← Back to Skills Marketplace
Ads ROAS Forecast
by
danyangliu
· GitHub ↗
· v1.0.0
318
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install roas-forecast-attribution-modeler
Description
Build ROAS forecasting and attribution-model assumptions for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP...
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install roas-forecast-attribution-modeler - After installation, invoke the skill by name or use
/roas-forecast-attribution-modeler - Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Frequently Asked Questions
What is Ads ROAS Forecast?
Build ROAS forecasting and attribution-model assumptions for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP... It is an AI Agent Skill for Claude Code / OpenClaw, with 318 downloads so far.
How do I install Ads ROAS Forecast?
Run "/install roas-forecast-attribution-modeler" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ads ROAS Forecast free?
Yes, Ads ROAS Forecast is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Ads ROAS Forecast support?
Ads ROAS Forecast is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ads ROAS Forecast?
It is built and maintained by danyangliu (@danyangliu-sandwichlab); the current version is v1.0.0.
More Skills