← 返回 Skills 市场
Ads ROAS Forecast
作者
danyangliu
· GitHub ↗
· v1.0.0
318
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install roas-forecast-attribution-modeler
功能描述
Build ROAS forecasting and attribution-model assumptions for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP...
安全使用建议
This skill appears coherent and minimal-risk because it's instruction-only and requests no credentials or installs. Before using it: (1) never paste ad-account credentials, API keys, or raw PII into prompts — provide only aggregated metrics and modeled assumptions; (2) ask the skill author or maintainer to clarify what the "structured handoff payload" contains and where it would be sent if the skill escalates an issue; (3) validate outputs on a small, controlled budget before acting on recommendations; (4) treat forecast results as decision support — confirm assumptions, monitor live performance, and implement explicit stop-loss controls; (5) if you plan to automate actions (e.g., via APIs), ensure the automation layer and endpoints are audited and authorised separately. Overall the skill is internally consistent, but safe usage depends on how you supply inputs and whether you connect it to automation or external endpoints.
功能分析
Type: OpenClaw Skill
Name: roas-forecast-attribution-modeler
Version: 1.0.0
The skill bundle is benign. All files contain standard metadata and instructions for an AI agent focused on ROAS forecasting and attribution modeling. The `SKILL.md` explicitly includes 'Constraints And Guardrails' that prevent fabrication of metrics, promote separation of facts from assumptions, and require rollback conditions for spend risk, indicating a strong intent for responsible behavior. There is no evidence of prompt injection, data exfiltration, malicious execution, or any other harmful activities.
能力评估
Purpose & Capability
Name, description, required inputs (forecast_target, planning_horizon, base_assumptions) and the outlined workflow are consistent with an ad forecasting/attribution planner. There are no unexpected requirements (no cloud creds, no unrelated binaries) that would be disproportionate to the stated purpose.
Instruction Scope
SKILL.md stays within modeling, scenarios, sensitivity analysis, and platform guidance. It does include a line about "escalate with a structured handoff payload" for high-risk issues but does not specify destinations or endpoints — this is ambiguous but not inherently malicious. Recommend clarifying where handoff payloads are sent and what data is included.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes on-disk risk and there are no external downloads or package installs.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not ask for unrelated secrets or system access and its declared inputs are reasonable for forecasting tasks.
Persistence & Privilege
Skill is not always-enabled and does not request persistent presence or modifications to other skills. Autonomous invocation is permitted (the platform default) but there are no additional privileges requested.
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 roas-forecast-attribution-modeler - 安装完成后，直接呼叫该 Skill 的名称或使用
/roas-forecast-attribution-modeler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
Initial release of the ROAS Forecast Attribution Modeler skill.
- Provides actionable ROAS forecasting and attribution modeling for major ad platforms (Meta, Google, TikTok, YouTube, Amazon, Shopify, DSP).
- Supports scenario planning, attribution sensitivity analysis, and budget recommendations tailored to each channel.
- Outlines explicit input/output contracts, workflow steps, and decision rules for ad-focused forecasting tasks.
- Includes platform-specific guidance and guardrails (e.g., creative testing for Meta/TikTok, intent-driven actions for Google/Amazon).
- Delivers failure handling, rollback criteria, and clear example cases for practical use.
元数据
常见问题
Ads ROAS Forecast 是什么？
Build ROAS forecasting and attribution-model assumptions for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 318 次。
如何安装 Ads ROAS Forecast？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install roas-forecast-attribution-modeler」即可一键安装，无需额外配置。
Ads ROAS Forecast 是免费的吗？
是的，Ads ROAS Forecast 完全免费（开源免费），可自由下载、安装和使用。
Ads ROAS Forecast 支持哪些平台？
Ads ROAS Forecast 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 Ads ROAS Forecast？
由 danyangliu（@danyangliu-sandwichlab）开发并维护，当前版本 v1.0.0。
推荐 Skills