# Submit Skill

> |

- **Type:** Skill
- **Install:** `agentstack add skill-swan-gtm-gtm-skills-submit-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [swan-gtm](https://agentstack.voostack.com/s/swan-gtm)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [swan-gtm](https://github.com/swan-gtm)
- **Source:** https://github.com/swan-gtm/gtm-skills/tree/main/skills/.system/submit-skill

## Install

```sh
agentstack add skill-swan-gtm-gtm-skills-submit-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

Submit the user's GTM playbook to the GTM Skills library. The authoritative, always-current instructions live in the repo itself:

1. Fetch https://raw.githubusercontent.com/swan-gtm/gtm-skills/main/AGENTS.md
2. Follow its "Submitting a skill" flow exactly: interview the user (extract judgment, not just steps), draft the files from the repo's templates, run `node tools/validate.mjs`, then open a PR — or a "Submit a skill" issue if git isn't available.

Rules that never change:

- Only create or edit files under `skills//`.
- The skill folder name is permanent and globally unique — check for collisions first.
- Speak in GTM verbs in the skill body; never vendor tool names.
- Never include lifecycle or operational fields (`prefix`, `isDefault`, …) — content only.
- A `## What good looks like` section is mandatory; a skill without judgment gets rejected.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [swan-gtm](https://github.com/swan-gtm)
- **Source:** [swan-gtm/gtm-skills](https://github.com/swan-gtm/gtm-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-swan-gtm-gtm-skills-submit-skill
- Seller: https://agentstack.voostack.com/s/swan-gtm
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.