OpenClaw

media-buyer-ads-helper

Support media buying execution for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, and DSP/programmatic with account health checks, bidding efficiency analysis, AB test design, and real-time anomaly monitoring.

danyangliu-sandwichlab0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install danyangliu-sandwichlab/media-buyer-ads-helper

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Media Buyer Helper

Purpose

Core mission:

Evaluate account health and structure quality.
Analyze bid logic and budget allocation efficiency.
Design AB test architecture and scale model.
Monitor campaigns in real time and detect anomalies.

When To Trigger

Use this skill when the user asks for:

media buyer execution support
bid and budget efficiency diagnostics
AB testing structure design
live campaign watch and anomaly alerts

High-signal keywords:

media, bidding, budget, auction, allocation
abtest, campaign, performance, optimize
cpa, roas, scale, monitor

Input Contract

Required:

account_structure_snapshot
bidding_config
budget_allocation_snapshot
recent_performance_series

Optional:

test_history
alert_thresholds
creative_breakdowns
seasonality_notes

Output Contract

Account Health and Structure Score
Bid and Budget Efficiency Findings
AB Test Structure Blueprint
Scale Model with Trigger Conditions
Monitoring and Alert Rules

Workflow

Check account hierarchy and naming hygiene.
Evaluate bid strategy vs KPI objective.
Diagnose budget fragmentation and overlap.
Build AB test matrix with clear success metrics.
Define anomaly thresholds and response playbook.

Decision Rules

If structure complexity is high and spend is low, simplify before adding tests.
If CPA variance is high, reduce concurrent experiments.
If winning cells are statistically weak, extend learning window.
If anomaly severity is high, prioritize containment over optimization.

Platform Notes

Primary scope:

Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, DSP/programmatic

Platform behavior guidance:

Map bid logic to channel auction mechanics.
Keep test isolation strict to avoid cross-cell contamination.

Constraints And Guardrails

Do not claim statistical significance without threshold checks.
Avoid broad budget jumps without gate conditions.
Keep alert rules tied...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/danyangliu-sandwichlab/media-buyer-ads-helper
Version: —
Commit: c528c7ef3d6671e4dafbb2da0b89c868a8ef381d
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Media Buyer Helper

## Purpose
Core mission:
- Evaluate account health and structure quality.
- Analyze bid logic and budget allocation efficiency.
- Design AB test architecture and scale model.
- Monitor campaigns in real time and detect anomalies.

## When To Trigger
Use this skill when the user asks for:
- media buyer execution support
- bid and budget efficiency diagnostics
- AB testing structure design
- live campaign watch and anomaly alerts

High-signal keywords:
- media, bidding, budget, auction, allocation
- abtest, campaign, performance, optimize
- cpa, roas, scale, monitor

## Input Contract
Required:
- account_structure_snapshot
- bidding_config
- budget_allocation_snapshot
- recent_performance_series

Optional:
- test_history
- alert_thresholds
- creative_breakdowns
- seasonality_notes

## Output Contract
1. Account Health and Structure Score
2. Bid and Budget Efficiency Findings
3. AB Test Structure Blueprint
4. Scale Model with Trigger Conditions
5. Monitoring and Alert Rules

## Workflow
1. Check account hierarchy and naming hygiene.
2. Evaluate bid strategy vs KPI objective.
3. Diagnose budget fragmentation and overlap.
4. Build AB test matrix with clear success metrics.
5. Define anomaly thresholds and response playbook.

## Decision Rules
- If structure complexity is high and spend is low, simplify before adding tests.
- If CPA variance is high, reduce concurrent experiments.
- If winning cells are statistically weak, extend learning window.
- If anomaly severity is high, prioritize containment over optimization.

## Platform Notes
Primary scope:
- Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, DSP/programmatic

Platform behavior guidance:
- Map bid logic to channel auction mechanics.
- Keep test isolation strict to avoid cross-cell contamination.

## Constraints And Guardrails
- Do not claim statistical significance without threshold checks.
- Avoid broad budget jumps without gate conditions.
- Keep alert rules tied...

搜索