ResearchifyLabs

Icp Gtm Sim — Testing skill for Claude Code

Testing community

Agent skill: find your ICP and validate GTM messaging by testing copy against simulated buyer personas.

How to install Icp Gtm Sim

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ResearchifyLabs/icp-gtm-sim and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Icp Gtm Sim does

Agent skill: find your ICP and validate GTM messaging by testing copy against simulated buyer personas.

Alternatives in Testing

  • Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
  • Deliver — Delivery phase - Review, validate, and test with multi-AI quality assurance 2.8k ★
  • Generic Browser Test — Execute browser UI testing workflows from a plan file against any URL 363 ★

README

icp-gtm-sim

An agent skill that finds your **ICP** and validates your **GTM messaging** by testing copy against hundreds of simulated buyer personas.

Paste a landing page, cold email, launch post or pitch. The skill builds a factorial audience (role × company size × industry × revenue × geography…), has every persona react to the exact copy, and tells you:

  • Who it lands with — the specific conjunction (e.g. growth leads at 11–50-person B2B SaaS companies under $1M revenue), specific enough to build a list against.
  • What's holding it back — separated into wrong audience (fix the targeting) and wrong message (fix the copy or proof).
  • What to do next — one real-world check and one message variant worth testing.

How it works

  1. Take the brief. Your exact copy — plus a quick check for things that skew results (copy that names its own audience, a missing price, the channel).
  2. Propose the audience. 4–5 filterable factors, every valid combination once, impossible companies dropped (a 5-person company with $100M revenue isn't a segment). You edit it in plain language: "drop manufacturing", "add funding stage", "only US".
  3. Run it. Each persona scores relevance, clarity and trust on a 1.00–5.00 scale and picks an intent: ignore · reject · inspect details · self-serve trial · bring to team. Large runs are split into parallel batches.
  4. Check before analysing. Flags flat dimensions, stereotyped responses and batch noise before any segment claim is made.
  5. Report. A short answer, a segment table with n on every number, and the full CSV as an audit trail.

It can also compare two runs — two message variants, a re-test after a copy change, or results from another tool.

Install

**Any agent** — Claude Code, Codex, Cursor, GitHub Copilot and 75+ others, via [skills.sh](https://skills.sh):

npx skills add ResearchifyLabs/icp-gtm-sim

**Claude Code plugin** — inside Claude Code:

/pl