Engineering skills

Create algorithmic art with p5.js using randomness and interactive parameters.

Build production-grade web components and interfaces with distinctive, polished design.

Apply professional color and font themes to slides, docs, and web pages.

Build complex React artifacts with Tailwind CSS and shadcn/ui components.

Test local web apps with Playwright, verify UI behavior, and capture screenshots.

Create, edit, and format Word documents with tables, images, and tracked changes.

Create original posters and visual art in PNG and PDF formats.

Build, debug, and optimize Claude API applications with caching and model migration support.

Build protocol servers that connect language models to external APIs and services.

Open, edit, and create Excel and CSV files with formulas, formatting, and data cleaning.

Guide structured workflows for writing docs, proposals, and technical specs collaboratively.

Create, edit, and optimize Claude skills with performance testing and benchmarking.

Analyze your codebase to create a trimmed ECC install plan with only the skills you actually need.

Learn REST API best practices for resource naming, versioning, pagination, and error handling.

Debug AI agent failures by diagnosing loops, token waste, and task drift systematically.

Jesse Vincent's full Claude Code methodology — TDD, brainstorming, git worktrees, all auto-triggering.

Delegate coding tasks to multiple AI models and get the best result.

Configure cross-session user memory and multi-profile isolation for AI agents.

Delegate coding tasks to OpenHands, a model-agnostic agent via terminal.

Query wallet balances, token info, gas prices, and transactions across 8 blockchain networks.

Create animated GIFs optimized for Slack messages and custom emojis.

Build multi-component React artifacts with Tailwind CSS and shadcn/ui components.

Test local web apps with Playwright to verify frontend functionality and capture screenshots.

Create, edit, and optimize skills with performance testing and benchmarking.

Build and optimize Claude API applications with prompt caching and model migration.

Build Model Context Protocol servers to connect AI with external APIs and services.

Garry Tan's 23-role Claude Code stack — CEO, designer, eng, QA, security, release, all as slash commands.

Automate web browsing tasks like filling forms, taking screenshots, and extracting data.

Create design tokens, component specs, and branded presentations from a systematic token architecture.

Add persistent memory to Claude agents across sessions via context injection.

Monitor a pull request until it's ready to merge, tracking comments and CI checks.

Execute multi-phase plans by coordinating specialized subagents.

Analyze git diffs and pull requests to understand changes, affected components, and risks.

Visualize your codebase's knowledge graph in an interactive web dashboard.

Ask questions about your codebase using an AI-powered knowledge graph.

Analyze open GitHub issues and PRs, generating evidence-backed reports without modifying anything.

Compare your code to the latest npm version and list what's changed.

Discover a hidden easter egg about the Oh My OpenCode development plugin.

Turn code folders into interactive knowledge graphs with community detection and query tools.

Create intelligent multi-step plans to achieve complex objectives using adaptive reasoning.

Automate website interactions like filling forms, clicking buttons, and extracting data.

Reference CSS classes and HTML patterns for presentation components.

Test and debug web apps in real browsers using Chrome DevTools inspection.

Design stable, well-documented APIs and module boundaries that are hard to misuse.

Set up and configure automated build and deployment pipelines with quality gates.

Review code across correctness, readability, architecture, security, and performance.

Create GitHub issues for your repository following its template format.

Verify actual demand exists before reviewing code that adds new surface area.

Test Cherry Studio pull requests with automated UI testing and code review.

Analyze, index, and generate wikis for your codebase via command line.

Trace bugs and errors by mapping code execution flows and finding root causes.

Review pull requests for production readiness using a coordinated multi-reviewer approach.

Diagnose your AI project and create an optimal technical roadmap in Spanish.

Design, write, and deploy new skills to your repository following Diamond Standard.

Audit code and infrastructure for security vulnerabilities and threats.

Writes reliable Playwright and Cypress E2E tests and fixes flaky ones.

Patterns for generics, conditional types, mapped types, and type-safe TypeScript utilities.

Picks the right React state tool and gives typed store and query patterns to copy.

Reference patterns for Next.js 14+ App Router, Server Components, and streaming.

Writes and validates OpenAPI 3.1 specs from code or design-first contracts.

Separates read and write models with CQRS patterns for scalable, event-sourced systems.

Reference for service boundaries, inter-service communication, and resilience patterns.

Scaffolds production FastAPI projects with async patterns, DI, and pytest setup.

Wires Vault, AWS/Azure/GCP secret stores, and rotation into CI/CD pipelines.

Sets up Prometheus scraping, recording rules, and alerting with proven conventions.

Sets up GitOps delivery for Kubernetes with ArgoCD or Flux and auto-sync.

Ready-to-use GitHub Actions workflows for testing, building, and deploying with sane defaults.

Generates production Kubernetes manifests with resource limits, health checks, and security contexts.

Builds reusable Terraform modules for AWS, Azure, GCP, and OCI with tested IaC patterns.

Split complex tasks across multiple focused agents while keeping strategic control in the parent.

Build Feishu and Lark bot automations, documents, sheets, and approval workflows securely.

Design, build, and debug Model Context Protocol servers with stdio and HTTP/SSE transports.

Manage LLM provider credentials and integrations in Arize for evaluators.

Create annotation schemas and manage human review workflows in Arize.

Generate customized instruction files for AI coding agents like Copilot and Claude.

Audit your repository's AI-readiness and generate an interactive HTML dashboard.

Analyze your codebase and recommend Claude Code automations to optimize your workflow.

A sample skill demonstrating slash command format and frontmatter options.

Create a reference template for building Claude Code plugin skills.

Configure your Discord bot token and review channel access policies.

Audit and improve CLAUDE.md files to optimize Claude's project context.

Develop and deploy MicroPython apps to your Cardputer device without re-flashing.

Flash and set up M5Stack ESP32 devices with UIFlow 2.0 firmware and MicroPython apps.

Manage Discord channel access, approve pairings, and control allowlist policies.

Determine correct file placement and structure for your project.

Automatically fix GitHub bug issues and submit pull requests.

Auto-fix high-frequency Sentry errors by analyzing stack traces and submitting pull requests.

Reduce Vercel costs and improve performance using verified metrics and framework-specific recommendations.

Generate and iterate high-performing ad copy, headlines, and variations for any platform.

Analyze competitor URLs to generate detailed profiles with market data and insights.

Generate and optimize images for blogs, social media, product mockups, and brand assets.

Design and plan A/B tests to measure which version performs better.

Set up and audit analytics tracking for events, conversions, and marketing measurement.

Plan what content to create and organize topics for your editorial roadmap.

Create automated email campaigns to nurture leads and guide customers through their journey.

Improve form completion rates by reducing friction and optimizing fields.

Optimize your content to be cited and surfaced by AI search engines.

Analyze your app listing against best practices and get a prioritized optimization plan.

Review and polish marketing copy to strengthen messaging and improve readability.

Plan and build free marketing tools to generate leads and attract organic traffic.

Build flexible, maintainable React components using composition techniques.

Optimize React and Next.js code following Vercel's performance best practices.

Build performant React Native apps with optimization and animation guidance.

Animate page and component transitions using React's native View Transition API.

Deploy your app to Vercel with preview or production environments.

Deploy and manage Vercel projects using token-based authentication instead of interactive login.

Review UI code for compliance with web interface best practices and accessibility standards.

Create and edit embedded skills in Crush's binary system.

Create and manage custom shell commands for Crush's embedded shell environment.

Configure Crush settings, providers, servers, and permissions via JSON.

Add and debug hooks to gate, approve, or modify tool calls in Crush.

Keep task plans and progress in markdown files that survive context loss.

Index and reference guide for Agent Memory's MCP tools and parameters.

Create animation-rich HTML presentations from scratch or convert PowerPoint files.

Open websites and interact with pages to extract data and automate tasks.

Customize and manage keyboard shortcut bindings for cmux.

Customize cmux actions, shortcuts, layouts, and terminal preferences.

Run health checks and debug reports for cmux hooks, sessions, and automation issues.

Compress images to WebP or PNG format with automatic tool selection.

Built by Vercel Labs. Claude searches the open skill ecosystem for you — surfaces real, popular skills instead of reinventing them.

Take a quick quiz to find your starting point in an AI engineering curriculum.

Test your understanding of AI Engineering from Scratch course phases.

Build knowledge graphs from documents and search them with natural language queries.

Coordinate GitHub workflows and marketing tasks using parallel subagents for issues, PRs, and releases.

Run live QA and end-to-end tests for provider validation and app configuration.

Check provider usage, limits, credits, and configuration health in JSON format.

Manage macOS app releases with versioning, notarization, and Homebrew updates.

Convert documentation, repos, PDFs, and videos into AI-ready skills automatically.

Search Slack chat history to find solutions, code snippets, and team decisions.

Build and optimize React and Next.js applications with performance analysis and accessibility.

Build immersive scroll-driven websites with parallax effects, text animations, and interactive depth.

Scan code for accessibility violations and generate WCAG 2.2 compliance reports.

Analyze customer accounts to predict churn risk and identify expansion opportunities.

Analyze sales pipeline health, forecast accuracy, and go-to-market efficiency for SaaS teams.

Analyze RFP requirements, build competitor comparisons, and plan proof-of-concept engagements.

Prepare tough answers and narratives for adversarial board questions.

Identify hidden weaknesses in your plan before they cause failure.

Challenge your business decisions and plans with adversarial questions before they fail.

Navigate difficult choices with no clear right answer using structured analysis.

Challenge your business assumptions by stress-testing revenue, market size, and competitive risks.

Get strategic advice from virtual CEO, CTO, CFO, and other executives for your business.

Get executive guidance on strategy, fundraising, board management, and organizational leadership.

Generate SQL queries from plain English descriptions for BigQuery, PostgreSQL, MySQL, and more.

Find gaps between what code should do and what it actually does.

Format Linear or Superset tickets with a standardized three-section structure.

Interact with OmniRoute A2A server, send tasks, and test the agent-to-agent protocol.

Backup and restore OmniRoute data, manage snapshots, and sync to cloud storage.

Verify code changes won't break the Pierre diff viewer integration.

Draft release notes with contributor credit, bump versions, and publish tagged releases.

Build tools to import, inspect, and migrate DeepChat chat data and configurations.

Control desktop apps and windows through screenshots, accessibility trees, and UI actions.

Read, update, and triage Linear issues directly from your workflow.

Control iOS simulators and interact with emulator streams directly from Orca.

Control Orca worktrees, terminals, repos, and embedded browser from Claude.

Configure git commits and changelogs following Chinese-adapted Conventional Commits standards.

Ask clarifying questions before starting work on ambiguous requests.

Find the simplest solution that works, questioning if the task is necessary.

Scan your entire codebase to find dead code, over-engineering, and simplification opportunities.

Display a quick-reference guide for Ponytail modes, skills, and commands.

Find over-engineered code, unnecessary dependencies, and complexity to delete.

Convert markdown workflow specs into compiled GitHub Actions using AI engines.

Automate browser interactions and test web pages with Playwright commands.

Automate tasks in your existing Chrome browser without creating new profiles.

Add redacted agent logs to GitHub PRs and issues for transparency.

Autonomously research, benchmark, and implement performance optimizations with production-ready pull requests.

Extract colors, fonts, and design tokens from any website into multiple formats.

Control Chrome via CDP protocol to automate browser tasks and reuse login sessions.

Get a cross-model review from Google Gemini on code, ads campaigns, or SEO changes.

Review project positioning, release strategy, and breaking changes for APM.

Launch and monitor AI coding agents in tmux with session management and parallel worktree support.

Attack ML models, craft adversarial examples, and solve AI-based CTF challenges.

Extract and organize your GitHub Copilot sessions into searchable Obsidian wiki pages.

Turn website data extraction into reusable, deployable skills with automatic API discovery.

Automate browser tasks like navigation, form filling, and content extraction for AI agents.

Build custom extensions for Super Agent Party with frontend or Node.js backends.

Discover and install agent skills to extend your capabilities.

Create, analyze, and modify Word, Excel, and PowerPoint files without Office installed.

Review code changes for quality, security, and performance issues.

Fetch brand logos and cloud service icons as ready-to-use SVG files.

Provision and orchestrate GPU workloads across clouds, Kubernetes, and on-premise clusters.

Access documentation and configuration guidance for the docmd AI-first docs engine.

Capture, clarify, and review product requirements before development starts.

Create and update feature task plans with progress tracking and blocker management.

Create, edit, and validate n8n workflows and automation configurations.

Generate multiple competing explanations for an observed problem or signal.

Decompose boundary statements into legal, admissibility, deontic, and evidence categories.

Manage project governance charters, interviews, and doctrine artifacts in Spec Kitty.

Structure code so business logic stays independent from frameworks and databases.

Create generative art with p5.js using custom algorithms and interactive parameters.

Create complex React artifacts with Tailwind CSS and shadcn/ui components.

Apply professional color and font themes to slides, docs, and web pages.

Test local web applications with automated browser interactions and debugging.

Create original visual designs as PNG and PDF files using design philosophy.

Build Model Context Protocol servers to connect LLMs with external APIs and services.

Detect AI-generated audio, images, video, and text to identify deepfakes and synthetic media.

Create, edit, and analyze Excel files with formulas, formatting, and data visualization.

Generate meeting prep materials and agendas by gathering Notion context and research.

Turn product specs into actionable Notion tasks with implementation plans.

Generate customer-friendly release notes from git commit history automatically.

View your context usage trends, quality scores, and session history in a live dashboard.

Search, transcribe speech, and extract text from documents using Azure AI.

Set up AI Runway on Azure Kubernetes Service from cluster to running model.

Learn state management best practices for the vm0 platform.

Apply consistent design patterns and conventions when building CLI commands.

Organize branch chains and manage stacked rebases, merges, and PR workflows.

Design schemas, optimize queries, and choose the right database for your application.

Extract design systems from UI screenshots and generate implementation-ready design prompts.

Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.

Diagnose and fix plugin installation, enablement, and activation problems.

Configure custom statuslines for Claude Code with token counts, costs, and git status.

Transcribe audio and video files to text with fast local or remote processing.

Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering.

Merge redundant documentation files while keeping all unique content and information.

Transform meeting transcripts into structured minutes with speaker identification and iterative review.

Convert markdown documents to professional PDFs with Chinese font support and theme options.

Convert DOCX, PDF, and PPTX files to clean, readable Markdown.

Debug network and streaming bugs using evidence-driven investigation and layered isolation experiments.

Capture macOS application windows programmatically with window control and automation.

Recover context from interrupted Claude sessions and continue work without replaying full history.

Find new Japanese NLP GitHub repositories missing from awesome-japanese-nlp-resources lists.

Write and update documentation for features, guides, and specs in Paca Docs.

Convert product requirements into structured epics with user stories and spec documents.

Author and publish curated release note story decks with images and videos.

Translate and sync App Store metadata to multiple languages automatically.

Store and retrieve decisions, discoveries, and patterns across chat sessions.

Classify and resolve conflicts when ingesting data bundles.

Create interactive UI mockups, prototypes, and wireframes as self-contained HTML.

Access stock quotes, charts, and financial data via the Yahoo Finance library.

Audit websites and repositories for SEO issues, Core Web Vitals, and schema optimization.

Interview users deeply about specs and tasks to extract complete implementation details.

Convert conversations into Flow Next spec files with review before saving.

Visualize spec dependencies, blocking chains, and execution order.

Design and implement Flutter state management using the Bloc and Cubit patterns.

Review Flutter and Dart pull requests against a structured quality checklist.

Structure Flutter apps with layered, feature-first architecture and dependency injection.

Create, edit, test, and optimize skills with performance benchmarking and accuracy improvements.

Calculate your agent's productivity score from session metrics and cache efficiency data.

Build AI chat interfaces with pre-made conversation and message components.

Search and retrieve SVG icons from 200+ libraries instantly.

List, query, version, and clean up model data artifacts with flexible filtering.

Audit components for WCAG accessibility issues and get fixes.

Add loading, success, error, and empty states to your components.

Create and apply brand.yml files for consistent branding across Shiny and Quarto projects.

Generate accessible alt text descriptions for images and data visualizations.

Split epics into detailed feature documents with scope and acceptance criteria.

Get design feedback by comparing your screen to real examples and improvement ideas.

Render interactive SVG diagrams, charts, and HTML widgets directly in chat.

Compile agent artifacts into a structured, interlinked markdown wiki.

Generate shadcn/ui-styled status badges for project documentation.

Discover and extract all URLs from any website's sitemaps.

Load named personas that shift how Claude approaches tasks and reviews work.

Deploy and manage generative AI models and ML workflows on SAP's enterprise cloud platform.

Master Godot 4.3+ 2D systems: tilemaps, parallax, lights, particles, and custom drawing.

Create an AI skill capturing a coworker's expertise and work style from your connected tools.

A fixture skill demonstrating incomplete implementation documentation.

Demonstration skill containing intentionally broken cross-references.

Identify markdown files missing required YAML frontmatter metadata.

Check if your local kernel matches the harness scaffold version.

Scaffold an AI agent harness in one command from pre-built templates.

Scaffold a custom AI agent harness with CLI, MCP server, and marketplace identity.

Diff two scaffolded harnesses and report manifest, host, and file changes.

Build production-grade web components and interfaces with polished, distinctive design.

Run a comprehensive WCAG compliance audit and generate a remediation plan.

Redesign and beautify pixel-art decorations for top-down game sprites.

Generate interactive architecture diagrams from codebases or system descriptions.

Audit and build accessible web interfaces meeting WCAG standards for news and academic sites.

Build modular data processing workflows with batch jobs and API integration.

Find, audit, and design AI agent loops with safe triggers, actions, and stopping conditions.

Manage tasks, boards, and workflows in your terminal with a CLI kanban tool.

Add purposeful animations and micro-interactions to enhance UI usability and delight.

Build self-improving AI agents using 9 reinforcement learning algorithms.

Extract design tokens and variables from Figma and generate ready-to-use QML code.

Apply your project's design system to UI, styling, and copy decisions automatically.

Break down objectives into focused, scoped work units with clear success criteria.

Design accessible iOS and Android interfaces following platform guidelines and modern best practices.

Explore ideas and tradeoffs through interactive conversation before implementation.

Build WCAG 2.2 compliant web apps with keyboard navigation and screen reader support.

Build accessible animations and page transitions with Motion library patterns.

Generate, review, and integrate AI-built UI components into design systems.

Query local project analytics for agent usage, costs, and performance trends.

Analyze code architecture, call graphs, and refactoring issues without AI.

Transform feature ideas into annotated stories with automated greenfield or brownfield detection.

Debug code issues by forming hypotheses from structural knowledge before reading code.

Apply a confirmed refactoring plan to your codebase step by step.

Write and run automated accessibility tests for web apps using Playwright and axe-core.

Scan web pages for WCAG compliance issues and accessibility violations using automated testing.

Generate HTML reports showing your Claude Code usage, projects, and activity statistics.

Generate PNG, JPEG, or WebP images using your ChatGPT account without an API key.

Scan code for WCAG 2.1 AA and EU accessibility compliance issues.

Generate multiple creative solutions in parallel for open-ended design problems.

Run automated accessibility tests and fix issues in your CI pipeline.

Test and improve web accessibility for WCAG compliance and inclusive design.

Attack any document or plan to find flaws, gaps, and weak points you'd miss otherwise.

Query scientific figures, select visual examples, and export reference bundles for plotting.

Keep documentation accurate and consistent with code changes.

Break design documents into atomic parallel tasks with dependencies and acceptance criteria.

Interview you to create project specs, charters, and acceptance criteria.

Get oriented to a multi-agent codebase and establish your role within the team.

Create reusable skills by analyzing your conversation history and learning from what worked.

Brainstorm ideas with a partner LLM in alternating turns, then synthesize the best into a plan.

Get nine pre-built Home Assistant dashboard styles with ready-to-copy CSS and templates.

Prepare a winning hackathon submission with track selection, demo scripts, and judging checklists.

Check your project files for conflicts before launching a team environment.

Search, create, update, and manage Jira issues, comments, and workflows.

Query wallet balances, token portfolios, transactions, and NFTs on Solana with USD pricing.

Execute substantial development tasks with isolated workspaces, testing phases, and quality gates.

Guide two agents through parallel research and joint design before implementation.

Plan and document design decisions before writing code.

Create a self-contained summary document to resume work in a new session or with another developer.

Monitor Treasury and bank liquidity impacts during US government shutdowns.

Record and query project decisions with timestamps, rationale, and consequences.

Generate responsive email templates that work reliably across Outlook, Gmail, Apple Mail, and mobile clients.

Generate automation scripts for browser agents to bundle multi-step interactions efficiently.

Track marketing funnel metrics from social posts through bookings.

Discover and test APIs for security vulnerabilities like BOLA, JWT attacks, and business logic flaws.

Map attack chains and kill paths from reconnaissance data using MITRE ATT&CK.

Map attack surface with subdomain enumeration, port scanning, and technology fingerprinting.

Map cloud infrastructure and identify security paths from external domains to cloud internals.

Connect to external services through managed API routes.

Publish React components to your team library or install shared ones.

Writes a clear pull-request title and a tight summary from a branch's diff or commit list.