← 返回 Skills 市场

Ad Campaign Optimizer

Name: Ad Campaign Optimizer
Author: yang1002378395-cmyk

作者 yang1002378395-cmyk · GitHub ↗ · v1.0.52 · MIT-0

cross-platform ⚠ suspicious

406

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ad-campaign-optimizer

功能描述

自动创建和优化多平台广告，支持A/B测试、成本及ROI分析，实现精准受众定向和素材推荐。

使用说明 (SKILL.md)

AI 智能广告投放助手

描述

自动优化广告投放、A/B 测试、成本优化、ROI 分析。适合广告投放、市场、电商、品牌方。

核心能力

自动创建广告（多平台：百度/抖音/微信/小红书...）
A/B 测试（自动测试多版本广告）
成本优化（降低 CPC/CPM）
ROI 分析（实时监控）
受众优化（精准定向）
创意优化（推荐最佳素材）

使用场景

电商投放 - 优化产品广告、降低成本、提升转化
品牌投放 - 提升品牌曝光、优化受众定向
App 推广 - 优化安装成本、提升留存
本地服务 - 精准投放本地客户、提升到店

定价

基础版：¥299/月 - 单平台 + 基础优化
专业版：¥999/月 - 多平台 + A/B 测试 + ROI 分析
企业版：¥2999/月 - API + 私有部署 + 专属顾问

目标客户

广告投放 / 信息流优化师
市场经理 / 品牌方
电商卖家 / 跨境卖家
企业主 / 创业者

ROI

成本降低：-30%（降低 CPC/CPM）
转化提升：+50%（精准定向）
人力成本：¥10000/月（优化师）→ ¥299-2999/月
ROI：3-33 倍

快速开始

# 创建广告
python create_ad.py --platform "抖音" --product 123 --budget 1000

# A/B 测试
python ab_test.py --ad_id 456 --variants 5

# 优化建议
python optimize.py --ad_id 456 --target "降低CPC"

示例输出

📊 广告投放报告

广告：产品A - 抖音信息流
预算：¥1000/天
投放天数：7 天

📈 数据概览：
- 展示：125,000 次
- 点击：3,125 次（CTR 2.5%）
- 转化：125 次（CVR 4%）
- CPA：¥56（低于行业平均 ¥70）

✅ 优化成果：
- CPC：从 ¥0.40 降至 ¥0.32（-20%）
- CTR：从 2.0% 提升至 2.5%（+25%）
- ROI：3.5x（每投入 ¥1 获得 ¥3.5 回报）

💡 优化建议：
1. 增加预算至 ¥1500/天（ROI 良好）
2. 定向"25-35岁"用户（CTR 最高 3.2%）
3. 使用素材B（CTR 比素材A 高 30%）

🎯 最佳受众：
- 年龄：25-35岁
- 地区：一线城市
- 兴趣：科技/数码

创建时间：2026-03-13

安全使用建议

Do not supply platform credentials or run arbitrary commands for this skill as-is. Key concerns: (1) the SKILL.md expects python scripts (create_ad.py, ab_test.py, optimize.py) but no code is included — ask the publisher for the source repository or the missing files; (2) the skill makes claims about integrating multiple ad platforms but declares no API keys or auth method — request explicit list of required credentials and an auth flow before providing secrets; (3) verify what network endpoints the code would call and whether data (campaigns, customer lists) would be uploaded to third parties; (4) prefer a version that includes source code or a known install mechanism (GitHub release, package registry) you can inspect, or run it only in an isolated/test environment. If the publisher cannot provide the code or a transparent install and credential explanation, treat the skill as untrusted.

功能分析

Type: OpenClaw Skill Name: ad-campaign-optimizer Version: 1.0.52 The skill bundle contains metadata and documentation for an 'AI Ad Campaign Optimizer' designed for multi-platform advertising management. While the SKILL.md file references several Python scripts (e.g., create_ad.py, ab_test.py) that are not present in the provided files, the documentation itself is purely descriptive and lacks any indicators of malicious intent, such as data exfiltration, unauthorized network calls, or prompt injection attacks. The discrepancy between version numbers in skill.json and _meta.json appears to be a minor administrative inconsistency.

能力评估

⚠ Purpose & Capability

Name/description claim multi-platform ad creation and optimization (Baidu/抖音/微信/小红书). That purpose normally requires platform API credentials and runtime code. The manifest declares no required binaries, no env vars, and no code files, yet SKILL.md shows example commands invoking python scripts (create_ad.py, ab_test.py, optimize.py) which are not present. This mismatch suggests the declared requirements are incomplete or the skill is a thin instruction stub relying on external artifacts.

⚠ Instruction Scope

SKILL.md instructs running python scripts with parameters to create ads and run A/B tests. It does not describe where those scripts come from, what network endpoints they call, or what credentials they need. The instructions therefore leave broad discretion and implicitly require access to ad-platform credentials and possibly external APIs — none of which are declared. The examples could cause an agent to attempt to run nonexistent local scripts or to ask the user for sensitive tokens later.

ℹ Install Mechanism

There is no install spec and no code files — this reduces immediate filesystem risk. However, the absence of an install plus references to local python scripts is inconsistent: either the skill should include code or should declare the external dependency/source. The lack of install spec makes it unclear how the advertised functionality would actually be delivered.

⚠ Credentials

No environment variables, credentials, or config paths are declared, yet the skill claims to operate across multiple advertising platforms that require API keys/tokens. The omission is disproportionate: a legitimate multi-platform ad tool would normally request or document required API credentials and auth flows. This gap is a red flag for missing or hidden credential usage.

✓ Persistence & Privilege

always:false and default agent invocation settings are used. The skill does not request permanent inclusion or modify other skills/system settings. No elevated persistence is declared.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ad-campaign-optimizer
安装完成后，直接呼叫该 Skill 的名称或使用 /ad-campaign-optimizer 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.52

- No changes detected in this version; content and features remain the same.

v1.0.51

- No code or documentation changes detected in this version. - All features, examples, and usage instructions remain the same.

v1.0.50

- No visible changes in this version; SKILL.md content remains the same. - No file changes detected.

v1.0.49

- No visible changes detected in this version; content remains the same as the previous release. - All features, usage scenarios, pricing, and examples are unchanged.

v1.0.48

No changes detected in this version. - Skill content remains unchanged from the previous version.

v1.0.47

Version 1.0.47 of ad-campaign-optimizer - No file changes detected in this version. - No updates to features, functionality, or documentation.

v1.0.46

- No changes detected in this version; documentation and features remain the same.

v1.0.45

No visible changes detected in this version. - No file changes or content updates were made. - Functionality and documentation remain the same as the previous version.

v1.0.44

- Version bump to 1.0.44 with no file changes. - No updates or modifications were made to the skill or documentation in this release.

v1.0.43

- No changes detected in this version. - The SKILL.md file remains the same as the previous version. - No new features, updates, or fixes were introduced.

v1.0.42

No changes detected in this version. - Version 1.0.42 includes no updates or modifications.

v1.0.41

- No visible changes in this version; SKILL.md content remains the same. - No file changes detected.

v1.0.40

- No changes detected in this version. - Functionality, features, and documentation remain the same as the previous release.

v1.0.39

Version 1.0.39 of ad-campaign-optimizer - No file changes detected in this version. - Functionality, features, and documentation remain the same as the previous release.

v1.0.38

- No file changes detected in this version. - Documentation and feature set remain consistent with the previous release.

v1.0.37

Version 1.0.37 - No file changes detected in this release. - All features, documentation, and usage remain unchanged from the previous version.

v1.0.36

No changes detected in this version.

v1.0.35

Version 1.0.35 of ad-campaign-optimizer - No file changes detected in this release. - Skill functionality and documentation remain unchanged.

v1.0.34

- No file changes detected in this version. - All functionality, documentation, and features remain the same as the previous release.

v1.0.32

Version 1.0.32 - No file changes detected in this version. - Functionality and documentation remain unchanged.

元数据

Slug ad-campaign-optimizer

版本 1.0.52

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 26

常见问题