メニュー
Plan and prepare a new paid-media campaign or cross-channel test before it can spend. Use when asked to create, launch, start, set up, or allocate budget to an advertising campaign on any supported platform.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/TuYv/ccpm --skill paid-ads-launchコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分
Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. 广告创意/广告文案/RSA标题
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
SOC 職業分類に基づく
SKILL.md を表示中
| name | paid-ads-launch |
| description | Plan and prepare a new paid-media campaign or cross-channel test before it can spend. Use when asked to create, launch, start, set up, or allocate budget to an advertising campaign on any supported platform. |
| argument-hint | <business goal, budget, and target platform> |
Read ../shared/operating-contract.md and ../shared/measurement-framework.md.
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.
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 |
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.