Gtm Skills

GTM Skills

[](https://github.com/esmefong/gtm-skills/actions/workflows/verify.yml)

Built by [Esme Fong](https://esmefong.com). I spent 14 years building data and growth systems, most recently an AI-enabled marketing operating system across three brands as a solo marketer, which cut content production cycle time by 50%. This repo is the reusable machinery from those systems, rebuilt in public: the research, sourcing, outreach, positioning, and quality layers of a go-to-market engine, each one runnable and checked. I build things like this for teams that want their GTM to run as a system; I'm at [linkedin.com/in/esmefong](https://linkedin.com/in/esmefong) and the case studies behind these skills are at [esmefong.com](https://esmefong.com).

Each skill is a folder in the Claude Code skill format: a `SKILL.md` spec an AI agent can execute (a disciplined SOP with judgment rules baked in), reference docs, worked examples, and plain Python scripts. If you use Claude Code, copy a folder into `~/.claude/skills/` and it runs. If you don't, every script is standard-library Python with no API keys and runs anywhere, and every example reads as a document.

One company, end to end

All worked examples run on one real company, **Cohere**, from public data only. This is a standing demonstration, not client work, and I have no affiliation with Cohere; every claim in the examples carries a cited public source and date. The thread: [icp-research](icp-research/) defines who buys and why. [account-sourcing](account-sourcing/) turns that ICP into a ranked, evidenced account list. [outbound-engine](outbound-engine/) turns a live signal into a sequence, or refuses to send. [brand-voice-guide](brand-voice-guide/) extracts the voice that [positioning-message-house](positioning-message-house/) writes in and [content-quality-check](content-quality-check/) enforces. [market-prioritization](market-prio