菜单
Meta ads planning playbook: objectives, structure, audiences, creative, testing cadence, Pixel/CAPI measurement. Does not assume live Marketing API access.
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
Optimize budget allocation across paid media channels using Marketing Efficiency Ratio (MER), marginal ROAS analysis, diminishing returns modeling, and incrementality-informed decisions.
AI search and citation behavior change quickly. The frameworks below use the best available public data as of early 2026 (Google surfaces, ChatGPT, Perplexity, Gemini, and large-sample studies). Re-check assumptions as platforms update.
Plan, write, and maintain content that wins purchase-near buyers in both organic search and AI answer engines. BOFU content is structurally different from TOFU — the reader has accepted they need to decide; the page's job is to resolve the decision. Get it right and a single deep page can outperform dozens of informational posts on revenue contribution.
Analyze paid media performance across dimensions, funnels, cohorts, and channels — turning data into actionable insights and business narratives.
Systematic 70+ checkpoint audit covering tracking, structure, keywords, ads, bidding, budgets, audiences, and competitive positioning — with ICE-prioritized recommendations.
Build and configure Google Ads campaigns across all 10+ campaign types — from campaign type selection through settings, targeting, creatives, and launch.
| name | meta-ads-playbook |
| description | Meta ads planning playbook: objectives, structure, audiences, creative, testing cadence, Pixel/CAPI measurement. Does not assume live Marketing API access. |
Use this skill for Meta ads planning: objective selection, account structure, audiences, creative formats, copy, testing cadence, and measurement concepts (pixel, CAPI). Live Meta Marketing API access is not assumed unless the user has connected integrations—use llm_call (e.g. Perplexity) for policy and trend research and web_scrape for URLs the user provides.
llm_call: Current policy questions, format specs, competitor public positioning research—do not fabricate metrics.web_scrape: User-supplied landing pages, help articles, public policy pages.If the user connects Meta via app integrations, Composio tools may apply—never guess tool slugs; follow integration search workflow when available.