mcpField
V
Vaybel

Vaybel

Remote
vaybel.comBusiness & Marketing1Updated 3w ago

About Vaybel

Vaybel Skills provides agent workflows for apparel product creation and management, using Vaybel’s public MCP and REST primitives. Advanced users can adapt the TypeScript orchestration for trend discovery, product launches, optimization, content creation, and insights.

Key features

  1. 01Find trends and plan product drops
  2. 02Generate designs and product mockups
  3. 03Optimize Printify or Printful products
  4. 04Create listing and social content
  5. 05Review performance insights

Use cases

  1. 01Explore a clothing trend and plan a launch
  2. 02Create a design with listing mockups
  3. 03Optimize an existing Printify or Printful product
  4. 04Generate social content for a listing

MCP support

The skills call Vaybel’s public MCP server through TypeScript wrappers and authenticate with `VAYBEL_PAT`. Workflows compose the server’s primitive MCP and REST operations.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.vaybel.com/
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Vaybel Skills

Vaybel Skills are agent workflows for operating clothing-product workflows through the public Vaybel MCP server.

Documentation: https://vaybel.github.io/skills/

This repo follows the code-execution-with-MCP pattern:

Agent skill -> TypeScript orchestration -> mcp.vaybel.com

There is no CLI dependency in v1. Skills call MCP through the small wrappers in servers/vaybel/, authenticated by VAYBEL_PAT.

These skills are the advanced user's starting point: fork them and iterate on the orchestration to fit your own workflow. The public MCP and REST surface is deliberately made of primitives; workflows are yours to compose, fork, and tweak here.

Skills

  • /vaybel:find-trend - find a trend opportunity and generate a launch concept.
  • /vaybel:plan-drop - plan a themed release: create or open a drop, see which trends fit its brief, pin them, file designs into it, and read its readiness.
  • /vaybel:launch-product - select a blank, generate a design, generate listing-ready mockups, optionally generate listing product videos, and return concise launch links.
  • /vaybel:optimize-product - import and optimize an existing Printify or Printful product.
  • /vaybel:make-content - generate a video, slideshow, carousel, or single post for an existing listing, with social drafts and explicit publish.
  • /vaybel:analyze-insights - read performance KPIs, top design snapshots, credit state, and next-best-action guidance.

The scope matches the four primary Vaybel workflows:

Find Trend -> Launch Product -> Optimize Product -> Make Content

plan-drop wraps that loop in a release: a drop pins the trends that fit its brief and tracks the designs launched from them until they are live. analyze-insights is a read-only management skill for deciding which workflow to run next.

Setup - Recommended

Claude Code marketplace install:

/plugin marketplace add vaybel/skills
/plugin install vaybel@vaybel

Use one shared secret for MCP and skills: define VAYBEL_PAT in Claude Code settings, and reference it from the Vaybel MCP server config. Then run:

/vaybel:launch-product "washed trail running poster art on a heavyweight tee"
/vaybel:launch-product "washed trail running poster art on a heavyweight tee" --listing-channels tiktok_shop,etsy
/vaybel:find-trend tshirt --lifecycle rising
/vaybel:plan-drop "Fall '26" --kind seasonal --date 2026-10-01 --motifs pumpkin,moon
/vaybel:optimize-product --provider printify --product-id <external-id>
/vaybel:make-content <listing-id> --channels tiktok,instagram
/vaybel:analyze-insights --range 28d

Manual Setup

git clone https://github.com/vaybel/skills.git
cd skills
npm install
export VAYBEL_PAT="<your-vaybel-pat>"
./setup

Repository Layout

client.ts                    MCP transport and auth helper
servers/vaybel/              thin typed wrappers around public MCP tools
skills/*/                    SKILL.md plus TypeScript orchestration per workflow
.claude-plugin/              Claude Code marketplace metadata
.codex-plugin/               Codex plugin metadata
.cursor-plugin/              Cursor plugin metadata
docs-site/                   Astro Starlight documentation site (GitHub Pages)
scripts/validate.mjs         structural validation for skills and manifests
scripts/smoke/               clean-project host install smoke tests
DEPLOYMENT.md                marketplace deployment checklist

Validate

npm run validate
npm run typecheck
npm run build
npm audit --omit=dev --audit-level=moderate
scripts/smoke/host_install_smoke.sh

The smoke script creates a clean sibling project, installs the plugin into isolated Claude and Codex homes when those CLIs are available, and runs every skill runner in no-token mode. It uses tmux automatically when installed; pass --no-tmux to run serially.

Docs Site

The published docs at https://vaybel.github.io/skills/ are generated from this repository, not maintained separately. docs-site/scripts/sync-docs.mjs rebuilds every page from skills/*/SKILL.md, the skill references/, and the root Markdown files, so the site cannot drift from the skills it documents.

npm run docs:dev      # local dev server
npm run docs:build    # production build into docs-site/dist

.github/workflows/pages.yml builds the site on every pull request and deploys it to GitHub Pages on push to main.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.