Explorar skills

Run 150+ AI applications in the cloud via the inference.sh platform. Triggers on "generate image with FLUX", "create video", "use Veo/Seedance", "run inference.sh", "infsh CLI", "single key for image+video+LLM". One API key covers image generation (FLUX, Reve, Seedream, Grok, Gemini), video (Veo, Wan, Seedance, OmniHuman, HunyuanVideo), LLMs (Claude, Gemini, Kimi, GLM-4), search (Tavily, Exa), 3D

Conclave é um conselho multi-LLM inspirado em Karpathy, que orquestra diversos modelos de IA para um debate anonimizado. Ele oferece três níveis de profundidade: respostas paralelas rápidas, síntese padrão e crítica cruzada anonimizada profunda com síntese de debate.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

审核代码可读性与复杂度，重点识别 AI 编程常见问题：过度设计、过度抽象、命名晦涩、注释失衡、重复类型、冗余代码、防御代码过多、单次使用却过度封装，以及超出项目需求的复杂度。用于"代码审核""简化代码""可读性优化""重构过度设计""删减废弃代码"或 code review；如无特殊说明，默认审查当前工作区未提交改动。

Yolanda Skills 项目的发布工作流。分析变更、生成双语 changelog、更新版本、创建 git tag 和 GitHub Release。当用户说"release"、"发布"、"新版本"、"bump version"、"更新版本"时触发。

This skill should be used when the user asks to "retro", "evaluate zforge", "review plugin performance", "score this session", or wants to assess how well zforge's workflow served a feature. Evaluates zforge's workflow scaffolding, not the project's technical decisions or LLM reasoning quality.

创建或更新项目根目录下的 README.md 文件，按固定模板整理项目名称、简介、核心功能、快速开始、开发指南、规划和参考文档。适用于任意技术架构。Use when the user asks to create, generate, write, refresh, rewrite, or update a project README, including requests such as `创建 readme`、`更新 readme`、`生成 README.md`、`create readme`、`update readme`。

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

基于 opencli（Chrome CDP + 站点适配器）采集 URL 内容，转为干净的 markdown 并下载图片/视频。Use when user asks to "下载"、"获取"、"提取"、"保存" with a specific URL, or provides a link and wants content archived as local files.

Rewrites AI-flavoured copy into a publishable register by stripping the language tells of an LLM draft — buzzwords, throat-clearing, false-inclusive openers, and the \"not just X — Y\" rhetorical tic — and supplies the canonical banned-list that runtime hooks read to flag drafts before they ship.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

将 Obsidian 笔记按专题组织为知识 Entity，通过 wiki link 建立知识图谱。Use when user asks to "整理笔记", "归档到知识库", "知识库整理", "知识库诊断", "专题整理", "ingest", "diagnose", "restructure", or provides a note and wants it organized into the knowledge base.