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.
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
Paste a viral Instagram or YouTube reference and get a score-backed decision: adapt it, change key variables, borrow the format, or skip it.
Send your product page URL, a screenshot, or pasted content, and this agent audits it into a prioritized CRO report. It checks 5 key areas (first impression, trust, pricing clarity, product info, CTA) and delivers your top 5 highest-impact fixes with concrete before/after copy examples. No invented stats, no vague advice — just recommendations grounded in your actual page content. Built to boost sales without increasing ad spend.
Paid ads advisor for performance marketers who need a diagnosis when ROAS drops, CPA spikes, or CVR falls — ranked hypotheses with confidence levels, not open-ended analysis. Routes to one of five task flows (Build / Diagnose / Decide / Report / Advise), applies the matching framework, and delivers structured output with stated assumptions. Unlike generic AI that asks 10 intake questions first, this outputs an immediate concrete deliverable — then refines with follow-up, not before.
Your agent or chatbot keeps getting document content wrong, citing passages that don't exist, or saying "I can't find it" about things plainly in the docs. This reframes it as a retrieval failure, not a prompt bug: corpus profile, chunking, embedding and vector-DB index choice, retrieval strategy (top-k, hybrid BM25 + dense, rerank, query rewrite), context assembly with citations, and a golden Q&A set scored on recall@k / MRR / faithfulness.
Before you quote, enter five RFQ facts and get a clear QUOTE, CLARIFY, or HOLD decision with the next buyer question. The core check runs locally with no login, upload, or tracking; optional AI follow-up uses your own OpenAI-compatible API Key.