Back to search
gtm-skills
SkillGitHub
Open, production-grade GTM skills for AI agents.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked yesterday
Badge for your README
Markdown
[](/listings/swan-gtm--gtm-skills)HTML
<a href="/listings/swan-gtm--gtm-skills"><img src="/api/listings/swan-gtm--gtm-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# one skill npx skills add swan-gtm/gtm-skills --skill reach-out # everything from one creator npx skills add swan-gtm/gtm-skills/skills/ido-goldberg # the whole library (interactive picker) npx skills add swan-gtm/gtm-skills
Add `-a claude-code`, `-a cursor`, `-a codex`, etc. to target a specific agent; `--list` to see what's here.
**Using Swan?** Every skill runs natively there with tools wired — hit **Use with Swan** on [gtmskills.com](https://gtmskills.com).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 56 lines
- # GTM Skills
- [](https://skills.sh/swan-gtm/gtm-skills)
- Open, production-grade go-to-market skills for AI agents — prospecting, research, outreach, signals, pipeline, RevOps. Built and curated by [Swan](https://getswan.com), authored by the GTM community.
- Every skill is a plain `SKILL.md` any agent can read — Claude Code, Cursor, Codex, Claude Desktop, and 70+ others. Use them anywhere; run them with full execution inside [Swan](https://getswan.com).
- Browse the library at **[gtmskills.com](https://gtmskills.com)**.
- ## Install
- ```bash
- # one skill
- npx skills add swan-gtm/gtm-skills --skill reach-out
- # everything from one creator
- npx skills add swan-gtm/gtm-skills/skills/ido-goldberg
- # the whole library (interactive picker)
- npx skills add swan-gtm/gtm-skills
- ```
- Add `-a claude-code`, `-a cursor`, `-a codex`, etc. to target a specific agent; `--list` to see what's here.
- **Using Swan?** Every skill runs natively there with tools wired — hit **Use with Swan** on [gtmskills.com](https://gtmskills.com).
- ## Submit your skill — with your AI
- You don't need to know git. Paste this to Claude, Cursor, or any capable agent:
- > Fetch https://raw.githubusercontent.com/swan-gtm/gtm-skills/main/AGENTS.md and follow its submission flow. Interview me thoroughly about my GTM skill — the full playbook, including my rubrics, numbers, and real examples — draft it in their format with reference pages for the depth, and submit it.
- Your agent will interview you, package your playbook in our format, validate it, and open the PR (or a submission issue if it can't use git). Details in [CONTRIBUTING.md](CONTRIBUTING.md).
- ## Layout
- ```
- skills/
- <creator>/ # a creator's space — their profile + all their skills
- author.md # who they are
- <skill>/
- SKILL.md # the skill — portable, tool-agnostic
- swan.md # optional — Swan-specific execution layer
- references/ # optional — deeper material the skill routes to
- ```
- The folder name is the skill's permanent identity. Categories, tags, and everything else live in frontmatter.
- ## What makes a skill good here
- Skills encode **judgment, not just steps** — what the best operator notices first, what gets overlooked, what good output looks like. They speak in GTM verbs ("check the CRM", "load the ICP"), never vendor tool names, so they work whatever your stack is. The bar is documented in [CONTRIBUTING.md](CONTRIBUTING.md); enforcement is `node tools/validate.mjs` + human review.
- ## License
- MIT — see [LICENSE](LICENSE). Attribution stays with you: your profile travels with your skills.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.