vertakhan
Community@vertakhan
VertaKhan provides a Claude skill suite for headless-browser QA testing, design review, security audits, and end-to-end release management.
Agent Skills by vertakhan
Showing 30 vetted skills indexed across 1 GitHub repositories.
VertaKhangstack
Provides structured AI agent workflow skills for software development, review, QA, and shipping.
VertaKhanbenchmark
Detects web performance regressions by comparing page metrics against captured baselines.
VertaKhandesign-shotgun
Generate multiple AI design variants and collect feedback through a browser comparison board.
VertaKhanplan-design-review
Reviews implementation plans for UI/UX design gaps and generates visual mockups before coding.
VertaKhanautoplan
Runs CEO, design, and engineering plan reviews sequentially with auto-decisions and a final approval gate.
VertaKhandesign-consultation
Generates a complete design system with typography, color, and layout into a DESIGN.md file.
VertaKhanfreeze
Restricts Edit and Write operations to a user-specified directory via PreToolUse hooks.
VertaKhancareful
Intercepts destructive bash commands and prompts for confirmation before execution.
VertaKhancso
Audits codebases and infrastructure for security vulnerabilities and produces a posture report.
VertaKhancanary
Monitors deployed web apps for console errors, performance regressions, and page failures using browser screenshots.
VertaKhaninvestigate
Diagnose bugs through systematic root cause investigation before applying fixes.
VertaKhandocument-release
Updates project documentation files to match shipped code changes after a release.
VertaKhangstack-upgrade
Upgrades gstack installations to the latest version and summarizes changelog changes.
VertaKhanland-and-deploy
Merges GitHub pull requests, waits for CI and deploy, and verifies production health via canary checks.
VertaKhancodex
Runs OpenAI Codex CLI for independent code review, adversarial challenge, and consult sessions.
VertaKhanqa
Tests web applications, fixes found bugs in source code, and re-verifies with atomic commits.
VertaKhanqa-only
Tests web applications via browser automation and produces structured QA reports without fixing anything.
VertaKhansetup-browser-cookies
Import cookies from a real Chromium browser into a headless Playwright browse session.
VertaKhanreview
Reviews pull request diffs against a base branch for structural issues before merging.
VertaKhanplan-ceo-review
Reviews implementation plans with CEO-mode scope analysis and failure-mode detection.
VertaKhanoffice-hours
Runs YC-style office hours diagnostics that produce design documents for product ideas.
VertaKhanretro
Generates weekly engineering retrospectives from git commit history with per-contributor metrics and trend tracking.
VertaKhanconnect-chrome
Launches a visible Playwright-controlled Chromium window with the gstack Side Panel extension auto-loaded.
VertaKhanbrowse
Controls a persistent headless Chromium browser for QA testing and site verification.
Frequently Asked Questions About vertakhan
FAQPage SchemaWhat tasks can I accomplish using VertaKhan's skills?▼
You can run headless-browser QA testing with screenshots and repro steps, benchmark Core Web Vitals and page load regressions, generate design systems and DESIGN.md files, review PR diffs for SQL safety and side effects, audit security posture, and ship code from feature branch through PR merge to verified production deploy.
Who are VertaKhan's skills designed for?▼
They target software engineers, QA testers, engineering managers, and founders working on web applications. Personas include developers debugging root causes, designers auditing visual consistency, security reviewers running OWASP and STRIDE analyses, and leads running weekly retrospectives or CEO-mode plan reviews.
How do the release and deploy skills work in practice?▼
The /ship skill runs tests, bumps VERSION, updates CHANGELOG, and creates a PR. Then /land-and-deploy merges it, waits for CI, deploys to production, and verifies health via canary checks. /setup-deploy first detects your platform (Fly.io, Render, Vercel, Netlify, Heroku) and writes config to CLAUDE.md.
What safety guardrails do these skills provide?▼
The /careful skill warns before destructive commands like rm -rf, DROP TABLE, force-push, and kubectl delete. /freeze blocks Edit and Write operations outside a designated directory via PreToolUse hooks. /guard combines both for maximum protection when touching production or debugging live systems.
What are the prerequisites for browser-based QA testing?▼
Browser skills require the gstack framework, which drives a persistent headless Chrome daemon at roughly 100ms per command. For authenticated pages, run /setup-browser-cookies first to import cookies from your real Chromium browser. /connect-chrome optionally attaches a visible Chrome window with a Side Panel activity feed.