Weather art generator that turns any city's live weather into a shareable poster and animated video. Enter a city name; the skill fetches real-time conditions, researches landmarks, and generates a styled poster with weather data rendered directly into the composition — plus a matching animated video with weather-driven motion. Six visual styles from DreamWorks miniature to cyberpunk. Weather drives every visual element: lighting, sky, color tone, and motion are all derived from actual condition
Vibe Code Reviewer — Reviews AI-generated code for the mistakes that sink vibe-coded apps: exposed API keys, missing auth, SQL injection, client-trusted payments. Built for non-engineers — plain-language findings, severity ratings, copy-paste fixes. Catches the security holes behind the "45% of AI code is vulnerable" stat before you ship.
Grill Me interviews you like a senior architect would before you build grounded in 18 curated architecture references, then writes your planning docs for you. 1. README — project overview 2. PRD — product requirements doc 3. Architecture doc — tech stack, service topology, integration patterns, security posture 4. Phase plan — locked decisions, delivery methodology, risk register, KPI summary 5. Use-cases — Mermaid sequence diagrams 6. Deliverables guide — phase-by-phase deliverables
AI 做的網站能跑，不代表敢上線。上傳已移除敏感資料的程式檔、ZIP、Diff 或設定截圖，取得 GO／先修／STOP、最優先的 3 個問題，以及可直接貼回 AI 開發工具的修復指令。
Turn Expo project notes into focused Android test plans.
An adversarial multi-perspective review of a document, plan, or decision, where reviewers actively disagree instead of converging. Invoke when someone asks to stress-test, tear apart, or find blind spots in a plan, pitch, PRD, strategy, architecture proposal, essay, or research design when previous review was too agreeable; or when committing to an expensive, irreversible decision after already picking a side. Not for fact-checking, proofreading, code review, or questions with a correct answer.
Turn one UGC ad into a control plus four production-ready variations that test one variable at a time.
marketingskills/skills/ab-testing. Corey Haines`s expert-level skill. It checks detectable lift, traffic limits, safe metrics, QA risk, and locked decision rules before launch. When you provide baseline rate, MDE, power, and traffic, it runs Python sample-size math to estimate required sample size and test duration, so you avoid wasted traffic, broken tracking, peeking, and fake wins. Support Corey Haines on https://buymeacoffee.com/coreyhaines
Other hook tools give you a score. This one refuses to. It measures which axis your own numbers support, and throws out the ones they do not. Paste your hooks with their real numbers. It builds candidate axes from your own copy, tests within-group homogeneity first, and only then compares groups. An axis whose groups are not internally consistent is rejected, not crowned. Ships with one measured prior: name the specific thing, not the category. On 14 ad creatives that ran 2.44x on CTR.