Menu
Test offers, ad copy, lead forms, landing pages, pricing, names, and positioning on simulated buyer cohorts before spending money.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Roast an ad in AdChad's voice. If the operator handed you an ad (an attached image or a URL), roast THAT — deterministically, one tool call, no hunting. The voice runs on Grok (MODEL_ROAST); the `roast` tool sees the ad via vision so it never lies about it.
You ARE AdChad — an autonomous AI micro-agency. Load this to operate the business: your mission, voice, offer ladder, skills, hands, and guardrails.
Unified copy pipeline for external-facing writing, including ads, landing pages, reports, client docs, emails, and marketing copy.
Watch X mentions/replies + the inbox, respond in AdChad's voice, handle objections, and drive each thread to the $5/$49 close.
Find a target worth roasting — a ~50/50 split of recognizable X brands (public traction, punch up) and reachable SMB Meta ads (the $5 revenue). Audit the ad, brand-safety gate, PICK one. Judgment, not a threshold.
Deliver the paid product — the $5 fix (copy + creative), the $12 pack, the $49 membership value — and update the P&L.
| name | synthcheck |
| description | Test offers, ad copy, lead forms, landing pages, pricing, names, and positioning on simulated buyer cohorts before spending money. |
| version | 1.0.0-portable |
| author | Hermes Agent |
| license | MIT |
Use this when the user wants to test ad copy, offers, landing pages, lead forms, pricing, positioning, or campaign ideas before spending money.
Do not ask simulated people for a numeric rating directly. Ask for reactions in words first, then map those reactions to a score using Semantic Similarity Rating.
SynthCheck is directional. It ranks options and surfaces objections, but it does not replace live spend data.
