.

A comprehensive tool for querying, storing, and managing complex knowledge across multiple agent sessions. AgentDB utilizes advanced techniques including semantic routing, hierarchical recall, causal graph construction, and context synthesis. Use this skill when your application requires robust, multi-faceted knowledge retrieval and reasoning based on structured and unstructured data. It provides a structured workflow for checking system health, starting sessions, storing knowledge in tiers (working, episodic, semantic), and searching learned patterns.

This harness transforms standard code environments into fully persistent, autonomous agent systems. It leverages native features like scheduled tasks (Crons), remote dispatching, and structured memory storage (MCP) to enable continuous, self-directing automation. Ideal for building AI assistants that require long-term context, recurring workflows, and complex, multi-step operations, eliminating the need for external agent frameworks like AutoGPT.

This tool enables complex web interactions using plain natural language commands. Instead of relying on unreliable selectors, it utilizes a powerful page-agent and LLM loop to interpret user intent, performing actions like filling forms, clicking buttons, and extracting data from dynamic websites. Ideal for testing and automation in pages with ambiguous or changing markup.

This tool enables the definition and management of structured cognitive patterns for advanced AI agents. It guides decision-making by codifying complex reasoning strategies, including decision trees, chain of thought (CoT), and analogy mapping. Use it to build robust, self-improving agents that can solve complex problems step-by-step and track their learning status.