菜单
Plan and reallocate budget across platforms by ROI, with revenue projections and shift scenarios. Use when a user asks where to put budget across channels, the true ROI of each channel, what happens if they move spend from one platform to another, or how campaigns are pacing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Expand targeting without wrecking CPA — lookalike ladders, seed quality, audience layering, and exclusion hygiene across platforms. Use when a user wants to scale beyond exhausted audiences, build lookalikes, fix audience fatigue, or set up exclusion lists.
Build a post-cookie first-party data strategy — Enhanced Conversions, server-side tracking, Consent Mode v2, and activating owned data for targeting. Use when a user wants to recover lost conversion data, set up Enhanced Conversions or CAPI, implement consent mode, or plan for cookie deprecation.
Verify that ad campaigns actually target the geographies they claim — location criteria exist, presence-only matching is set, and click geography matches intent. Use when auditing campaigns, investigating cheap clicks or missing conversions, or reviewing any campaign before and after launch.
Diagnose and improve Google Ads Quality Score — Expected CTR, Ad Relevance, and Landing Page Experience — to cut CPCs and lift Ad Rank. Use when CPCs look high for the vertical, impression share is capped by rank, or keywords sit at QS 5 and below.
Optimize Google Shopping — product feed quality, titles, Merchant Center disapprovals, supplemental feeds, custom-label segmentation, and Shopping vs Performance Max structure. Use when Shopping impression share is low, products are disapproved, or feed titles and labels need work.
Design and run incrementality tests that measure true lift from ads — geo holdouts, platform lift studies, significance math, and iCPA decisions. Use when a user wants to know whether ads actually cause conversions, design a holdout test, or decide budget based on real lift.
| name | mmm-budget-planner |
| description | Plan and reallocate budget across platforms by ROI, with revenue projections and shift scenarios. Use when a user asks where to put budget across channels, the true ROI of each channel, what happens if they move spend from one platform to another, or how campaigns are pacing. |
Decide where the next dollar goes across platforms, grounded in real performance rather than gut feel. Reads are free; changing budgets is a change and waits for explicit approval.
Confirm the account and what is connected: list_connected_accounts.
Pull recent performance per platform so the plan sits on real numbers:
pull_google_ads_performance, pull_meta_ads_performance, pull_linkedin_ads_performance, and the other pull_<platform>_ads_performance tools for spend, conversions, and CPA per channel.get_attribution to see how conversions credit across touchpoints, not just last click.measure_incrementality where a holdout exists, to separate true lift from spend that would have converted anyway. This is the honest answer to "what is this channel really worth."optimize_budget reallocates spend across platforms toward the channels returning the most per dollar, within the total you set. Feed it the budget and any per-channel floors or caps, and it returns a proposed split.
Read the output as a plan, not a command:
Show the current split, the proposed split, the projected outcome, and the rationale. Change budgets only on the user's clear go, with update_campaign_budget (or by executing an approved plan). Guard against fat-finger amounts. Then confirm the new budgets with a fresh pull_<platform>_ads_performance read.
For single-account bid and pacing tuning rather than cross-platform allocation, use the optimize and bid-optimization skills. For pure ROAS and CPA math, use the roas-calculator skill.