Explorar skills

一键建立项目文档系统。初始化 Rule1, Memory 以及基于 Diátaxis 的目录结构。

科学调试专家 - 观察(Observe) -> 假设(Hypothesize) -> 实验(Experiment) -> 修复(Fix)

Use quando o usuário quiser projetar, pré-visualizar ou personalizar um tema de vault do Obsidian, incluindo a escolha de estilos, comparação de esquemas de cores, ajuste de tipografia ou geração de snippets CSS. Ativa com palavras-chave como "tema Obsidian", "esquema de cores", "snippet CSS", "aparência".

口播稿一键生成幻灯片图片，通过 NotebookLM 生成中文幻灯片，PDF 转图片输出供剪映使用。Use when 用户说"生成PPT""生成幻灯片""做PPT图片""幻灯片""PPT"或提到口播稿背景图/视觉素材。

全栈开发规范百科全书 (React/TS/Node/Supabase). Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend/backend code.

Prioritize vulnerability remediation using KEV-style exploitation context plus asset criticality. Use for CVE triage, patch order decisions, and remediation reporting.

Meta-workflow for creating your own Claude Code skill that actually activates when needed and delivers genuine value. Starts with skill-creator as the canonical starting point, adds elicitation frameworks when the skill is for a human/domain area (interviewing, research, therapy-adjacent), designs the examples that will illustrate the skill (example-design), aligns with repo conventions (consisten

Generate a complete CRUD REST API with validation, error handling, auth middleware, tests, and OpenAPI docs. Use when asked to create API endpoints, REST resources, or backend CRUD operations.

深度联网审查技术文档和部署方案，联网验证事实准确性、参数正确性、版本兼容性。Use when 用户说"深度审查""老韩审查""联网审查""技术文档审查"或要求对技术方案/部署脚本/配置文件进行事实核查。不适合纯文字审查或非技术文档。

Architects new features through the full lifecycle. Use when designing, planning, implementing, or extending features. Triggers on 'new feature', 'design', 'plan', 'implement', 'architect', 'prd', 'spec'.

Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4) Compare model performance across experiments, (5) Integrate evaluations with Pydantic

Creates a safe, step-by-step plan to refactor messy code without breaking existing behavior.