Total 41,914 skills
Showing 12 of 41914 skills
Implement and maintain GitHub project documentation using a layered system. Use when creating, updating, or auditing documentation.
Browser automation for AI agents. Use when the user needs to interact with websites, navigate pages, fill forms, click buttons, take screenshots, extract data, test web apps, or automate any browser task. Triggers include "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data", "test this web app", "login to a site", or any task requiring programmatic web interaction.
Creates detailed Product Requirements Documents in Markdown format. Use when writing PRDs, defining feature requirements, or creating specification documents for development teams.
Generate images using Google's Gemini API. Use when creating images from text prompts, editing existing images, or combining reference images for AI-generated visual content.
Control the cmux terminal multiplexer. Use this skill when the user asks to manage terminal panes, workspaces, windows, browser splits, or interact with cmux in any way. Also use when you need to read other terminal screens, send commands to other panes, create splits, or manage the terminal layout.
Code review specialist focused on patterns, bugs, security, and performance
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.