Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Guide for building NexAU agents from scratch. This skill should be used when implementing a new NexAU agent — including YAML configuration, system prompt, tool definitions, tool bindings, entry point scripts.
Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action items. Use when requests involve long-term ZiWei, short-term MeiHua, tarot, daily card, philosophy RAG, or mixed multi-domain queries.
Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and progressive disclosure.
Initialize or update setup for pi-side-agents (running asynchronous agents spawned/controlled from main session)
Analyze whether a role-play agent's activity output reads like a real human. Use when the user says "分析对话", "analyze activity", or "检查角色扮演".
Deeply analyze a simulation run's results — agent experiences, inner journey, personality growth, etc. Use when the user says "分析run", "analyze run", or "分析这个运行".
Filing gate for ALL brain writes. Consulted before creating any new brain page to determine the correct path. Reads the ACTIVE schema pack via `inbrain schema show --json` — no hardcoded directory table. Also runs periodic taxonomy drift detection via `inbrain schema review-orphans`.
Use when a user provides a smart contract address and wants to generate a reusable SKILL.md file for interacting with that contract through keypo-wallet. Analyzes verified contracts by fetching their ABI, categorizes functions, and outputs a complete agent skill file with verified addresses, function signatures, calldata encoding instructions, and keypo-wallet execution commands. Also use when a user says "make a skill for this contract", "generate a skill", or "I want to interact with this contract using keypo-wallet". Requires Foundry (cast) to be installed.
Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.