Design Campaign 2

Builds a paid media campaign plan across channels with targeting, creative, budget, and experiment structure.

Published by @gtmagents·0 agent reads / 30d·0 saves·Updated June 14, 2026

Command: design-campaign

Inputs

goal – pipeline, revenue, awareness, lead gen, PLG activation, etc.
budget – total spend available.
channels – comma-separated list of platforms.
audiences – optional persona or account segments.
timeline – flight dates or campaign length.

Workflow

Brief Analysis – clarify KPIs, attribution, constraints.
Audience & Offer Mapping – align personas/offers to channels and creative formats.
Channel Plan – allocate spend by channel/ad set, define bidding/optimization events.
Creative & Experiment Plan – propose hooks, asset needs, tests per channel.
Measurement – specify tracking setup, dashboards, guardrail metrics, post-launch review cadence.

Outputs

Campaign plan deck/table with budgets, targeting, messaging.
Creative brief + asset checklist.
Experiment backlog + KPI targets.

Agent/Skill Invocations

media-strategist – leads planning.
campaign-architecture skill – enforces funnel/channel best practices.
creative-variants skill – recommends asset variations.

More on the bench

Build Social Calendar

Generates detailed social content calendar with briefs, approvals, and publishing workflow.

marketing-growth-copy+2

On Page

Use when crafting or refreshing pages to align copy, UX, and conversion goals with target keywords.

marketing-growth-copy+2

Audit Technical

Runs technical SEO diagnostics, prioritizes issues, and packages remediation guidance.

marketing-growth-copy+2

Sharebench · Public bench

Connect via MCP.

Add the public bench to any AI tool. Your agents read every artifact you see — no signup needed.

1Pick your tool

# Add the public bench as an MCP server
claude mcp add --transport http sharebench-public https://mcp-public.sharebench.ai

# Settings → MCP → Add new MCP server
{
  "mcpServers": {
    "sharebench-public": {
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}

# Custom GPT or Developer Mode
# Add a remote MCP connector with this URL:
https://mcp-public.sharebench.ai

# Append to ~/.codex/config.toml
[mcp_servers.sharebench_public]
url = "https://mcp-public.sharebench.ai"

2Ask your agent for an artifact

Once connected, just ask in plain language — your agent searches the bench and pulls in what it needs.“Pull the brand voice from sharebench and rewrite this draft.”