# Canonical NotFair workflow Human Guide

## What This Is For
Plan and prepare a new paid-media campaign or cross-channel test before it can spend. It gives the agent a clearer input/output frame for paid media: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Canonical NotFair workflow agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for canonical NotFair workflow.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Canonical NotFair workflow guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- Frame the work around canonical NotFair workflow and ask for the context needed to do it well.
- Turn vague preferences into explicit choices before drafting the final output.
- Ask for a concrete deliverable, not just general advice.

## Decision Points And Nuance
The original skill emphasizes: Supporting file: paid-ads/paid-ads-launch/SKILL.md, Gate the launch, Produce a preflight brief, Execute only on verified surfaces.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- | Field | Required content |

## Copy-And-Paste Prompt
```text
Use the Canonical NotFair workflow human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the nowork-studio/notfair-plugin skill entry for `paid-ads-launch`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Canonical NotFair workflow

Read [`../../paid-ads/paid-ads-launch/SKILL.md`](../../paid-ads/paid-ads-launch/SKILL.md) completely, then follow it as the active workflow. Resolve every relative reference from that file against `../../paid-ads/paid-ads-launch/`.

---

## Supporting file: paid-ads/paid-ads-launch/SKILL.md

# Paid Ads Launch

Read `../shared/operating-contract.md` and `../shared/measurement-framework.md`.

## Gate the launch

Do not build or recommend a spend plan until these are known: primary conversion and verification method, target CPA/ROAS or customer economics, daily and monthly budget, destination URL, geography, approved offer and claims, and the user who can approve spend. Diagnose tracking before optimizing toward it.

Choose the narrowest viable test. Search demand generally merits Google Search; visual discovery can suit Meta; B2B job/company targeting can suit LinkedIn; marketplace product demand can suit Amazon. A small budget split across several channels is usually an underpowered experiment: explain the tradeoff and set a review date if the user chooses it anyway.

## Produce a preflight brief

Mark the following artifact `ready_for_review`:

| Field | Required content |
|---|---|
| Objective and measurement | Conversion, source of truth, attribution window, baseline, target, and review date |
| Channel and structure | Platform, campaign/ad-set or ad-group structure, audience/query intent, and exclusions |
| Budget | Currency, daily cap, implied monthly maximum, allocation, and pacing guardrail |
| Message chain | Audience motivation, approved claim source, ad concept, CTA, and matching landing URL |
| Experiment | Single primary variable, success metric, guardrail, minimum observation window, and stop condition |
| Readiness | Tracking, policy/rights, creative, access, and dependencies marked complete or blocked |

## Execute only on verified surfaces

For Google Ads, hand the approved brief to `/notfair:google-ads`, then create paused and read it back. For Meta, use `/notfair:meta-ads` for supported operations and route unavailable creation steps to Ads Manager. For all other platforms, provide an operator-ready brief unless the current session exposes a verified NotFair connector with the needed capability. Never resume a campaign without a separate explicit approval.