claudeskills

Use an AI coding agent to review and improve web projects against Lighthouse guidance, Core Web Vitals patterns, WCAG 2.2 accessibility practices, SEO requirements, and modern browser standards. The skills work across major frameworks or plain HTML and can be invoked by topic, but this is an unofficial collection intended as structured engineering guidance rather than an official certification tool.

guard-skills supplies focused second-pass reviews for production code, tests, documentation, WordPress, and WooCommerce work. Run the relevant guard after an agent changes a repository to catch patterns such as needless abstraction, ineffective tests, documentation drift, or platform-specific mistakes before commit or merge. The package is primarily Markdown and includes no executable scripts, network calls, or credential requirements.

Greptile Skills provides workflows for checking unresolved review comments and status failures, running a Greptile CLI review on the current checkout, and repeatedly reviewing and fixing a change. The skills can detect GitHub, GitLab, or Perforce from the environment, but you must install and authenticate the matching gh, glab, p4, or Greptile CLI first.

make-no-mistakes packages two Cursor agent skills, a standard version and a stronger variant. Once copied or linked into the Cursor skills directory, they add behavioral instructions intended to keep model output coherent, accurate, and less prone to cascading logic errors. The project is a prompt-level steering layer rather than a standalone test runner or formal verification system, so it can encourage a more careful coding workflow but does not itself prove that output is error-free.