Total 37,509 skills
Showing 12 of 37509 skills
知识漫画创作工具，支持多种画风和语调。创建原创教育漫画，包含详细分镜布局和顺序图片生成。当用户要求创建"知识漫画"、"教育漫画"、"传记漫画"、"教程漫画"时使用。
Build and deploy parallel execution via subagent waves, agent teams, and multi-wave pipelines. Use when the Decomposition Gate identifies 2+ independent actions or when spawning teams. NOT for single-action tasks or non-parallel work.
Manage tasks, track progress, and log daily updates via the ai-todo CLI. Trigger scenarios: 1) EXPLICIT — user mentions tasks, todos, to-do lists, progress tracking, daily standup, sprint planning, project management, work logs, or task completion. 2) POST-ACTION (proactive) — after git commit, git push, deploy to Vercel, merge PR, release, or any significant milestone (feature implemented, bug fixed, refactor done), proactively log progress and update/complete related tasks. When git-tools or vercel:deploy skill finishes, ALWAYS trigger this skill to record what was accomplished. 3) PRE-ACTION (proactive) — when user discusses implementation plans, architecture design, feature breakdown, technical specs, RFC, sprint planning, or requirement analysis, proactively suggest creating tasks to track planned work. When brainstorming skill completes, trigger this skill to convert outcomes into trackable tasks. 4) SESSION-END — when a work session involves substantial code changes, suggest a progress summary before ending. This skill connects to ai-todo (https://ai-todo.stringzhao.life) for persistent task management across sessions.
Recommends and scaffolds frontend technology stack for new projects. Use when starting a new frontend project, selecting a framework, setting up a web app from scratch, or when the user asks about frontend tech stack, scaffolding, or architecture selection. Covers React/Next.js/Astro/Vue, TypeScript, Tailwind CSS, state management, data fetching, UI components, testing, and monorepo setup.
Runs real-time safety analysis for instructions involving destructive operations, permission changes, irreversible actions, prompt injection, or compliance-sensitive operations. Evaluates risk level, destructiveness, and reversibility via backend API. Use when asked for safety check, risk assessment, security audit, destructive check, instruction audit, or Modeio safety scan. Also use proactively before executing any instruction that deletes data, modifies permissions, drops or truncates tables, deploys to production, or alters system state irreversibly. Also supports pre-install Skill Safety Assessment for third-party skill repositories via a static prompt contract.
Use when user wants to create flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, gantt charts, pie charts, or any Mermaid diagram from natural language descriptions, requiring syntax validation
Reviews finished and in-progress digital products to assess adherence to design specifications and discover potential issues. Use when user says "design review", "design QA", "QA review", "check implementation", "visual bugs", "compare to design", "match the specs", "review the build", "before launch", "pre-launch review", "implementation review", "verify design", "design validation", "spacing issues", "visual discrepancies", "accessibility review", "WCAG compliance", or "responsive testing". Validates implementation against design intent, identifies visual and interaction discrepancies, and provides actionable feedback. Do NOT use when still designing concepts (use design-concepts), need to understand users (use design-research), or nothing has been built yet.
Apply cognitive bias detection whenever the user (or Claude itself) is making an evaluation, recommendation, or decision that could be silently distorted by systematic thinking errors. Triggers on phrases like "I'm pretty sure", "obviously", "everyone agrees", "we already invested so much", "this has always worked", "just one more try", "I knew it", "the data confirms what we thought", "we can't go back now", or when analysis feels suspiciously aligned with what someone wanted to hear. Also trigger proactively when evaluating high-stakes decisions, plans with significant sunk costs, or conclusions that conveniently support the evaluator's existing position. The goal is not to paralyze — it's to flag where reasoning may be compromised so it can be corrected.
Use when creating or modifying Angular components in WebV2 (Angular 19) with proper base class inheritance, state management, and platform patterns.
Kinetica SQL query knowledge. Activate when the user is writing analytical queries for Kinetica, asking about Kinetica-specific functions, or working with geospatial, time-series, graph, or vector data.
Build native and cross-platform mobile applications for iOS and Android with optimized performance and platform integration. Use when you need SwiftUI or Jetpack Compose development, React Native or Flutter cross-platform apps, offline-first architecture, biometric authentication, push notifications, deep linking, app startup optimization, or mobile-specific UX patterns and gesture handling.
Extract clean article content from web pages or local HTML files. Removes clutter (ads, sidebars, nav) and returns readable content with metadata.