icp-gtm-sim SKILL.md skillA

icp-gtm-sim from researchifylabs/icp-gtm-sim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add researchifylabs/icp-gtm-sim/icp-gtm-sim@git:20260929.83a1260

Pins git:20260929.83a1260 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
researchifylabs/icp-gtm-sim
Path
SKILL.md
Versions recorded
1
Latest version
git:20260929.83a1260, committed Sep 29, 2026
Size
16,703 bytes
Repository stars
3
License
MIT

Find the ICP and validate GTM messaging by testing a product brief, marketing message, positioning, or GTM hypothesis against a simulated audience of buyer personas, and report which segment it lands with, what's blocking it, and what to fix. Use this whenever someone wants to know who their product or message is for, which segment or ICP to target first, whether their positioning works, what objections to expect, whether a GTM or messaging hypothesis holds up, or wants to pressure-test a…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ICP & GTM simulation

A grid of buyer personas reacts to a message. One run answers two questions: *who is this
for?* (the ICP) and *does the message work?* (GTM messaging). Because the grid is factorial,
the reactions show *which attribute* moves the response — turning "who is this for?" into a
conjunction specific enough to buy a list against.

These are model predictions about attribute labels, not customers. The output is a sharper
hypothesis and a shorter list of things to ask real people. State that once in the report,
then write with confidence — hedging every sentence doesn't add honesty, it just makes the
report unreadable.

The only setup is the user's brief. Propose everything else and let them adjust it in
conversation. Never ask them to write a config file.

## 1. Take the brief

Accept anything — pasted copy, a file, a URL, a rough paragraph. If they *describe* the brief
instead of showing it, ask for the real thing: a description tests your summary, not their copy.

Check three things and raise only what's actually wrong:

- **Does the copy name its own target audience?** "Built for growth marketers at mid-market
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add researchifylabs/icp-gtm-sim/icp-gtm-sim@sha256:da63473ad3f43594

The line at the top of this page pins the label git:20260929.83a1260, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vox3iclj52qgme3l.svg)](https://markdownregistry.com/a/art_vox3iclj52qgme3l)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 29, 2026.

versioncommittedcommitsizeaudit
git:20260929.83a1260 latest2026-09-29 83a1260 16,703 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16703 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

researchifylabs/icp-gtm-sim · 3 stars · license MIT · pushed 2026-09-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vox3iclj52qgme3l
GET https://markdownregistry.com/api/v1/resolve?ref=researchifylabs/icp-gtm-sim/icp-gtm-sim
GET https://markdownregistry.com/api/v1/blob/da63473ad3f43594a9e148845c913a57b5b93f8bf4d62cfae7f837d861cda5b0

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.