ウェブサイト、画像、プレゼンテーション、動画のためのオリジナルワークフロー。
Explore the individual skills in Anthropic’s official repository: documents, visual design, development and reusable workflows. Each entry includes its own introduction and two illustrative examples.
25 engineering workflows for requirements, planning, implementation, testing, review, performance and production delivery.
Define feature stores, debug feature retrieval and understand Feast data flows.
Apply focused rules for interface design, mobile layout, accessibility, writing and code comments.
Run Happy workspaces and use session, browser, terminal, diagram and observability workflows.
Review and improve SwiftUI state management, layouts, accessibility and performance, with Instruments trace guidance.
Review SwiftUI code for modern API usage, accessibility, data flow and performance.
security skill for Claude AI. Grade A. Continuous security vulnerability scanning for OWASP Top 10, common vulnerabilities, and insecure patterns. Use when reviewing code, before deployments, or on file changes. Scans for SQL injection, XSS, secrets exposure, auth issues. Triggers on file changes, security mentions, deployment prep.
Binary investigation and Android kernel CVE research using the remote Dr. Binary MCP service.
Install and update vendored Oxlint plugins that detect unwanted AI coding patterns while preserving a project's local rule customizations.
Four learning-oriented Skills for agent design, code review, MCP servers and PDF processing.
Review an AI agent Skill before installation using static scanning and source-aware security analysis.
Python reference examples and focused readability guidance.
Coordinate agents, workspaces, handoffs, advisors, committees and user plugins.
testing skill for Claude AI. Grade A. Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
Control authorized Android devices and create reusable app-verification Skills.
Keep code changes small, review connected code and track deliberate technical debt.
Run an iterative worker-reviewer cycle for code, specifications or writing, with actionable feedback and a bounded review loop.
React Doctor workflows for scanning React code, planning fixes, inspecting Three.js and measuring runtime performance.
Review and maintain dsh-TUI, triage issues and pull requests, and navigate its user guide.
Read service usage and investigate provider connection problems in CodexBar.
Concise agent responses plus workflows for code changes, research, token usage and optional Caveman Cloud operations.
Focused planning, research, debugging, review, reading, writing, and interface workflows.
Automate browser interactions, inspect pages and work with Playwright tests through the official Playwright CLI.