← 返回 Skills 市场
leooooooow

Win-Back Campaign

作者 LeroyCreates · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
91
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install win-back-campaign
功能描述
Design automated win-back campaigns targeting lapsed customers with personalized re-engagement sequences across email, SMS, and paid ads, using recency-based...
安全使用建议
This skill appears to be a legitimate operational playbook for win-back campaigns, but it asks the operator to access and move sensitive customer data and interact with multiple external services while declaring no required credentials. Before installing or running it: (1) verify exactly which credentials and API keys are needed and supply them with least-privilege (read-only where possible, limited ad audiences only); (2) ensure PII/consent requirements are met (explicit SMS opt-in, lawful basis for EU contacts, hashed or consented email uploads to ad platforms); (3) restrict any agent or automation that will execute these steps to a sandbox or test audience first and require manual approval for audience uploads and paid spend; (4) require audit logging for any data exports/uploads and review logs regularly; (5) confirm suppression lists, unsubscribe handling, and deletion requests are honored automatically; and (6) if you cannot confirm which systems/endpoints the skill will call or what credentials it will use, treat it as untrusted — do not provide broad API keys or service accounts until the missing details are clarified.
功能分析
Type: OpenClaw Skill Name: win-back-campaign Version: 1.1.0 The 'Win-Back Campaign' skill bundle provides comprehensive documentation and instructions for an AI agent to design and execute ecommerce re-engagement strategies. It covers data-driven RFM segmentation, multi-channel orchestration (email, SMS, and paid ads), and performance measurement using holdout groups. The instructions are professionally written, align strictly with the stated marketing purpose, and include significant emphasis on legal compliance (GDPR, TCPA, CAN-SPAM) and deliverability safety. No malicious code, data exfiltration attempts, or harmful prompt injections were identified in SKILL.md or the supporting guides.
能力标签
cryptocan-make-purchases
能力评估
Purpose & Capability
The name, description, SKILL.md, and supplemental guides all consistently describe designing and executing RFM-based multi-channel win-back campaigns; included templates and checklists line up with that purpose and there are no unexpected binaries or install steps.
Instruction Scope
The instructions direct the agent/operator to pull order history, calculate RFM, access ESP/SMS/CRM/analytics data, remove suppressed contacts, upload audiences to ad platforms, and coordinate cross-channel suppression. Those actions involve reading/transmitting PII and interacting with third‑party ad/ESP APIs. The SKILL.md grants broad, operational discretion (data pulls, audience uploads, frequency caps, suppression logic) but does not precisely constrain what systems, endpoints, or data may be accessed — increasing the risk of accidental or intentional data exposure.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest installation risk (nothing is written or executed by the skill itself).
Credentials
Registry metadata lists no required env vars or credentials, yet the instructions implicitly require API keys/credentials for ESPs, SMS providers, CRM/ecommerce DB access, ad platforms, and possibly server-side CAPI endpoints. That mismatch (no declared credentials but clear need for multiple sensitive credentials) is a proportionality and transparency issue and should be clarified before use.
Persistence & Privilege
The skill does not request 'always: true' or persistent system-level presence and has no install steps that modify agent/system config. It allows normal autonomous invocation (platform default), which increases blast radius only if combined with the other concerns above.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install win-back-campaign
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /win-back-campaign 触发
  4. 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
v1.1.0
**Summary: Adds comprehensive documentation resources and supporting guides.** - Introduced four new supporting documents: channel-strategy-guide.md, output-template.md, quality-checklist.md, and segmentation-guide.md. - Expanded practical resources for campaign design, execution, and quality assurance. - Enables easier reference for best practices in segmentation, channel orchestration, and expected output. - Aims to improve campaign consistency and end-user implementation confidence.
v1.0.0
Initial release.
元数据
Slug win-back-campaign
版本 1.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Win-Back Campaign 是什么?

Design automated win-back campaigns targeting lapsed customers with personalized re-engagement sequences across email, SMS, and paid ads, using recency-based... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 91 次。

如何安装 Win-Back Campaign?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install win-back-campaign」即可一键安装,无需额外配置。

Win-Back Campaign 是免费的吗?

是的,Win-Back Campaign 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Win-Back Campaign 支持哪些平台?

Win-Back Campaign 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 Win-Back Campaign?

由 LeroyCreates(@leooooooow)开发并维护,当前版本 v1.1.0。

💬 留言讨论