← 返回 Skills 市场
CMO Helper
作者
danyangliu
· GitHub ↗
· v1.0.0
290
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cmo-ads-helper
功能描述
Support CMO-level planning across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP/programmatic with revenue,...
使用说明 (SKILL.md)
CMO Helper
Purpose
Core mission:
- Parse top-level business goals (revenue, profit, cashflow) into executable growth paths.
- Simulate budget allocation and channel structure with ROAS and LTV forecasts.
- Produce quarterly and annual growth strategy with risk alerts.
- Generate board-ready growth reports.
When To Trigger
Use this skill when the user asks for:
- annual or quarterly growth planning
- high-level budget allocation by channel
- ROAS/LTV forecast and risk evaluation
- CMO report narratives for leadership updates
High-signal keywords:
- growth, revenue, profit, roi, roas, ltv
- ads, media, campaign, forecast, model, allocation
- strategy, budget, dashboard, report, predict
Input Contract
Required:
- business_targets: revenue_target, profit_target, cashflow_target
- planning_horizon: quarter or year
- budget_pool: total budget and flexibility range
- current_mix: channel spend and KPI baseline
Optional:
- market_constraints
- hiring_or_resource_limits
- inventory_or_supply_constraints
- risk_tolerance
Output Contract
- Executive Goal Decomposition
- Growth Path by Quarter (or month)
- Channel Allocation Simulation (base/upside/downside)
- ROAS/LTV Forecast Assumptions and outputs
- Risk Radar and Mitigation Plan
- CMO Report Outline
Workflow
- Normalize top goals into quantifiable KPI tree.
- Build growth path candidates by objective priority.
- Simulate channel budget structure under multiple scenarios.
- Forecast ROAS and LTV under attribution assumptions.
- Flag risks and attach mitigation owners.
- Export leadership-ready summary.
Decision Rules
- If cashflow is constrained, prioritize payback speed over max scale.
- If profit target conflicts with growth target, optimize blended margin first.
- If uncertainty is high, widen confidence ranges and use staged budget release.
- If one channel dominates risk, cap exposure and add redundancy channels.
Platform Notes
Primary scope:
- Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, DSP/programmatic
Platform behavior guidance:
- Meta/TikTok: fast learning via creative breadth.
- Google/Amazon: demand-capture and intent-driven efficiency.
- DSP: incremental reach and controlled frequency.
Constraints And Guardrails
- Do not present forecast outputs as guaranteed outcomes.
- Separate assumptions, historical facts, and modeled estimates.
- Keep all recommendations linked to measurable KPI deltas.
Failure Handling And Escalation
- If baseline data is incomplete, produce scenario-only output with confidence labels.
- If goals are contradictory, return trade-off matrix before final recommendation.
- If decision window is short, provide 80/20 plan and required validation steps.
Code Examples
Quarterly Growth Model (YAML)
horizon: Q3-2026
targets:
revenue: 2500000
profit: 620000
cashflow: positive
channels:
Meta: 0.35
GoogleAds: 0.30
TikTokAds: 0.15
AmazonAds: 0.10
DSP: 0.10
Forecast Table Schema (JSON)
{
"scenario": "base",
"blended_roas": 2.9,
"projected_ltv": 145,
"risk_level": "medium"
}
Examples
Example 1: Quarterly board plan
Input:
- Need Q3 growth plan with profit floor
Output focus:
- channel budget simulation
- risk warnings
- executive summary points
Example 2: Annual strategy reset
Input:
- Revenue target increased by 40%
- Cashflow pressure exists
Output focus:
- staged growth roadmap
- payback-sensitive allocation
- guardrails
Example 3: Budget cut scenario
Input:
- Spend reduced by 20%
- KPI targets unchanged
Output focus:
- re-prioritization logic
- expected trade-offs
- mitigation actions
Quality Checklist
- Required sections are complete and non-empty
- Trigger keywords include at least 3 registry terms
- Input and output contracts are operationally testable
- Workflow and decision rules are capability-specific
- Platform references are explicit and concrete
- At least 3 practical examples are included
安全使用建议
This skill appears coherent and low-risk as an offline CMO planning helper. Before using: (1) avoid pasting real platform API keys or other secrets into free-text inputs — the skill does not need them; (2) verify inputs (revenue, baseline KPIs) are accurate because outputs are model-driven estimates, not guaranteed outcomes; (3) if you later enable live integrations with ad platforms, expect explicit credential requests and review them carefully; (4) treat forecasts as decision-support, validate with your analytics stack before acting. If you want the skill to pull live campaign data, request documentation on how it plans to authenticate and which endpoints it will call.
功能分析
Type: OpenClaw Skill
Name: cmo-ads-helper
Version: 1.0.0
The skill bundle contains standard metadata and a `SKILL.md` file that clearly defines the purpose, triggers, inputs, outputs, workflow, and decision rules for a CMO ad planning helper. There are no indications of prompt injection attempts against the AI agent, unauthorized command execution, data exfiltration, or any other malicious activities. In fact, the `SKILL.md` includes explicit 'Constraints And Guardrails' that promote responsible and transparent AI behavior, such as not presenting forecasts as guaranteed outcomes and separating assumptions from facts.
能力评估
Purpose & Capability
Name/description (CMO-level planning across ad channels) matches the SKILL.md: it asks for business targets, budget, current mix and describes simulation, forecasting, and reporting tasks. There are no unrelated environment variables, binaries, or platform credentials requested that would be disproportionate.
Instruction Scope
SKILL.md contains only modeling, decision rules, scenario workflows, examples, and output contracts. It does not instruct the agent to read local files, access system configuration, call external endpoints, or exfiltrate data. All instructions stay within the declared planning/reporting scope.
Install Mechanism
No install spec is provided (instruction-only). Nothing is written to disk or downloaded, which minimizes install-time risk.
Credentials
The skill declares no required env vars, no primary credential, and no config path access. That is proportionate to an offline modeling/reporting tool that uses user-supplied inputs.
Persistence & Privilege
always:false and user-invocable:true (defaults) — the skill does not request permanent/global presence or attempt to modify other skills or system-wide settings. Autonomous invocation is allowed by platform default but is not combined here with other red flags.
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 cmo-ads-helper - 安装完成后,直接呼叫该 Skill 的名称或使用
/cmo-ads-helper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
v1.0.0
cmo-ads-helper v1.0.0
- Initial release providing CMO-level planning support across Meta, Google, TikTok, YouTube, Amazon, Shopify, and DSP/programmatic ad channels.
- Translates top-line business targets (revenue, profit, cashflow) into actionable growth paths with ROI, ROAS, and LTV modeling.
- Features simulation of budget allocation, risk radar, channel scenario planning, and growth strategy output.
- Delivers board-ready reports and leadership summaries for quarterly or annual planning.
- Includes robust input/output contracts, high-signal trigger keywords, decision rules, and practical implementation examples.
元数据
常见问题
CMO Helper 是什么?
Support CMO-level planning across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP/programmatic with revenue,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 290 次。
如何安装 CMO Helper?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cmo-ads-helper」即可一键安装,无需额外配置。
CMO Helper 是免费的吗?
是的,CMO Helper 完全免费(开源免费),可自由下载、安装和使用。
CMO Helper 支持哪些平台?
CMO Helper 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 CMO Helper?
由 danyangliu(@danyangliu-sandwichlab)开发并维护,当前版本 v1.0.0。
推荐 Skills