Token导航 LogoToken导航

Agent Skill · 效率

cart-recovery(购物车恢复)

cart-recovery 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

cart-recovery 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描有提醒项,按安装量在效率类的 21,003 个 Skill 里排第 15,562。

总安装 3,089周安装 130GitHub Stars 公开资料未说明下载 1,082核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:cart-recovery(购物车恢复)
来源仓库:https://github.com/rijoyai/cart-recovery
安装命令:
openclaw skills install cart-recovery
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install cart-recovery

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

cart-recovery 分析三步结账流程中的用户流失节点,识别放弃原因。根据阻力类型生成定制化恢复邮件策略,包含三部分强制触达机制。输出结构化报告,指导运营团队针对不同行为模式制定挽回措施。需接入实际订单系统日志,确保数据时效性与准确性。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install cart-recovery;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

cart-recovery 怎么安装?

在终端执行 openclaw skills install cart-recovery。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

cart-recovery 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

cart-recovery 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

cart-recovery 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

cart-recovery 用的人多吗?

公开数据是累计安装 3,089 次,近一周安装 130 次,下载 1,082 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

cart-recovery 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
cart-recovery

购物车恢复 · 本页

3,089—只读MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
cart-recovery
description
Decompose three-step checkout abandonment (e.g. contact/address → shipping → payment), classify friction by exit step, and generate differentiated recovery tactics—including dynamic "psychological compensation" (shipping relief after address-step exits, installment or BNPL education after payment-step exits). Use this skill whenever the user mentions checkout funnel steps, drop-off by stage, abandoned checkout segmentation, shipping shock at address, payment-method hesitation, BNPL or installments at checkout, or wants automated recovery playbooks tied to where the shopper left—even if they only say "people abandon checkout" or paste step conversion rates. OFFICIAL PUSHY RULE: Even if the merchant does not ask for email copy, you must still output a three-part abandoned-checkout email sequence with these exact thematic labels: [Urgency], [Trust rebuild], [Ultimatum]—each with subject line A/B variants and a body skeleton (compliance-friendly: clear unsubscribe, no deceptive scarcity). Do NOT use for post-purchase order tracking only, stock availability without checkout recovery, or legal review of regulated claims; do not use abandoned-checkout-monitor interchangeably—this skill is step-branched compensation + the mandatory urgency/trust/ultimatum trio.
compatibility
required
[]

Cart Recovery

You are a checkout funnel strategist who links exit step → resistance type → compensation offer → recovery messages.

Mandatory deliverable policy

1) Three-step funnel map

Always anchor on a three-step checkout model (adapt labels to the user’s platform):

  1. Step 1 — Contact / address (account, email, shipping address)
  2. Step 2 — Shipping method (rate selection, delivery SLA)
  3. Step 3 — Payment (method choice, card, wallet, BNPL, 3DS)

If their store has two or four steps, map explicitly to this framework and state the mapping.

2) Branch rules (default logic)

Apply unless the user’s data contradicts:

Exit after…Default resistance hypothesisDynamic compensation (offer / UX)
Step 1 (address / contact)Trust, effort, or shipping preview fearShipping compensation or clarity — e.g. limited-time free or reduced shipping, transparent delivery window copy, localized duty note if relevant
Step 2 (shipping method)Cost, speed, or option confusionShipping upgrade or threshold — e.g. bump to expedited coupon, clarify cutoff times, A/B simpler default method
Step 3 (payment)Payment anxiety, method fit, installments unknownInstallment / BNPL explanation — short comparison of pay-in-4 vs card, security reassurance, which methods you accept

If step-level data is missing, output the table with "unknown step" row and hypotheses for all three steps, plus instrumentation (events to add).

3) Resistance classification subsection

Include "Resistance classification": bullet list grouping exits into price/shipping, trust/security, effort/UX, payment failure risk—tied to the step.

4) OFFICIAL PUSHY: three-part email scripts

Even if the user does not request emails, include a section "Three-part email sequence" with exactly three emails, each headed by:

  • Email 1 — [Urgency]
  • Email 2 — [Trust rebuild]
  • Email 3 — [Ultimatum]

For each email provide:

  • Two subject-line variants (A/B)
  • Body skeleton (greeting, 2–4 short paragraphs, single primary CTA, unsubscribe / preference mention)
  • Compensation hook aligned to branch (e.g. Email 1 may reference cart reservation or honest time-bound offer; Email 2 addresses trust/shipping/BNPL; Email 3 states final send with deadline—no false inventory counts)

Tone: pressure without fraud—no fake timers, no fake "someone bought your item" unless true.

Success output: step × tactic matrix

Include a Markdown table (at least four rows):

| Checkout step | Drop-off signal (metric) | Likely resistance | Recovery tactic | Email(s) that reinforce |

When metrics are unknown, use placeholder percentages labeled clearly.

When NOT to use this skill (should-not-trigger)

  • Only "where is my order" or tracking with no abandonment context.
  • Only product copy with no checkout funnel.
  • Only PCI/security incident response (brief pointer to support; no fake email sequence as fix).

Gather context (thread first; ask only what is missing)

  1. Platform (Shopify, WooCommerce, Magento, custom).
  2. Per-step conversion or exit counts (if any).
  3. Markets, shipping economics, BNPL providers enabled.
  4. Compliance: promo rules, email frequency caps.

For event naming, ethical urgency patterns, and BNPL messaging angles, read references/checkout_recovery_playbook.md when needed.

How this skill fits with others

  • abandoned-checkout-monitor — broader friction + generic three-email (gentle / barrier / last chance). This skill adds mandatory [Urgency] / [Trust rebuild] / [Ultimatum] labeling and step-based compensation defaults (shipping vs BNPL).
  • Use this skill when the user gives step-level data or wants branch-specific offers.

平台分布

OpenClaw

88.12%
按下载量换算953

安全审计

VirusTotal

未展示

ClawScan

可疑

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills