
Turns Amazon return signals into evidence-backed product opportunities, challenges weak ideas, calculates inventory exposure, and issues a guarded BUILD, TEST, REJECT, or INSUFFICIENT EVIDENCE decision.

Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.

Helps users turn rough prompts into clear, specific, reusable prompts in different LLMs through concise critique.

Turn match observations into actionable football tactics and structured training sessions. MatchLab AI helps coaches analyze strengths and weaknesses, prepare for upcoming matches, design tailored drills, and track player development. Get clear reports, practical objectives, and recommendations based on the information provided—without invented statistics or match data.

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

Avoid shipping an agent / prompt on vibe checks, then discovering after a production failure that there is no repeatable evidence for quality. Produces 5-10 runnable eval test cases + grading rubric: happy path, edge cases, adversarial input, subtle quality tests, regression cases, quantitative assertions, and qualitative review, organized into evals JSON + grading JSON structures.

Wandeln Sie Kundenbewertungen, Umfrageantworten und Support-Tickets in priorisierte Themen, nachvollziehbare Belege und praktische nächste Schritte um.

Paste delivery commitments and acceptance wording, with your updates and records, and get a source-linked review ledger: what is directly supported, what is a gap, and what is still unknown — so you can decide what to chase, clarify, or verify next, without certifying completion.

Turn messy Amazon, Shopee, Shopify, App Store, or marketplace reviews into a buyer insight map you can act on: buyer language, pain patterns, purchase motivation, objections, competitor gaps, FAQ topics, and next experiments. Built so reviews stop being just star ratings, real selling points stop hiding in buyer words, and competitor complaints become product and listing opportunities.