//
XXD Panel 100 — naïve folk-inspired narrative illustration Soldier Skill
AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage reservations, cancellations, and payments via the TourMind API.
Evidence-aware flavor state modeling, molecule matching, and interaction network skill for Codex.
教 AI 写 NovelAI Diffusion V5 提示词的方法 skill：构思＋写法两件套，基于 2226 张实测图库 / 962 条真实提示词。Agent Skills 标准封装。
GPT-6 Astra 提示词写作 Skill：基于官方指南生成、优化、压缩与诊断提示词，支持 Codex、Agent 和 Responses API。
A Claude Code skill that turns one topic prompt into a finished Vox-style explainer video. Script, keyframes, animation, voiceover, music, and local assembly — end to end.
Agent Skill for evidence-based Wi-Fi diagnosis and safe, reversible optimization.
Material-reference-driven photorealistic character casting skill for Codex
Agent Skill that makes Claude a pixel artist — no Aseprite, no MCP, no diffusion. Every pixel is a decision.
The first Agent Skill a beginner installs. Bootstraps Claude Code, Cursor, and other agents, then routes every task to the current best skill for that job.
Objective-C iOS maintenance skill for legacy UIKit apps. Helps review, refactor, debug, and write safer OC code with guidance on ARC ownership, retain cycles, KVO/KVC, Swift interop, performance, scrolling, rendering, crash prevention, networking, and beginner-safe UIKit architecture.
Kanvis Video: open-source Codex Skills and a local Kanvis Studio workspace for turning long-form content into editable video projects.
Build motion-first, high-touch creative websites on vanilla Three.js / Canvas 2D / WebGL / CSS. A Claude Agent Skill with real physics and automated verification.
An AI filmmaking skill by Leos, bringing together six directing roles for scene planning, performance, staging, cinematography, video prompts, and continuity review. 面向 AI 影视创作的六部门导演组，协同完成场次设计、表演调度、摄影方案、视频提示词与连续性审查。
一个面向教材 PDF 的双 MCP 审计工作流：用 PaddleOCR-VL 作为结构主干，用强制 OCR 的 MinerU 做独立交叉核验，再以原始 PDF 的渲染页面作为视觉事实来源，生成可追溯的修订版和净版 Markdown。
通用网页端 JS 逆向工程技能：统一通过 ruyipage + RuyiTrace 采集运行时日志，基于日志证据逆向还原加密参数。融合黑盒补环境（JS 层 NativeProtect）与纯算还原双路径，支持 Node.js / Python 双语言纯协议交付。已在抖音 / 小红书 / 快手 / 同花顺 / 猿人学 / 易盾等真实案例场景中得到实践。（如果最新版效果差可以使用release2.2重构前的版本）
macOS & Windows Codex Desktop 梦幻换肤 Skill｜由世事宜AI免费提供
AI数学建模skill可视化绘图：ModelViz 是一个面向数学建模竞赛与科研写作场景的可视化 Skill。项目内置上百个覆盖多种建模场景的高质量科研绘图模板，将不同功能的图表按统一类别和编号管理，并确保模板源码可独立运行、稳定输出图片。后续系统将通过结构化模板信息、数据特征分析与检索规则，根据用户上传的数据和自然语言需求，推荐适合的图表类型、字段映射与配色方案，再调用对应模板生成可复现的 PNG、SVG 或 PDF 图像。项目重点解决通用大模型直接生成绘图代码时风格不统一、运行不稳定、参数难复用等问题，强调模板驱动、配置清晰、结果可复现和科研表达规范。