viknesh20-20

Pre-launch audit for any website. Verifies privacy policy, ToS, cookie consent, sessions, sitemap, robots.txt, SEO meta tags, structured data, accessibility (WCAG AA), Core Web Vitals, and compliance frameworks (GDPR/CCPA). Returns severity-graded findings with a GO / NO-GO verdict.

End-of-session summary written to .claude/memory/handoffs/<date>.md so the next session can pick up cleanly. Captures what was done, what's pending, what's blocked, what to verify, and any decisions awaiting the user.

Scaffolds a new component, module, or package following the project's existing structure, naming conventions, and patterns. Auto-detects framework and generates all necessary files including tests.

Audits project dependencies for known vulnerabilities, outdated packages, unused dependencies, and license compliance. Works with npm, pip, cargo, go modules, and more.

Analyzes code for performance bottlenecks and produces prioritized, actionable optimization recommendations with before/after code. Use before shipping performance-critical features or when code feels slow.

Analyzes test coverage, identifies untested code paths, and generates tests for the most critical uncovered areas. Use to improve test coverage before releases.

Converts code between programming languages while preserving logic, error handling, and idiomatic patterns. Use when migrating modules between languages or frameworks.

Generates a comprehensive codebase onboarding guide by scanning the project structure, detecting the stack, mapping architecture, and identifying key entry points. Use when joining a new project or onboarding teammates.

Generates a CI/CD pipeline configuration for the project. Auto-detects the stack and creates GitHub Actions, GitLab CI, or other CI configs with lint, test, build, and deploy stages.

Accessibility audit of UI code or a running site against WCAG 2.1 AA. Walks every WCAG criterion that maps to common patterns: keyboard reach, focus visibility, contrast, semantic HTML, ARIA, labels, alt text, motion, screen-reader sense. Severity-graded with code fixes.

Reviews existing business code (billing, multi-tenancy, state machines, inventory, GL postings, audit logs, etc.) for missing real-world edge cases. Severity-graded findings — invariant violations, race conditions, missing idempotency, currency precision bugs, audit gaps, jurisdiction issues.

Scaffolds production-grade SEO for any website: per-page meta tags, Open Graph, Twitter Cards, canonical URLs, JSON-LD structured data, sitemap.xml, robots.txt, and security.txt. Auto-detects the framework and uses its idiomatic approach (Next.js metadata API, Astro layouts, etc.).