Runs an evidence-led audit of performance, accessibility, SEO, best practices, and agentic browsing, then outputs a prioritized, verifiable report.
Audits and fixes web security, browser compatibility, and code quality using Lighthouse Best Practices as the baseline.
Diagnose and fix LCP, INP, and CLS using real-user CrUX field data plus browser performance traces.
A step-by-step skill for committing and pushing your working tree straight to a PR whose head branch lives on a fork — without touching origin/upstream.
A Bugcrowd-specific reporting overlay: VRT selection, manual severity-override requests, and ready-made out-of-scope rebuttals.
Produces, iterates, and scales paid ad copy that fits each platform's character limits and passes review.
Audit, optimize and track your content so ChatGPT, Perplexity, Claude and Gemini cite it as the authoritative source.
Scans React, Next.js, Vue, Angular, Svelte, or plain HTML code for WCAG 2.2 Level A/AA violations and delivers fix code plus compliance reports.
Scans, validates and syncs .env files, then generates safe .env.example templates and schemas.
Detects your project's migration framework, diffs the schema, generates migration plus rollback scripts, and flags risky DDL before you run anything.
Compares the running app's computed styles against project design tokens to catch hardcoded colors, unusable controls, and animations that never ran.
Sweeps a running web app by clicking every reachable control and reports dead buttons, console errors, failed requests, and API-vs-UI contradictions — no codebase knowledge required.
Instruments your running web app with a dev-only SDK so the agent can read real DOM, network, console and framework state, drive one full user flow, and return a pass/fail verdict with the file:line to fix.
Runs 28 scanners over a Git repo, AI skill, or MCP server to surface prompt injection, credential theft, supply-chain tampering, and known CVEs.
Analyzes GA4 traffic, acquisition, landing pages, events and conversions through the NotFair MCP connector, and safely handles key-event or custom-dimension changes.
Turns approved business evidence into a reviewable Google Ads asset manifest — sitelinks, callouts, snippets, image assets and PMax briefs — and publishes only after explicit approval.
A read-only Google Ads audit skill that reduces account health to three pulse metrics — waste, demand captured, CPA — each tied to a named contributor and a concrete fix.
Lets Claude write and run focused Playwright scripts to test sites, capture screenshots, and validate responsive layouts or login flows.
Runtime protocol for driving the md2wechat CLI to turn Markdown into WeChat Official Account HTML, drafts, and image posts.
Directs Claude to drive the `md2wechat` CLI for converting Markdown into WeChat Official Account HTML, with previews, cover art, and draft uploads.