Token导航 LogoToken导航

Agent Skill · 研究检索

campaign-sending(活动发送)

campaign-sending 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。

campaign-sending 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,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 46,384。

总安装 783周安装 32GitHub Stars 93下载 251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:campaign-sending(活动发送)
来源仓库:https://github.com/extruct-ai/gtm-skills
仓库路径:skills/campaign-sending
安装命令:
npx skills add https://github.com/extruct-ai/gtm-skills --skill campaign-sending
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/extruct-ai/gtm-skills --skill campaign-sending

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。

campaign-sending 上传并执行邮件序列发送任务。支持主流邮件服务商 API 对接,处理去重与个性化变量替换。操作流程包含提供商选择、API 学习与正式发送三个阶段。正式发送前务必验证收件人列表与模板合规性。

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/campaign-sending

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/extruct-ai/gtm-skills --skill campaign-sending;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

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

campaign-sending 怎么安装?

在终端执行 npx skills add https://github.com/extruct-ai/gtm-skills --skill campaign-sending。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

campaign-sending 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。

campaign-sending 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

campaign-sending 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。

campaign-sending 用的人多吗?

公开数据是累计安装 783 次,近一周安装 32 次,下载 251 次,GitHub 93 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。

campaign-sending 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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 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。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
campaign-sending

活动发送 · 本页

78393接触敏感数据未明确未通过

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

Run Campaign

Upload finalized emails for sequencing and sending.

Environment

Provider selection and credentials are handled in Step 0 of the workflow.

Workflow

Step 0: Confirm provider and learn API

  1. Ask the user which email sequencing provider they want to use. If they're unsure, pre-configured options with local reference docs are available in references/.
  2. Fetch or read the provider's API documentation and identify:

- Campaign/sequence creation endpoint - Lead upload endpoint and schema - Deduplication options - Custom variable / personalization support - Authentication method and credentials - Throughput limits and upload constraints

  1. Ask for their API credentials and confirm access
  2. Plan the field mapping based on the provider's lead schema and confirm with the user before proceeding

Step 1: Read and analyze final emails

Load the finalized email CSV (output from email-generation). Read the CSV headers to discover all available columns. Verify required columns exist (email, first_name, company_name, company_domain). Identify all content columns (paragraph fields, hypothesis, tier, etc.) that will need to be mapped to the provider's variables.

Step 2: Check DNC list

Read the context file and remove any domains on the DNC list. Report how many were removed.

Step 3: Create or find campaign

Using the chosen provider's API:

  • List existing campaigns
  • Create a new campaign if needed (suggest name based on vertical + date)

Ask the user to specify the campaign based on region and time zone — leads in different regions/time zones should go into separate campaigns so sending schedules align with recipients' local business hours.

Ask the user: use an existing campaign or create a new one?

Step 4: Map fields to provider lead schema

Analyze the CSV headers discovered in Step 1 and create corresponding fields in the provider:

  1. Map email, first_name, last_name, company_name, company_domain to the provider's standard lead fields
  2. For every remaining column in the CSV, create a matching custom variable / personalization field in the provider
  3. Present the full mapping to the user and confirm before uploading

Step 5: Upload leads in batches

Upload via the provider's API in batches (respect rate limits from Step 0). Enable deduplication if the provider supports it.

Report: uploaded count, skipped (dedup) count, total attempted.

Step 6: Pre-send verification checklist

Present this checklist to the user BEFORE they activate the campaign:

## Pre-Send Verification Checklist

Campaign: [name]
Leads uploaded: [N]
Leads skipped (dedup): [N]

### Verify in your sequencer:

- [ ] **Email accounts connected** — at least 2-3 sending accounts are linked and warmed
- [ ] **Sending schedule set** — check timezone, sending hours, daily limits
- [ ] **Email sequence configured** — first email + follow-up(s) are set up in the campaign
- [ ] **Custom variables working** — preview 3-5 emails to confirm {{variables}} render correctly
- [ ] **Unsubscribe link present** — required for compliance
- [ ] **DNC list checked** — confirm no blacklisted domains made it through
- [ ] **Reply handling set** — auto-stop sequence on reply is enabled
- [ ] **Warmup active** — sending accounts have adequate warmup history

### Sample emails to spot-check:

[Show 3 random emails from the upload for the user to visually verify]

Step 7: Remind about manual activation

Never auto-activate a campaign. Always tell the user:

"Leads are uploaded. Please review the campaign in your sequencer, check the sequence and sending settings, then manually activate when ready. I will not start the campaign automatically."

After Sending: Feedback Loop

After the campaign has been running (typically 1-2 weeks), prompt the user to run the feedback loop:

  1. Export results from the sequencer (opens, replies, bounces)
  2. Run context-building in feedback loop mode to update Campaign History
  3. Use results to refine hypotheses and improve future campaigns

API Reference

Pre-configured provider docs in references/ directory. For other providers, docs are fetched during Step 0.

平台分布

Codex

33.73%
按下载量换算85

Claude

33.22%
按下载量换算83

Cursor

18.16%
按下载量换算46

Gemini CLI

9.22%
按下载量换算23

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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