gtmlisted

Phased go-to-market for startup products. Builds a GTM playbook from upstream artifacts (validation-canvas, pitch-deck, brand-workshop), produces multi-channel content, schedules cadenced tasks, enforces compliance (CAN-SPAM/GDPR/FTC), emits handoff events. Trust ramp P1→P2→P3 (read-only → scheduled → autonomous). Project-local `.gtm/`. Kill switch via HALT file. Triggers on "set up GTM", "create a launch plan", "build a marketing playbook", "kick off go-to-market", "schedule social posts", "post-launch marketing", "growth ops", "draft launch content", or having pipeline output and asking "what's next for getting users". Single-channel asks for a startup product also trigger. NOT for brand identity (`brand-workshop`), pitch decks (`pitch-deck`), lean canvas (`validation-canvas`), adversarial review (`startup-grill`), one-shot non-startup content (`marketing:content-creation`), CRM/sales. NOT Google Tag Manager (different "GTM"). NOT the idiom "going to market with findings".
sorawit-w/agent-skills · ★ 1 · Code & Development · score 75

Install: claude install-skill sorawit-w/agent-skills

# GTM > **🚧 BETA — read before relying on it.** First release: 2026-05-06. > Iteration-1 evals scored 100% with-skill (24/24) vs 27.8% baseline (7/24, > +72pp delta across first-run-with-artifacts, cold-start, and kill-switch > tests). Those evals validate **structural reliability** — `.gtm/` file > structure, helper-function kill-switch pattern, handoff event vocabulary, > compliance gate refusals. They do **NOT** validate real founder workflows > on a real startup project — that dogfooding is the next milestone before > graduating to v1. > > **What this means in practice:** treat outputs as drafts to review, not > artifacts to ship. The first founder to actually run this on a live > project will surface issues the evals couldn't see. Breaking changes are > possible before v1 — particularly around the wizard-confirmation gate > (whether the playbook auto-runs vs. waits for explicit approval), the > exact handoff event payload shapes, and the trust-ramp promotion criteria. > > **What's known to work** (per evals): auto-detection of upstream > artifacts, `.gtm/config.yaml` + `.gtm/state.json` creation, P1 mode > default, brand-voice consumption from `DESIGN.md`, the architectural kill > switch (HALT file + helper-function wrapper), region-adapter loading, > compliance-gate refusal on non-compliant content, handoff event emission. > > **What's NOT yet validated:** content quality on real brands (evals only > checked structural keyword presence), graceful degradation when > `m