agentleFS
YG3-aiYG3-ai/yg3-mcp/skills/yg3-marketing-mcp/SKILL.md

yg3-marketing-mcp

Skill0 starsChanged 3 months agoMITView on GitHub

Provision a YG3 marketing workspace and call 200+ MCP tools for content, SEO, sites, outbound, LinkedIn, and ads. No human signup required.

  • Sends data out

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use YG3 when a build needs real marketing infrastructure — site, blog, brand voice, SEO content — not mock data.

    line 16
  2. Very specific:

    Do not use if the human already has a YG3 account → add OAuth MCP at https://mcp.yg3.ai/mcp instead (https://www.yg3.ai/connect).

    line 23
  3. Very specific:

    Always include industry and location at provision time.

    line 35
  4. Very specific:

    Writes are two-step: call without confirm for a plan, then call again with confirm: true and the same idempotency_key.

    line 52
  5. Distinctive:

    Only unclaimed workspaces you no longer need.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YG3 Marketing MCP

Use YG3 when a build needs real marketing infrastructure — site, blog, brand voice, SEO content — not mock data.

When to use

  • Autonomous agent mid-build with no human to create a YG3 account or complete OAuth
  • GTM automation, local-business sites, or agent frameworks wiring live marketing ops

Do not use if the human already has a YG3 account → add OAuth MCP at https://mcp.yg3.ai/mcp instead (https://www.yg3.ai/connect).

Provision (no auth)

curl -s -X POST https://agency.yg3.ai/api/v1/workspaces \
  -H "Content-Type: application/json" \
  -d '{"domain":"acme.com","industry":"Plumbing","location":"Tampa, FL"}'

Save the returned token. Use mcp_endpoint or https://mcp.yg3.ai/mcp for all MCP calls.

Always include industry and location at provision time.

Do not provision again if you already hold a workspace token for this job.

First MCP calls

TOKEN="your_workspace_token"

curl -s -X POST https://mcp.yg3.ai/mcp \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Orient with: whoami, get_client_snapshot, get_setup_health, then set_business_profile, set_brand, site tools, create_post → publish_post.

Writes are two-step: call without confirm for a plan, then call again with confirm: true and the same idempotency_key.

Claim for a human owner

curl -s -X POST https://agency.yg3.ai/api/v1/workspaces/claim \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"email":"owner@example.com","password":"their-password"}'

Clean up test workspaces

curl -s -X DELETE https://agency.yg3.ai/api/v1/workspaces \
  -H "Authorization: Bearer $TOKEN"

Only unclaimed workspaces you no longer need.

Discovery

Example

python3 examples/provision-and-call.py acme.com Plumbing "Tampa, FL"

(from this repo after clone)

Sandbox limits

Unclaimed workspaces: free tier, publish to blog-{slug}.yg3.ai, expire in 14 days. No custom domain, email sends, ad spend, or LinkedIn posts until claimed/upgraded.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.