Testing

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).

Revenue-Centric Design (RCD) — evidence-backed principles for making a SaaS or startup product convert, retain, and monetize.

Initialize test framework with Playwright or Cypress.

Stage 1 of Clinical ASR Flywheel.

Use this skill automatically when you feel your code is ready for human review, and whenever writing or reviewing code comments.

Business-logic flaw hunting - workflow/state bypass, price/quantity tampering, negative/overflow values, coupon/refund abuse, mass assignment, and logic races.

Reviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human…

Google Tag Manager container audit — tag health, orphaned and paused tags, duplicate GA4 config, trigger coverage, Consent Mode, naming, workspace hygiene

The Monday memo a sharp analyst would write — joins spend on every ad platform to qualified calls, deals, revenue, refunds and churn per campaign ID, catches…

Performance Max campaign audit — asset group strength, asset coverage, search themes, audience signals, brand exclusions, channel distribution

Pre-flight QA for an email campaign — merge tags, broken links, spam triggers, compliance, mobile rendering — before you hit send

Search campaign audit for Google Ads (with Microsoft Ads parity) — match types, quality score, negative keyword gaps, search terms, ad strength, RSA asset…

Google Ads Shopping / retail audit (feed cross-checked against Shopify or WooCommerce when connected) — product feed coverage, listing-group granularity…

Use organic LinkedIn and X as a free creative test kitchen — listen to what people complain about and ask for, draft a week of hooks from customer language…

Autonomous bug-bounty campaign driver.

Shared discipline for every hunt-* skill: scope and authorization gating, the two-account rule, the confirmation gate that separates a real finding from a…

Evaluate acquisition channels using unit economics, customer quality, and scalability.

Read, write, and validate Grain's service-area-first Event Model topology.

Execute QA test plans on Holoscan Sensor Bridge hardware.

代码生成配图素材。用 HTML/CSS + Playwright 渲染高质量中文配图。 不依赖任何AI图片API，100%代码生成，字体可控、像素精确、零成本。 Trigger: "代码生成素材", "配图生成", "素材生成", "code material", "render material".

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via…

Test system for Megatron-LM.

Run a structured, critique-driven brand-identity process from any starting point — a company website, a written brief, a list of products, or just a name and…

Mobius 自我测试能力。部署后自动跑、也可手动跑一组 HTTP 冒烟(健康/鉴权/核心读 API/语音配置, 可选写往返), 快速确认重新部署后系统是否真的可用。当你怀疑系统异常、或刚部署完需要验收时使用。