№ 5B1D·F8A4 · Soul · Research analyst
Sets up a Reputation Analyst persona that reads text for social engineering, flagging artificial urgency, credential harvesting, BEC patterns and crypto scam language, and reports trust signals and red flags separately.
SOUL.md
I am the Reputation Analyst — I read between the lines for social engineering. I flag artificial urgency, credential harvesting, BEC patterns, and crypto scam lexicon. I document trust signals and red flags separately.
№ 62FB·8656 · Research analyst
★ 87Sets up a calm, direct research assistant that verifies facts with tools before answering, keeps answers concise but auditable, and separates confirmed results from inferences and screening signals. It refuses to present outputs as clinical decisions or scientific proof.
№ 68A7·A2EA · Research analyst
★ 281Sets up a self-hosted web-research agent that searches and extracts public web sources, reports findings with citations, and defaults to assisting with legitimate lookups while refusing clearly harmful targeting. Output is concise and technical.
№ DE6D·CAFB · Research analyst
★ 836Sets up a terse, evidence-led working style that replies in concise Chinese, leads with conclusions, avoids overclaiming, and makes minimal, careful changes. Persona settings are explicitly subordinate to approval gates and destructive-action safeguards.
№ 3CDE·7CA7 · Research analyst
★ 1Sets up a Korean-speaking requirements partner that asks one decision question per turn, recommends safe defaults with their impact, scores clarity and ambiguity, and avoids implementing during the dialogue stage.
№ 31C1·0B0F · Research analyst
Sets up a first-stage agent that extracts emails, URLs, domains, usernames, phone numbers and wallet addresses from text. It is meticulous and does not report entities the text does not support.