---
title: "Turn your agent skill into a varg how to listing — tools & renderers tutorial and best practices for AI video"
description: "Publish your agent skill to varg how to in the one card format: checked, shown to you, sent for review. Install in Claude Code, Codex and Grok with one command."
url: https://varg.ai/how-to/skills/varg-publish-skill
updated: 2026-10-28
---

# Turn your agent skill into a varg how to listing — guide skill for tools & renderers

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

Publish your agent skill to varg how to in the one card format: checked, shown to you, sent for review.

- **Type:** [Guide](https://varg.ai/how-to/guides.md) · [Tools & renderers](https://varg.ai/how-to/browse/skills/tooling.md)
- **Slug:** `varg-publish-skill`
- **Status:** live
- **Publisher:** varg (varg, verified)
- **License:** MIT
- **Source:** https://github.com/vargHQ/skills/tree/main/varg-publish-skill
- **Works in:** Claude Code, Codex, Cursor, OpenClaw, Claude.ai, ChatGPT, Any MCP client
- **Requires:** a varg account (varg MCP login or VARG_API_KEY), curl
- **Cost:** Free — publishing costs no credits
- **Runtime:** a few minutes

## What it does

The flow an author's agent follows to list a skill on varg how to. It reads the skill folder or repo, checks for a duplicate with `search_skills`, runs the standard checklist (blocking: secrets, `curl | bash` or install hooks, unknown hosts, unlicensed media), and fills the card every listing uses: a name from the 12 name templates, a one-line summary under 160 characters, the install command copied from the repo, 3–6 use-when triggers, a category id, tags and a real example of the output (`references/card.md`). It shows the card in a fixed layout, publishes on the person's OK through the varg MCP `publish_skill` tool (or `POST /v2/skills/submissions` with a varg key), and explains review and `my_skills`. Publishing is free.

## Use when

- Publishing a skill you built to varg how to
- Listing a skill on varg so AI agents can find it
- Checking a skill against the varg media skill standard before sharing it
- Filling the catalog card for a skill: name, summary, install, category, example

## Not for

- Finding a skill (use how-to-make-ai-video)
- Adding a skill to the vargHQ/skills repo (that is a pull request)

## Install

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg`
- Codex: `npx skills add vargHQ/skills --skill varg-publish-skill -a codex -y`
- Cursor: `npx skills add vargHQ/skills --skill varg-publish-skill -a cursor -y`

## More tools & renderers skills

- [varg AI](https://varg.ai/how-to/skills/varg-ai.md): The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
- [Local-first video downloader: private, no subscription](https://varg.ai/how-to/skills/media-download.md): Save any video by link (X, YouTube, Instagram, TikTok, 1800+ sites) or Pinterest images as references, locally, no key.
- [Templates Gallery Ops](https://varg.ai/how-to/skills/varg-templates-section.md): Internal runbook for the varg app Templates gallery: publish renders, preview clips, frame-0 posters, shelves.
- [HyperFrames CLI](https://varg.ai/how-to/skills/hyperframes-cli.md): Drive the HyperFrames CLI: scaffold, check, preview, snapshot, edit the timeline, render locally or in the cloud.
- [HyperFrames Registry](https://varg.ai/how-to/skills/hyperframes-registry.md): Pull any of ~450 ready-made blocks into a video as editable source: transitions, titles, captions, charts, 3D.
- [HyperFrames Media Use](https://varg.ai/how-to/skills/hyperframes-media-use.md): Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.