Claude Cursor Skill

paid-ads-chatgpt

Plan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilities. Use for ChatGPT advertising, OpenAI ads, conversational ad concepts, ChatGPT campaign plans, or performance reviews from a verified export.

LLM Mart · 0 points · 22 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download nowork-studio-notfair-plugin-paid-ads_paid-ads-chatgpt-adf7601.zip · 1 KB

nowork-studio/notfair-plugin 3849 495 forks MIT Updated 2d ago

Part of nowork-studio/notfair-plugin — 88 skills

Install

skills CLI npx skills add https://github.com/nowork-studio/notfair-plugin/tree/main/paid-ads/paid-ads-chatgpt

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install nowork-studio-notfair-plugin@llmmart

Git git clone https://github.com/nowork-studio/notfair-plugin.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole nowork-studio/notfair-plugin collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

ChatGPT Ads Planning

Read ../shared/operating-contract.md and ../shared/measurement-framework.md. This plugin has no declared first-party NotFair ChatGPT Ads connector. Do not claim that inventory, campaign creation, targeting, or creative formats are currently available without official, current evidence.

Design a bounded experiment

Define the business objective, approved destination, conversion event, source-of-truth measurement, geographic and audience constraints, spend ceiling, and observation window. Write a concise, concrete message that earns attention without claiming results the business cannot substantiate. Include a claim ledger, rights review, and an explicit policy/eligibility check owned by the human platform operator.

Present a ready_for_review test brief with: hypothesis, audience/context assumptions, creative and landing-page message match, budget and monthly maximum, primary metric, guardrail, attribution caveat, and stop condition. Treat early delivery or engagement as directional signal, not proof of incremental conversions.

Verify externally

If the user provides an official account export or a verified connector becomes available, review only what it exposes and preserve its attribution definition. Otherwise, provide the brief and state the exact missing access. Never fabricate a campaign ID, delivery result, or platform setting.

Files (notfair-plugin)

agents

openai.yaml 227 B

interface:
  display_name: "ChatGPT Ads Planning"
  short_description: "Plan ChatGPT Ads experiments without unsupported claims"
  default_prompt: "Use $paid-ads-chatgpt to plan a ChatGPT Ads experiment or review its results."

SKILL.md 1.7 KB

---
name: paid-ads-chatgpt
description: Plan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilities. Use for ChatGPT advertising, OpenAI ads, conversational ad concepts, ChatGPT campaign plans, or performance reviews from a verified export.
argument-hint: "<objective, audience, or verified ChatGPT Ads export>"
---

# ChatGPT Ads Planning

Read `../shared/operating-contract.md` and `../shared/measurement-framework.md`. This plugin has no declared first-party NotFair ChatGPT Ads connector. Do not claim that inventory, campaign creation, targeting, or creative formats are currently available without official, current evidence.

## Design a bounded experiment

Define the business objective, approved destination, conversion event, source-of-truth measurement, geographic and audience constraints, spend ceiling, and observation window. Write a concise, concrete message that earns attention without claiming results the business cannot substantiate. Include a claim ledger, rights review, and an explicit policy/eligibility check owned by the human platform operator.

Present a `ready_for_review` test brief with: hypothesis, audience/context assumptions, creative and landing-page message match, budget and monthly maximum, primary metric, guardrail, attribution caveat, and stop condition. Treat early delivery or engagement as directional signal, not proof of incremental conversions.

## Verify externally

If the user provides an official account export or a verified connector becomes available, review only what it exposes and preserve its attribution definition. Otherwise, provide the brief and state the exact missing access. Never fabricate a campaign ID, delivery result, or platform setting.