skill▌

Use this skill when the quality of the work depends on art direction, hierarchy, restraint, imagery, and motion rather than component count.

Anti-AI-slop design skill for creating and auditing web pages.

Read, search, and send Gmail emails. Access Google contacts.

Build, test, and automate Android applications using accessibility-driven navigation and structured data instead of pixel coordinates.

This skill allows you to fully interact with the Xiaohongshu (Little Red Book) platform. You can search for posts by keyword and return results, extract content from specific notes to structured markdown format, and perform engagement actions like liking, commenting, collecting, following users, and more.

Security-first vetting protocol for AI agent skills. Never install a skill without vetting it first.

Guidance for creating effective, discoverable skills for Claude Code plugins with progressive disclosure and strong triggering. \n \n Create skills in the plugin's skills/ directory with SKILL.md (required) and optional references/ , examples/ , and scripts/ subdirectories for progressive context loading \n Write frontmatter descriptions in third person with specific trigger phrases users would say (e.g., \"This skill should be used when the user asks to 'create a hook', 'validate tool use'...\"

Skills are modular packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools.

50+ production-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. \n \n Covers 10 golden rules including resilient locator selection ( getByRole() first), web-first assertions with auto-retry, fixture-based test isolation, and CI/CD best practices across GitHub Actions, GitLab, CircleCI, Azure, and Jenkins \n Includes framework-specific recipes for React, Next.js, Vue, Angular, and migration guides from Cypress and Selenium with TypeScript and JavaSc

Security gate that scans skills for malicious code, vulnerabilities, and suspicious patterns before installation. \n \n Runs four integrated scanners: aguara (prompt injection detection), skill-analyzer (malicious patterns and CVE database), secrets-scan (hardcoded credentials), and structure-check (malformed files and dangerous configurations) \n Accepts ClawHub skill names, GitHub URLs, or local paths as input and returns a three-tier verdict: BLOCKED (critical/high findings), REVIEW (medium f