Agentic Skills
Drop-in capabilities for your AI agents. Each skill is a self-contained workflow — download the .md file and plug it into any LLM.
- 1.Save the .md file to .claude/commands/ in your project
- 2.Use /skill-name in any Claude Code session
- 1.Paste the skill content as Custom Instructions or into a GPT's system prompt
- 2.Or create a Custom GPT with the skill as its instructions
- 1.Save as .cursorrules or .windsurfrules in your project root
- 2.The AI reads it automatically on every session
- 1.Paste as the system prompt in any API call or chat interface
- 2.Works with Gemini, Ollama, Llama, Mistral, and any OpenAI-compatible API
Pro tip: Skills are composable. Combine multiple skills in a single session — use /plan to design, /tdd to implement, and /code-reviewer to validate, all in one workflow.
Audits components for WCAG 2.1 compliance, missing ARIA attributes, keyboard navigation, and color contrast issues.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
Create beautiful visual art in .png and .pdf documents using design philosophy. Use when the user asks to create a poster, piece of art, design, or other static visual piece.
Build apps with the Claude API or Anthropic SDK. Triggers when code imports anthropic/@anthropic-ai/sdk/claude_agent_sdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK.
Guide users through a structured workflow for co-authoring documentation. Use when writing documentation, proposals, technical specs, decision docs, or similar structured content.
Create, read, edit, or manipulate Word documents (.docx files). Handles tables of contents, headings, page numbers, letterheads, tracked changes, comments, and more.
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code and UI design that avoids generic AI aesthetics.
A set of resources to help write all kinds of internal communications using structured formats. Covers 3P updates, company newsletters, FAQ responses, status reports, and more.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Read, create, edit, merge, split, rotate, watermark, encrypt, OCR, and manipulate PDF files using Python libraries and command-line tools.
Create, read, edit, and manipulate PowerPoint presentations (.pptx files). Includes design guidance for creating visually striking, non-generic slide decks.
Create new skills, modify and improve existing skills, and measure skill performance. Includes eval creation, benchmarking, and iterative optimization.
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, easing functions, and animation concepts.
Toolkit for styling artifacts with a theme. 10 pre-set professional themes with colors and fonts that can be applied to slides, docs, reports, HTML pages, or any artifact.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui. For complex artifacts requiring state management, routing, or rich UI components.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing screenshots, and viewing browser logs.
Create, read, edit, and manipulate Excel spreadsheets (.xlsx files). Handles formulas, formatting, charts, financial models, and data analysis with professional standards.
Designs REST or GraphQL APIs from requirements with typed schemas, validation rules, error contracts, and example requests.
Analyzes JavaScript bundle size, identifies bloated dependencies, and suggests tree-shaking and code-splitting opportunities.
Diagnose and fix failing CI/CD pipelines. Reads logs, identifies root causes, and applies targeted fixes.
Reviews code for bugs, logic errors, security vulnerabilities, and adherence to project conventions.
Creates conventional commits with proper formatting, staged file analysis, and hook compliance.
Audits a component library for consistency, accessibility compliance, reuse opportunities, and API design issues.
Identifies untested code paths, generates targeted tests for uncovered branches, and tracks coverage toward project goals.
Systematic debugging workflow that reproduces, isolates, root-causes, fixes, and verifies bugs with surgical precision.
Deploy current project to Vercel with environment configuration and preview URL generation.
Extracts and organizes design tokens from a codebase into a centralized, consistent token system.
Build, optimize, and debug Docker containers and compose files. Analyzes Dockerfiles for security, size, and performance.
Auto-generates API documentation, JSDoc/TSDoc comments, README sections, and architecture diagrams from source code.
Validate environment variables, secrets, and configuration. Catches missing or misconfigured values before they cause runtime failures.
Guided feature development with codebase understanding, architecture focus, and test-first approach.
Finds hardcoded strings, sets up i18n infrastructure, and extracts text into translation files.
Analyze cloud infrastructure costs and suggest optimizations. Finds unused resources, right-sizing opportunities, and savings.
Systematic Kubernetes debugging workflow. Diagnoses pod failures, networking issues, and resource constraints.
Guides database schema migrations, API version upgrades, and framework migrations with rollback safety.
Set up monitoring, alerting, and observability. Configures health checks, error tracking, and performance dashboards.
Build and scaffold ChatGPT apps using the OpenAI Apps SDK with MCP server integration.
Deploy Workers, Pages, and platform services on Cloudflare with intelligent product selection.
Build web games with a Playwright-driven development and testing loop for reliable iteration.
Edit and review .docx files programmatically with structured formatting and change tracking.
Turn Figma designs into production-ready code matching layout, states, and responsive behavior.
Use Figma MCP to inspect designs and translate them into implementable UI decisions.
Address all actionable comments in a GitHub PR review and summarize the updates.
Debug and fix failing GitHub Actions CI by inspecting checks, fetching logs, and proposing targeted fixes.
Generate and edit images using the OpenAI Image API with structured prompt augmentation.
Create clean, reproducible Jupyter notebooks for experiments and tutorials with structured templates.
Manage Linear issues, projects, and team workflows with MCP-powered project management.
Deploy web projects to Netlify with CLI-driven authentication, site linking, and preview/production deploys.
Capture conversations and decisions into structured Notion pages with proper linking and templates.
Prep meetings with Notion context, tailored agendas, pre-reads, and research enrichment.
Research across Notion sources and synthesize into structured briefs, comparisons, and reports with citations.
Turn Notion specs into implementation plans with milestones, tasks, dependencies, and progress tracking.
Reference official OpenAI documentation with cited, up-to-date guidance and upgrade references.
Create, edit, and review PDF documents with programmatic manipulation and content extraction.
Persistent browser and Electron QA with interactive Playwright sessions for debugging and evidence capture.
Automate real browsers from the terminal with Playwright scripts for testing and workflow automation.
Deploy applications to Render via Blueprints or MCP with service URL, env vars, and configuration.
Capture targeted screenshots of applications, web pages, and UI elements for documentation and QA.
Security reviews and secure-by-default guidance for codebases with actionable improvement recommendations.
Map maintainers, bus factor, and sensitive code ownership from git history for security risk analysis.
Repository-grounded threat modeling with abuse-path analysis and prioritized mitigations.
Read-only Sentry observability for investigating issues, root cause analysis, and impact assessment.
Create and edit PPTX slide decks programmatically with PptxGenJS and layout validation.
Generate and manage Sora videos with structured prompt planning and iterative refinement.
Generate narrated audio from text using OpenAI with voice style, pacing, and format control.
Create, edit, and analyze spreadsheets with formulas, structure, and formatting.
Transcribe audio and video using OpenAI with optional speaker diarization and clean summaries.
Deploy apps and agents to Vercel with zero configuration. No account required for preview deployments.
Stage changes, write a focused commit, and open a PR in one command for fast shipping.
Identifies performance bottlenecks through static analysis, suggests optimizations, and estimates impact.
Creates step-by-step implementation plans before writing code. Waits for confirmation before executing.
Comprehensive pull request review using specialized agents for code, tests, types, and silent failures.
Structural refactoring with dependency analysis, safe rename/extract/move operations, and regression verification.
Audits and fixes responsive design issues across breakpoints. Catches layout breaks, overflow, and touch-target problems.
Safe rollback procedures for deployments. Reverts to the last known good state with data integrity checks.
Bootstraps new projects, features, or modules from templates with proper structure, types, tests, and configuration.
Analyze application bottlenecks and recommend scaling strategies. Covers horizontal, vertical, and architectural scaling.
Scans code for OWASP Top 10 vulnerabilities, hardcoded secrets, insecure dependencies, and auth bypass risks.
Post-implementation cleanup pass. Finds reuse opportunities, improves quality, reduces complexity.
Automatically generates Storybook stories for components with variants, states, and interactive controls.
Test-driven development workflow. Writes tests first, then implements minimal code to pass.
Generates comprehensive test suites with happy paths, edge cases, error conditions, and boundary values from existing code.
Progressively tightens TypeScript strictness. Eliminates any types, adds missing annotations, and enables stricter compiler options.
Built a useful skill?
Skills are extensible. Add your own as an MDX file and share it with the community.