Discover Data & AI skills, compare source repositories and read the instructions for each workflow.
Guidelines for contributing commands in VS Code extensions. Indicates naming convention, visibility, localization and other relevant attributes, following VS Code extension development guidelines, libraries and...
A tiered approach to answering research questions with clear stop rules, evidence capture, and escalation to Tavily/Playwright only when needed.
Patterns for finding and exporting mail via Microsoft Graph (delegated auth), with safe defaults and paging/retry guidance.
Navigate web-based trainings that gate progress via timers/videos/disabled Next buttons.
General-purpose patterns for reliable browser automation (selectors, waiting, scrolling, overlays, HITL).
Autonomous agent for systematically upgrading applications with polished anime.js animations. Use when asked to add animations, improve UI polish, upgrade visual experience, or make an app feel more alive. Trig...
A guide for coding with UdonSharp. Use this when you are asked to create or edit UdonSharp programs. Code that inherits from UdonSharpBehavior falls under UdonSharp code.
This skill should be used when the user asks to "add a component", "change architecture", "refactor X", "implement feature", "fix bug", "create new service", "update diagram", or "remove component". Requires .c...
Creates C3 architecture documentation from scratch using staged Socratic discovery. Use when the user asks to "adopt C3", "onboard me to architecture", "scaffold C3 docs", "init C3", "set up architecture docs",...
This skill should be used when the user asks to "adopt C3", "onboard me to architecture", "scaffold C3 docs", "init C3", "audit architecture", "validate C3", or "check C3 docs". Also triggers when no .c3/ direc...
This skill should be used when the user asks "where is X", "how does X work", "explain X", "show me the architecture", "find component", "what handles X", or references C3 IDs (c3-0, c3-1, adr-*). Requires .c3/...
Create clear, informative, and well-structured Git commit messages following best practices and conventional commit standards.
Push local commits to remote, check for uncommitted changes, and create a PR with structured summary, changes list, and test plan.
Watch CI checks, auto-fix failures, and squash-merge the PR when all checks pass.
Identifies redundant or duplicate test cases, removes them while ensuring test coverage is not reduced.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user me...
Review UI code for Web Interface Guidelines compliance using Vercel Engineering standards.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, rou...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Vercel React Best Practices for performance and engineering.
Use this skill when transitioning Architecture Decision Records (ADRs) into production implementations. Provides ADR parsing patterns, task breakdown templates, and health check frameworks for ADR-to-production...
Use this skill when creating production roadmaps from research projects. Provides H1/H2/H3 horizon planning, backcast planning, stakeholder view templates, and milestone design patterns for research-to-producti...
Use this skill when evaluating research projects, POCs, experiments, or prototypes for production readiness. Provides the "What Did We Prove?" framework, production readiness checklist, and gap analysis matrix...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.