Agent Skills Hub

english-text-editor

Provides targeted, concise English language editing and stylistic improvements for text without performing full rewrites.

content-writer

Multi-platform content generator for Chinese social media including Xiaohongshu, Zhihu, Official Accounts, and Douyin with native formatting.

voice-apply

Transforms content to match specific voice profiles, tones, or styles using configurable YAML templates for consistent brand and narrative output.

building-ai-agent-on-cloudflare

Build stateful AI agents on Cloudflare Workers using the Agents SDK. Features real-time WebSockets, persistent state management, scheduled background tasks, and native tool integration for production-ready deployments.

crawl

Crawl websites to extract content as clean markdown files. Ideal for documentation, research, and offline knowledge management.

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

nano-image-generator

Generate professional visual assets including app icons, logos, banners, and illustrations using the Nano Banana Pro (Gemini 3 Pro) AI model.

nano-banana-pro

Generate and edit images, diagrams, and infographics using Google's Gemini 3 Pro model. Supports text-to-image, style transformation, and data-accurate visual creation.

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.