Canonical NotFair workflow
Quick answer
- 01What is it?
- Produce a read-only, evidence-based paid-media performance review across connected platforms or supplied exports. It stands out by giving paid media a defined shape, so the agent asks for better context and returns a more usable result.
- 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-reviewSkill 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-review/SKILL.md completely, then follow it as the active workflow. Resolve every relative reference from that file against ../../paid-ads/paid-ads-review/.
Supporting file: paid-ads/paid-ads-review/SKILL.md
Paid Ads Review
Read ../shared/operating-contract.md and ../shared/measurement-framework.md. This is read-only.
Assemble comparable evidence
Check which sources are actually connected, request the missing export rather than reporting a failed call, and use the most recent complete equivalent window. For every source, keep currency, conversion definition, attribution window, and reporting lag visible. Verify tracking before treating CPA, ROAS, or revenue as a decision-grade metric.
For live platform accounts, hand data collection and diagnostics to /notfair:google-ads, /notfair:meta-ads, /notfair:paid-ads-x, or /notfair:paid-ads-linkedin. Keep TikTok, Amazon, and ChatGPT Ads review grounded in a verified connector or supplied platform export.
Report the decision, not a dashboard transcription
Lead with the strongest contributor, the largest risk, and one recommended next action. Include a platform scorecard with spend, qualified conversions, CPA, attributable revenue/ROAS where available, link CTR, and pace against the declared budget. Compare each row to the preceding equivalent period and name the likely driver only when data supports it.
Do not present an unqualified blended CPA or ROAS. If a cross-channel aggregate is useful, label the consistent conversion definition, attribution source, spend-weighted formula, and included channels. Separate confirmed facts from inference and mark absent tracking or data as a blocking limitation.
End with hold, investigate, or one proposed action; route mutations to /notfair:paid-ads-optimize or the relevant platform operator skill.
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-review 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