Token导航 LogoToken导航TokenDH.com
开发操作浏览器clawhub未标认证来源可访问clear审计通过

new-visitor-cold-startNEW visitor cold start 开发

Agent Skill

new-visitor-cold-start 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。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。

总安装

6,750

周安装

287

GitHub Stars

公开资料未说明

下载量

2,365
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:new-visitor-cold-start(NEW visitor cold start 开发)
来源仓库:https://github.com/rijoyai/new-visitor-cold-start
安装命令:
openclaw skills install new-visitor-cold-start
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 new-visitor-cold-start

简介

使用基于行为的细分来转化首次访问者,通过退出意图和定时弹出窗口提供有针对性的一阶优惠,以实现更高的转化。

SKILL.md

name
new-visitor-cold-start
description
Convert first-time store visitors with behavior-based personalization — browse path → preference segment → matched first-order incentive → popup timing including exit intent. Use when the user wants cold-start offers for new visitors, first-purchase coupons tied to what they viewed, exit-intent or timed modals, or onboarding for anonymous traffic before email capture. Steps baked in: monitor path, classify preference, match first-order voucher or gift, set trigger (exit intent and alternatives). Do NOT use for loyalty win-back of existing customers only, post-purchase flows with no first-visit lens, or legal-only coupon policy with no behavioral targeting ask.
compatibility
required
[]

New visitor cold-start conversion

You turn first session behavior into a single high-fit first-order offer and clear modal timing so new visitors convert without generic blasts.

Core workflow (always in order)

  1. Monitor browse path — Pages viewed, sequence, time on category/PDP, scroll depth proxy (if described), cart add without checkout.
  2. Classify user preference — Segment from path (e.g. category A explorer, price-sensitive browser, single-SKU deep dive, bouncer on shipping page).
  3. Match first-order offer — Code or auto-apply; type (%, fixed, gift, free ship) aligned to segment; guardrails (min order, exclusions).
  4. Set popup / push timingExit intent primary; backups (seconds on PDP, second category view, cart abandon on first visit).

Gather context

  1. Catalog categories and margin-safe discount bands.
  2. Stack rules with other promos.
  3. Compliance: new-customer definition, consent for popup/email.

Read references/cold_start_playbook.md for segment → offer → trigger map.

Mandatory outputs (full run)

A) Path → segment table

Observed path patternPreference labelRationale
e.g. 3 PDPs same categoryCategory intent
e.g. cart + shipping pageShipping sensitivity

B) Segment → first-order offer

SegmentFirst-order offerMin order / notes

C) Trigger spec

TriggerWhenCopy role
Exit intentMouse leave viewport / mobile back intent proxySave offer + urgency light
Backup 1e.g. 25s on PDPDeep interest
Backup 2e.g. second collection viewBroad interest

Include one modal headline + subline + CTA per primary segment (or one adaptive template with dynamic category name).

Pushy when vague

If user only says "better first-time conversion," still deliver one full row chain: path example → segment → offer → exit-intent line.

When NOT to use

  • Repeat-customer-only campaigns.
  • No first-visit or anonymous context.

Split with other skills

  • LTV win-back — lapsed buyers; this skill is first session.
  • Cart bundle AOV — add-ons; this skill is cold start + first order.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

91.73%
按下载量换算2,169

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills