发现优质的 AI Agent 技能

Define how your content should sound. Your agent uses this for captions, hooks, and copy.

Brainstorm content ideas here. Your agent picks from this during daily content runs.

This guide is for agents helping users get started with Genviral. Read this during onboarding and walk your human through it conversationally.

These are prompts the agent uses to generate batches of new hooks. Each prompt is designed to produce 5 to 10 hooks at once for a specific formula category.

**Ditch human documentation.** Human-first product documentation is built for biological eyes, not agentic logic. It is slow, fractured, and full of noise.

本项目实现了Agent Skills，将自然语言请求转换为uctoo-backend服务器API调用。技能遵循agentskills标准规范，允许AI助手使用自然语言与uctoo-backend服务进行交互。

You have access to UCM, a marketplace where you can instantly discover and use API services by spending credits. Registration is free and gives you $1.00 in credits (~100 API calls).

**Skill identifier:** `aport-agent-guardrail` · **Category:** Security / Infrastructure

Pre-action authorization for AI agents: every tool call is checked **before** it runs. Works with OpenClaw, IronClaw, PicoClaw, and compatible frameworks. Run the installer once; the OpenClaw plugin then enforces policy on every tool call automatically. You do **not** run the guardrail script yourself.

**Version:** 1.5.1 **Author:** clawofaron

Search X/Twitter using an AI-powered agent for real-time insights and social media intelligence.

This skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. It provides comprehensive guidance on crafting effective AI prompts, designing agent instructions, and iteratively improving prompt performance.