Token导航 LogoToken导航

Agent Skill · 研究检索

bounce-monitoring-workflow(弹跳监控工作流程)

bounce-monitoring-workflow 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

bounce-monitoring-workflow 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 71,089。

总安装 196周安装 8GitHub Stars 14下载 63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
unknown

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:bounce-monitoring-workflow(弹跳监控工作流程)
来源仓库:https://github.com/tomgranot/hubspot-admin-skills
仓库路径:skills/bounce-monitoring-workflow
安装命令:
npx skills add https://github.com/tomgranot/hubspot-admin-skills --skill bounce-monitoring-workflow
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/tomgranot/hubspot-admin-skills --skill bounce-monitoring-workflow

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

bounce-monitoring-workflow 提供邮件弹跳检测和抑制功能,保护发件人信誉。适用场景包括硬弹跳警报、自动抑制和手动审查,确保营销邮件的稳定性和有效性。核心能力包括条件触发、行动执行和阈值管理,适用于 HubSpot Marketing Professional 或更高版本。

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。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/bounce-monitoring-workflow

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/tomgranot/hubspot-admin-skills --skill bounce-…;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

bounce-monitoring-workflow 怎么安装?

在终端执行 npx skills add https://github.com/tomgranot/hubspot-admin-skills --skill bounce-monitoring…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bounce-monitoring-workflow 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

bounce-monitoring-workflow 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。

bounce-monitoring-workflow 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

bounce-monitoring-workflow 用的人多吗?

公开数据是累计安装 196 次,近一周安装 8 次,下载 63 次,GitHub 14 星。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。

bounce-monitoring-workflow 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 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

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、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

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
bounce-monitoring-workflow

弹跳监控工作流程 · 本页

19614只读未明确通过

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

Bounce Monitoring Workflow

Protect your email sender reputation with automated bounce detection and suppression. This workflow catches bounces as they happen rather than waiting for periodic cleanup.

How It Works

ConditionAction
Hard bounce detectedAlert admin immediately, suppress contact
Suppression threshold reached (commonly 2-3 bounces)Auto-suppress from marketing emails
Review threshold reached (commonly 3-5 bounces)Flag for weekly manual review (delete vs. recover)

Prerequisites

  • HubSpot Marketing Professional or Enterprise plan
  • A custom contact property (e.g., email_health_flag or delivery_status) — checkbox or dropdown with value: "flagged for review"
  • Admin email or Slack channel for hard bounce alerts

Building the Workflow: Three Options

Option 1: Manual UI Build

Follow the step-by-step instructions in the "Execute" section below. This is the most reliable method and gives you full control over every trigger, branch, and action.

Option 2: HubSpot Breeze AI

HubSpot's built-in Breeze AI can generate a workflow skeleton from a natural language prompt. Navigate to Automation > Workflows > Create workflow > "Describe what you want" and paste the following prompt:

Create a contact-based workflow that triggers when the "Email Bounce" property
is known (has a value). The workflow should:

1. First, check if the contact has a hard bounce reason (hard_bounce_reason is known):
   - If YES: send an internal notification saying "Hard bounce: [email]" and set the
     contact as a non-marketing contact
   - If NO: continue to the next check

2. Check if the bounce count is greater than or equal to [your suppression threshold, commonly 2-3]:
   - If YES: set the contact as a non-marketing contact, then check if bounce count
     is >= [your review threshold, commonly 3-5]. If so, set a custom property
     "[your bounce review property]" to "flagged" and send an internal notification
     saying "Contact [email] has [review threshold]+ bounces - review for deletion"
   - If NO: end (below threshold, monitor only)

Enable re-enrollment so the contact re-enters if their bounce count increases.

CRITICAL WARNING: Breeze trigger limitations. Breeze creates event-based triggers (OR logic) instead of filter-based triggers (AND logic). After Breeze creates the workflow, you MUST manually verify and fix the trigger/enrollment conditions in the UI. Breeze is best used for creating the workflow skeleton (actions, branches, delays) -- the trigger conditions almost always need manual correction.

Additional Breeze limitations for this workflow:

  • Breeze cannot create "is unknown" branch conditions -- you must verify that branch conditions checking for hard bounce reason are correctly configured
  • Breeze cannot configure re-enrollment rules -- you must enable re-enrollment manually
  • Breeze may flatten the nested branch structure (hard bounce check > 2+ bounces > 3+ bounces) into a single level

Option 3: Claude Anthropic Chrome Extension

The Claude Anthropic Chrome extension lets Claude see and interact with the HubSpot workflow builder UI directly. You can describe the workflow logic in natural language and Claude will click through the UI to build it. This is often more accurate than Breeze for workflows with nested branching logic (this workflow has three levels of branches), because Claude can verify the branch hierarchy visually.

To use this approach:

  1. Open the HubSpot workflow builder in Chrome (Automation > Workflows > Create workflow)
  2. Activate the Claude Chrome extension
  3. Describe the workflow using the design table and instructions from this skill
Note on Fast Mode: If you're using Claude Code's Fast Mode to speed up workflow creation, be aware of the billing model: Haiku usage is included in your subscription, but Opus in Fast Mode consumes extra credits. For workflow building tasks (which are UI-heavy and may require many interactions), consider whether the speed tradeoff is worth the credit cost.

Step-by-Step Build Instructions

Stage 1: Before — Create Properties

  1. Create your bounce review property (e.g., email_health_flag or delivery_status):

- Object: Contact - Type: Single checkbox or dropdown - Group: Contact information

  1. Identify your current bounce baseline — run a quick search for contacts where hs_email_bounce > 0 to understand the starting volume.

Stage 2: Execute — Build the Workflow

Build a single contact-based workflow with branching logic.

  1. Trigger: hs_email_bounce is known (fires when bounce count updates)
  2. Branch 1: Hard bounce check

- Condition: hs_email_hard_bounce_reason_enum is known - YES: - Send internal notification: "Hard bounce: {email} — {hs_email_hard_bounce_reason_enum}" - Set hs_marketable_status to non-marketing (workflow action) - NO: Continue to Branch 2

  1. Branch 2: Bounce count >= your suppression threshold (commonly 2-3)

- Condition: hs_email_bounce is greater than or equal to your suppression threshold - YES: - Set hs_marketable_status to non-marketing (workflow action) - Continue to Branch 3 - NO: No action (below threshold — monitor only)

  1. Branch 3: Bounce count >= your review threshold (commonly 3-5)

- Condition: hs_email_bounce is greater than or equal to your review threshold - YES: - Set your bounce review property = flagged - Send internal notification: "Contact {email} has [review threshold]+ bounces — review for deletion" - NO: No further action

  1. Settings:

- Re-enrollment: ON (contact should re-enter if bounce count increases) - Goal: None

  1. Turn on the workflow.

Stage 3: After — Verify

  1. Check workflow history after the first week of email sends.
  2. Review the flagged contacts list weekly — decide for each contact:

- Delete if the email is clearly invalid (typo domain, defunct company) - Attempt recovery if the domain is valid (could be a temporary mailbox issue)

  1. Monitor overall bounce rate in HubSpot email health dashboard.

Stage 4: Rollback

  1. Turn off the workflow.
  2. Contacts already suppressed remain non-marketing. To reverse:

- Filter contacts suppressed by this workflow (check your bounce review property or workflow history) - Manually set back to marketing contacts in the UI

  1. Clear your bounce review property values in bulk if needed.

Weekly Review Process

For contacts flagged at your review threshold:

  1. Export the flagged contacts list.
  2. For each contact, check:

- Is the email domain still active? (Quick MX record check) - Is this a known customer or high-value contact? - Was the bounce recent or historical?

  1. Delete contacts with invalid domains or clearly fake emails.
  2. Keep suppressed contacts with valid domains but repeated soft bounces.
  3. Clear the bounce review property after review.

平台分布

Codex

36.42%
按下载量换算23

Claude

27.38%
按下载量换算17

Cursor

17.76%
按下载量换算11

Gemini CLI

10.07%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。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