Canonical NotFair workflow
Quick answer
- 01What is it?
- Plan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilities. Its edge is a particular angle on paid media, giving the agent tighter constraints than a plain canonical NotFair workflow request.
- 02Inputs
- Context for paid media: your goals, audience, constraints, and any source material the skill asks for.
- 03Output
- A ready-to-use result for paid media: the analysis, copy, or recommendations the agent produces.
Add this skill
Install as a package
Installs this one skill package for your coding agent, including any supporting files that skill ships with — not every skill in the repository. Read the tutorial.
$ npx skills add nowork-studio/notfair-plugin --skill paid-ads-chatgptSkill instructions
The instruction file for this skill. The skill also includes other files you need to install to use it.
Canonical NotFair workflow
Read ../../paid-ads/paid-ads-chatgpt/SKILL.md completely, then follow it as the active workflow. Resolve every relative reference from that file against ../../paid-ads/paid-ads-chatgpt/.
Supporting file: paid-ads/paid-ads-chatgpt/SKILL.md
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.
Common questions
How do I install Canonical NotFair workflow in Cursor, Claude Code, or Codex?
Run npx skills add nowork-studio/notfair-plugin --skill paid-ads-chatgpt in the project where you want it, then ask your agent for the skill by name. The --skill flag installs only Canonical NotFair workflow, not every skill in the repository.
Where does Canonical NotFair workflow come from and what license is it under?
Canonical NotFair workflow comes from the nowork-studio/notfair-plugin repository on GitHub. That repository has 3.4K GitHub stars. The skill is published under the MIT license.
Prefer plain text? Read the Canonical NotFair workflow guide as markdown.
Related skills
More from nowork-studio
More Paid Ads skills