Skip to content

The GTM Co-Founder v1.1.0 — enforcement layer

Choose a tag to compare

View all tags
@AIDevGTM AIDevGTM released this 28 Jul 12:56
· 22 commits to main since this release
v1.1.0
d424f60

Adds an enforcement layer so the agent follows the go-to-market SOPs, not just reads them. Thanks to cgallic (kai-cmo-harness) for the nudge.

What's new

  • A non-negotiable protocol in AGENTS.md: five gates the agent runs every session (state before advice, diagnosis before tactics, evidence before belief, the judge is not the author, update state after).
  • A new skill, review-the-work: an actor-vs-judge self-check gate. Before any deliverable reaches you, the agent stops being the author, becomes the skeptic, and stress-tests it against the standard.

18 skills total.

Install with no terminal

Claude apps (claude.ai, desktop): download any single skill's zip below, then go to Customize -> Skills -> Create skill and upload it. Start with 00-start-here.

Claude Code (no CLI): download gtm-cofounder-skills.zip, unzip it, and move the folders into ~/.claude/skills/.

Prefer the CLI? npx skills add AIDevGTM/gtm-cofounder, or the plugin marketplace. See the README for all paths.

Assets 21
Loading