Skills 导航

Strategy to get recommended by ChatGPT, Claude, Perplexity, and Gemini. Use when someone wants help with LLM SEO, AI search optimization, AEO, or GEO.

Build and evaluate LLM prompts. Use when crafting system prompts, comparing variants, estimating tokens, or managing prompt templates.

A 4-step thinking framework to boost LLM output quality. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM responses. No LLM endpoint needed - LLM follows the framework itself. Triggered by "detailed analysis", "in-depth analysis", "use booster", or /booster command.

Applies fixes from a prior review-llm-artifacts run, with safe/risky classification

LLM-as-judge methodology for comparing code implementations across repositories. Scores implementations on functionality, security, test quality, overengineering, and dead code using weighted rubrics. Used by /beagle:llm-judge command.

>

快速查找 Claude、GPT、Gemini 等 AI/LLM 模型、厂商和应用图标，直接返回 lobe-icons 的 SVG/PNG/WEBP 链接及明暗/彩色版本，适合下载 Logo 或嵌入页面。

✎ 为 AI/LLM 产品快速找到并获取官方风格图标，支持 SVG、PNG、WEBP 多格式下载，做界面、文档和品牌素材时特别省心