ezzatmakar
- 7 skills
- 0 followers
- 9 hours ago last updated
- ▌
- ▌ Web Perf Audit · ezzatmakar bundleRun an evidence-based web performance and RUM (Real User Monitoring) audit on a live site or a codebase, and produce two documents — PERFORMANCE_AUDIT.md with every finding ranked, and PERFORMANCE_PLAN.md with the fixes organized into delivery phases. Measures field data first (Core Web Vitals p75 from CrUX/PageSpeed Insights), then lab (Lighthouse), response headers, runtime traces and static causes, covering LCP/INP/CLS/TTFB, JavaScript bundles and execution, network waterfalls, API latency, images, fonts, third-party scripts, caching, memory, mobile performance, performance budgets and per-deploy regressions. Use when asked to audit or improve site speed, page load, Core Web Vitals, LCP/INP/CLS, TTFB, bundle size, hydration cost, API latency, RUM or field performance, why a site is slow for real users, why a deploy made things slower, or to set performance budgets and regression gates. Measures before it recommends — it never invents a number and labels everything it could not measure.
- ▌ Comment Cleanup · ezzatmakar bundleSweeps a codebase and rewrites its code comments in place to one standard — short (1-line default, 3-line cap), sorted (canonical docblock tag order), correctly placed (attached to the declaration, no detached or trailing essays), and consistently marked (TODO with a tracked issue). Deletes comments that restate the code, banner art, commented-out blocks, changelog-in-comments, and assistant filler; adds a docblock only to non-obvious public API. Use when asked to clean up, shorten, sort, standardize, or fix code comments and docblocks — "my comments are too long", "sort the docblocks", "remove the useless comments", "normalize the JSDoc/PHPDoc/docstrings". Edits comments only, never executable code, and always previews the plan before touching a file. Do not use for writing prose documentation, README files, PR review comments, or commenting out code.
- ▌ Pre Push Review · ezzatmakar bundleReviews your local uncommitted changes before you push, in any language or framework (auto-detected), and scores Security, Performance, and Clean Code as Pass/Warn/Fail with an overall push-readiness recommendation. Use before pushing or committing — "check my changes before I push", "review my local diff", "is this safe to push?" — to get one Markdown report with evidence, impact, fixes, verification, references, and a per-measurement scorecard. Supports Quick, Standard, and Deep review modes. Do not use for feature implementation unless the user separately asks for fixes.
- ▌ Nextjs Pr Review · ezzatmakar bundleReviews pull requests, merge requests, branch changes, and code diffs for Next.js and React applications (App Router and Pages Router, Next.js 13–16). Use when asked to review a PR or changed code for security, performance, and clean-code quality, then create one detailed Markdown report containing evidence, impact, rationale, recommendations, validation results, references, and a merge verdict. Supports Quick, Standard, and Deep review modes and can optionally post findings as inline PR comments. Do not use for feature implementation unless the user separately asks for fixes.
- ▌ Laravel Pr Review · ezzatmakar bundleReviews pull requests, merge requests, branch changes, and code diffs for Laravel and PHP applications (Laravel 9–12, PHP 8.0–8.4). Use when asked to review a PR or changed code for security, performance, and clean-code quality, then create one detailed Markdown report containing evidence, impact, rationale, recommendations, validation results, references, and a merge verdict. Supports Quick, Standard, and Deep review modes and can optionally post findings as inline PR comments. Do not use for feature implementation unless the user separately asks for fixes.
- ▌ Technical SEO Geo Audit · ezzatmakar bundleRun a developer-focused technical SEO and GEO (Generative Engine Optimization) audit on a live website or a codebase, and produce one per-page README report — covering crawlability, indexability, rendering/SSR, Core Web Vitals, structured data, metadata, semantic HTML, redirects/HTTP, AI-crawler access and llms.txt — with every finding rated by severity and carrying a concrete code-level fix. Use when asked to audit SEO, check technical SEO, run an SEO health check, audit AI/LLM visibility, GEO, generative engine optimization, answer engine optimization, Core Web Vitals, render-blocking, indexability, crawlability, structured data, or "why isn't this page ranking / showing up in AI answers." Technical only — do not use for content, keyword, or editorial advice.