← 返回 Skills 市场
rijoyai

Cart Recovery

作者 RIJOY-AI · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
105
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cart-recovery
功能描述
Analyzes three-step checkout abandonment by exit step, classifies shopper resistance, and generates tailored recovery tactics plus a mandatory three-part ema...
使用说明 (SKILL.md)

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 hypothesis Dynamic compensation (offer / UX)
Step 1 (address / contact) Trust, effort, or shipping preview fear Shipping 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 confusion Shipping 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 unknown Installment / 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.
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 cart-recovery
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cart-recovery 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
v1.0.0
cart-recovery v1.0.0 — Launch with step-based checkout abandonment diagnosis and required three-part recovery email sequence. - Maps any checkout to a standardized three-step model (contact/address, shipping, payment); handles mapping if user flow differs. - Diagnoses abandonment causes by step, and prescribes targeted compensation (shipping relief, shipping upgrade, BNPL/installment education). - Always outputs a detailed resistance classification and step × tactic matrix—including hypotheses when step data is missing. - Mandates generation of a three-part recovery email sequence: [Urgency], [Trust rebuild], [Ultimatum], each with A/B subject lines and compliant body skeletons—even if not explicitly requested. - Distinguishes itself from generic approaches by requiring explicit branch logic and theming in recovery flows. - Clearly specifies when not to trigger (e.g., order tracking inquiries only, non-funnel contexts).
元数据
Slug cart-recovery
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Cart Recovery 是什么?

Analyzes three-step checkout abandonment by exit step, classifies shopper resistance, and generates tailored recovery tactics plus a mandatory three-part ema... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 105 次。

如何安装 Cart Recovery?

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

Cart Recovery 是免费的吗?

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

Cart Recovery 支持哪些平台?

Cart Recovery 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 Cart Recovery?

由 RIJOY-AI(@rijoyai)开发并维护,当前版本 v1.0.0。

💬 留言讨论