Token导航 LogoToken导航

Agent Skill · 研究检索

meta-ads-campaign-builder(元广告活动构建器)

meta-ads-campaign-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

meta-ads-campaign-builder 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 48,496。

总安装 685周安装 28GitHub Stars 636下载 222核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:meta-ads-campaign-builder(元广告活动构建器)
来源仓库:https://github.com/athina-ai/goose-skills
仓库路径:skills/meta-ads-campaign-builder
安装命令:
npx skills add https://github.com/athina-ai/goose-skills --skill meta-ads-campaign-builder
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/athina-ai/goose-skills --skill meta-ads-campaign-builder

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

meta-ads-campaign-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索梳理等研究检索类工作。通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。

安装前需确认权限范围、维护状态,注意是否涉及联网、命令执行或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/meta-ads-campaign-builder

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/athina-ai/goose-skills --skill meta-ads-campai…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

meta-ads-campaign-builder 怎么安装?

在终端执行 npx skills add https://github.com/athina-ai/goose-skills --skill meta-ads-campaign-builder。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

meta-ads-campaign-builder 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

meta-ads-campaign-builder 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

meta-ads-campaign-builder 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

meta-ads-campaign-builder 用的人多吗?

公开数据是累计安装 685 次,近一周安装 28 次,下载 222 次,GitHub 636 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

meta-ads-campaign-builder 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
meta-ads-campaign-builder

元广告活动构建器 · 本页

685636需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Meta Ads Campaign Builder

Build a complete Meta Ads campaign structure — targeting, ad sets, placements, copy framework, and budget allocation. This skill handles the strategic architecture that determines whether a campaign succeeds before a single ad runs.

Core principle: The biggest Meta Ads mistake startups make is boosting a post and calling it a campaign. Proper campaign structure — objective selection, audience layering, placement optimization, and testing framework — is what separates burning money from building pipeline.

When to Use

  • "Set up Meta Ads for our product"
  • "Build a Facebook/Instagram ad campaign"
  • "Help me structure a Meta campaign"
  • "I want to run ads on Facebook — where do I start?"
  • "Create a Meta Ads plan for [product launch / lead gen / awareness]"

Phase 0: Intake

  1. Product name + URL — What are we advertising?
  2. Campaign objective:

- Awareness (brand reach) - Traffic (website visits) - Lead Generation (in-platform lead forms) - Conversions (website sign-ups / purchases) - App Installs

  1. ICP — Target buyer: role, company size, industry, pain points
  2. Monthly budget — How much for Meta specifically?
  3. Landing page(s) — Where will traffic go?
  4. Competitor names — For audience analysis
  5. Existing Meta Pixel / Conversions API? — Tracking setup status
  6. B2B or B2C? — Changes targeting strategy significantly

Phase 1: Campaign Architecture

1A: Objective Selection

Business GoalMeta ObjectiveWhy
"Get demos/leads"Lead Generation OR ConversionsLead Gen = in-app forms (higher volume, lower quality). Conversions = website (lower volume, higher quality)
"Drive free trial sign-ups"ConversionsOptimize for on-site conversion event
"Build awareness for launch"Awareness (Reach)Maximize eyeballs in target audience
"Retarget website visitors"ConversionsBring warm traffic back to convert
"Drive traffic to content"TrafficOptimize for clicks to blog/resource

1B: Campaign Structure

Campaign: [Product Name] — [Objective]
├── Ad Set 1: [Audience — Prospecting: Interest-Based]
│   ├── Ad 1: [Primary creative variant]
│   ├── Ad 2: [Secondary creative variant]
│   └── Ad 3: [Tertiary creative variant]
├── Ad Set 2: [Audience — Prospecting: Lookalike]
│   ├── Ad 1-3: [Same creative variants]
├── Ad Set 3: [Audience — Retargeting: Website Visitors]
│   ├── Ad 1-3: [Retargeting-specific creative]
└── Ad Set 4: [Audience — Retargeting: Engagement]
    └── Ad 1-3: [Engagement retargeting creative]

1C: Competitor Ad Research (Optional)

If competitors were provided, check what they're running on Meta:

web_search: site:facebook.com/ads/library "[competitor name]"
web_search: "[competitor name]" Meta Ads examples

The Meta Ad Library (facebook.com/ads/library) is publicly accessible — search for competitor pages to see their active ads, formats, and messaging angles. Use findings to inform copy angles and audience strategy.

Phase 2: Audience Strategy

2A: Prospecting Audiences

Interest-Based Targeting:

Research relevant interests, behaviors, and demographics:

web_search: [product category] Meta Ads targeting options
web_search: [ICP role] Facebook ad audience interests

Build audience layers:

LayerTargetingRationale
Job title / Industry[Specific titles, industries]Direct ICP match
Interests[Tools they use, publications they read, topics they follow]Behavioral proxy
Behaviors[Business decision makers, technology early adopters, etc.]Meta behavioral data
Demographics[Age range, education, income (if B2C)]Narrowing

Audience size target: 500K-2M for prospecting (smaller = expensive, larger = diluted)

Lookalike Audiences:

SourceLookalike %Rationale
Customer list (emails)1%Closest match to actual buyers
Website converters (Pixel)1%People who took action
Website visitors (Pixel)1-3%Broader interest signal
Page engagers3-5%Widest cold audience

2B: Retargeting Audiences

AudienceWindowPurpose
All website visitors30 daysBroad retarget
Visited pricing/demo page14 daysHigh intent — push to convert
Engaged with ads (no click)30 daysAwareness → consideration
Video viewers (50%+)30 daysWarmed but not clicked
Lead form openers (not submitted)14 daysAbandoned lead capture

2C: B2B-Specific Adjustments

B2B targeting on Meta is harder. Recommended approach:

  1. Upload customer email lists → Build lookalikes (best B2B signal)
  2. Layer interests with behaviors — "Business decision makers" + "[specific software interest]"
  3. Use LinkedIn for precision targeting — Meta for retargeting/awareness
  4. Exclude broad audiences — No one under 25, exclude students, exclude job seekers (unless relevant)

Phase 3: Ad Copy Framework

Per Placement, Generate Copy Structure

PlacementHeadline LimitPrimary Text LimitNotes
Feed (FB + IG)40 chars125 chars visible (500 max)Most versatile
Stories (FB + IG)40 charsMinimal text — visual-firstCTA button matters most
ReelsOverlay text onlyHook in first 3 secondsVideo required
Right column (FB)40 charsShortDesktop only — cheap impressions
Audience Network40 chars90 charsLower quality traffic

Copy Framework Per Ad

ElementFrameworkExample
Primary text[Hook → Pain/Outcome → Proof → CTA]"Still prospecting manually? [Product] finds qualified leads while you sleep. 500+ teams use it. Try free →"
Headline[Direct benefit or action]"Automate Your Outbound in 5 Min"
Description[Support or specificity]"No credit card required. Cancel anytime."
CTA button[Match to objective]Learn More / Sign Up / Get Started / Book Demo

Generate 3-5 Ad Copy Variants Per Ad Set

VariantAnglePrimary Text HookHeadline
1Pain"[Pain point question]""[Solution benefit]"
2Outcome"[Result promise]""[Specific metric]"
3Social proof"[Customer result + name]""[Join X teams]"
4Contrarian"[Myth busting]""[Unexpected claim]"
5Product-led"[Feature highlight]""[Feature → benefit]"

Phase 4: Budget & Bidding

Budget Allocation

Budget TierProspectingRetargetingTesting
< $1K/mo60%30%10%
$1K-5K/mo50%30%20%
$5K+/mo45%25%30%

Bidding Strategy

ObjectiveRecommended Bid StrategyWhen to Switch
ConversionsLowest Cost (start) → Cost Cap (after 50 conversions)Once you have conversion data
Lead GenLowest CostUsually sufficient for lead forms
TrafficLowest Cost per ClickKeep it simple
AwarenessLowest Cost per 1K ImpressionsMaximize reach

Learning Phase

Critical: Each ad set needs ~50 conversions/week to exit learning phase. If your budget can't support that:

  • Consolidate ad sets (fewer, larger audiences)
  • Use an earlier funnel event as the optimization target (e.g., "Add to Cart" instead of "Purchase")
  • Start with Traffic or Landing Page Views objective, switch to Conversions later

Phase 5: Output Format

# Meta Ads Campaign Plan — [Product Name] — [DATE]

## Campaign Overview
- **Objective:** [Selected objective]
- **Monthly budget:** $[X]
- **Target audience:** [ICP summary]
- **Geographic targeting:** [Countries/regions]
- **Placements:** [Automatic / Manual selection]
- **Conversion event:** [What we're optimizing for]

---

## Campaign Structure

[Visual tree]

---

## Audience Targeting

### Ad Set 1: [Name — e.g., "Interest-Based Prospecting"]
- **Audience size:** ~[N]
- **Interests:** [List]
- **Behaviors:** [List]
- **Demographics:** [Age, etc.]
- **Exclusions:** [Existing customers, recent converters]
- **Budget:** $[X]/day

### Ad Set 2: [Lookalike]
...

### Ad Set 3: [Retargeting — Website]
...

---

## Ad Copy

### Ad Set 1 — Ad Variant 1: [Angle Name]
- **Primary text:** "[Copy]"
- **Headline:** "[Copy]"
- **Description:** "[Copy]"
- **CTA:** [Button]
- **Landing page:** [URL]

### Ad Variant 2: ...

---

## Budget & Bidding
[Allocation table + strategy]

---

## Tracking Setup Checklist
- [ ] Meta Pixel installed on all landing pages
- [ ] Conversion events configured (lead, purchase, etc.)
- [ ] Conversions API connected (if server-side tracking)
- [ ] UTM parameters set for GA4 tracking
- [ ] Custom audiences created (website visitors, customer list)
- [ ] Lookalike audiences built

---

## Launch Checklist
- [ ] Campaign structure created in Ads Manager
- [ ] All ad copy uploaded with correct placements
- [ ] Audiences configured with proper exclusions
- [ ] Daily budget caps set
- [ ] A/B test structure confirmed (one variable per test)
- [ ] Conversion tracking verified (test conversion fired)
- [ ] Campaign set to start on [date]

---

## Week 1-2 Monitoring Plan
- Day 1-3: Check delivery — are ads spending? Any disapprovals?
- Day 4-7: Review CTR and CPC — are we in range?
- Day 7-14: First conversion data — any ad set clearly winning/losing?
- Day 14: First optimization pass — pause losers, scale winners

Save to meta-campaign-plan-[YYYY-MM-DD].md in the current working directory (or user-specified path).

Cost

ComponentCost
Audience research (web search)Free
Competitor ad research (web search)Free
Copy generation + structureFree (LLM reasoning)
TotalFree

Tools Required

  • web_search — for audience research, targeting ideas, and competitor ad research via Meta Ad Library

Trigger Phrases

  • "Build a Meta Ads campaign for [product]"
  • "Set up Facebook Ads for us"
  • "Create an Instagram ad campaign"
  • "Help me structure Meta Ads for lead gen"
  • "Plan a Facebook campaign for our launch"

平台分布

Codex

36.66%
按下载量换算81

Claude

31.92%
按下载量换算71

Cursor

17.97%
按下载量换算40

Gemini CLI

8.94%
按下载量换算20

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills