What problem does it solve? Cold email openers need proof that you researched the prospect, but manually finding a named customer on each prospect's website does not scale, and letting a model write the sentence freely produces hallucinated names and copied numbers. ## Core Features & Use Cases - Ten-path page discovery: Probes /customers, /case-studies, /testimonials and seven other paths with free HEAD requests, including a soft-404 guard that rejects redirects to the homepage. - Model picker with verbatim gates: A locked prompt returns client_name, evidence_quote, detail_phrase, and confidence as JSON, then five code checks verify the name and quote appear verbatim on the fetched page and reject placeholder or investor/press/partner contexts. - Deterministic line assembly: A script, never the model, builds the clause "your work with X on Y", enforces grounding and grammar rules, and holds low-confidence rows for human review. - Use Case: Given a list of B2B prospect domains, produce a ship-ready case_study_line per row that slots into "Saw {{case_study_line}}." in email 1, with roughly 50-60% ship-ready coverage on a mixed list. ## Quick Start Give the skill a prospect domain like ramp.com and ask it to find a named customer on that company's case-study page and return the case_study_line for my cold email opener.
