Testing & QA on Vibe Coding

Playwright Browser Automation

Mon, 01 Jan 0001 00:00:00 +0000

This skill gives Claude Code direct, model-invoked control of Playwright — driving a real browser through a web app’s flows to click, fill forms, and validate behavior end-to-end.

Why a skill for this

Reading component code doesn’t confirm a flow actually works in a browser. A dedicated Playwright skill turns that verification into a repeatable, invokable step instead of an ad hoc script written from scratch each time.

iOS Simulator

Mon, 01 Jan 0001 00:00:00 +0000

The iOS Simulator skill lets Claude drive Apple’s Simulator directly — building the app, navigating its screens, and exercising flows the way a developer would during manual QA.

Why a skill for this

iOS development often has no equivalent to a browser’s headless test runner conveniently available mid-conversation. This skill closes that gap by giving Claude a controllable simulator instead of relying on the developer to manually verify every change.

FFUF Web Fuzzing

Mon, 01 Jan 0001 00:00:00 +0000

This skill integrates the ffuf web fuzzer, letting Claude run authenticated fuzzing scans, auto-calibrate for noisy responses, and analyze results for real vulnerabilities during a penetration test.

Why a skill for this

Fuzzing tools have enough flags and calibration nuance that getting authenticated, low-noise scans right by hand takes real fuzzer expertise. Packaging that expertise as a skill makes competent fuzzing runs repeatable for anyone using it.

Threat Hunting with Sigma Rules

Mon, 01 Jan 0001 00:00:00 +0000

This skill uses Sigma detection rules — a vendor-neutral format for describing log-based threat signatures — to hunt for suspicious activity and analyze security events.

Why a skill for this

Sigma’s rule format is expressive but verbose to write and match by hand across large event logs. A skill that already knows the format turns threat hunting into a repeatable query task instead of a manual log-reading exercise.

Trail of Bits Security Skills

Mon, 01 Jan 0001 00:00:00 +0000

Trail of Bits’ security skills bring their own audit tooling — static analysis with CodeQL and Semgrep, variant analysis, and vulnerability pattern detection — into Claude Code.

Why a skill for this

Security auditing firms encode years of hard-won pattern knowledge into their tooling configs. Packaging that as a skill means Claude Code inherits Trail of Bits’ actual audit methodology instead of a generic security pass.

Chrome Relay

Mon, 01 Jan 0001 00:00:00 +0000

Chrome Relay drives the user’s already-signed-in Chrome session — cookies, SSO, localhost included — through a local CLI bridge, as a real-browser counterpart to headless Playwright automation.

Why a skill for this

Some flows only work correctly inside an authenticated, already-logged-in browser session — SSO-gated internal tools, for instance. Relaying through the real Chrome session sidesteps re-authenticating a separate automated browser.

Full-Page Screenshot

Mon, 01 Jan 0001 00:00:00 +0000

This skill captures full-page screenshots of web pages via the Chrome DevTools Protocol, with zero external dependencies.

Why a skill for this

Full-page capture (beyond the visible viewport) usually needs either a heavier automation framework or manual scrolling-and-stitching. Talking to the DevTools Protocol directly gets a clean full-page image without either.

PICT Test Case Design

Mon, 01 Jan 0001 00:00:00 +0000

This skill designs comprehensive pairwise-combinatorial test suites from requirements or code, using Microsoft’s PICT methodology to keep the case count manageable.

Why a skill for this

Testing every combination of inputs is usually infeasible, but pairwise coverage catches most real-world combinatorial bugs with far fewer cases. PICT’s methodology is the standard way to generate that reduced set correctly.

Playwright Testing Skill

Mon, 01 Jan 0001 00:00:00 +0000

OpenAI’s curated Playwright skill gives Codex the same browser-automation and interactive test-authoring capability as its Claude Code counterpart, packaged for Codex’s skill system.

Why a skill for this

Verifying a web app in a real browser matters regardless of which coding agent is driving the session — this is the Codex-native equivalent of that same verification step.