Back to Details

cold-outbound-optimizer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Preamble (runs on skill start)

前置流程（skill启动时自动运行）

bash
undefined
bash
undefined

Version check (silent if up to date)

Version check (silent if up to date)

python3 telemetry/version_check.py 2>/dev/null || true
python3 telemetry/version_check.py 2>/dev/null || true

Telemetry opt-in (first run only, then remembers your choice)

Telemetry opt-in (first run only, then remembers your choice)

python3 telemetry/telemetry_init.py 2>/dev/null || true

> **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`.

---
python3 telemetry/telemetry_init.py 2>/dev/null || true

> **隐私说明：** 本skill会将使用日志本地存储在 `~/.ai-marketing-skills/analytics/` 路径下。远程遥测为完全可选的自愿加入模式，绝不会收集任何代码、文件路径或仓库内容，详情可查看 `telemetry/README.md`。

---

Cold Outbound Optimizer

冷触推广优化器

Startup: Determine Mode

启动：确定运行模式

Ask the user:
  1. Do you have an existing Instantly account with campaigns to audit, or are you starting from scratch?
  2. Do you have an Instantly API key? (Required for audit mode.)
If API key provided → run 
scripts/instantly-audit.py
to pull campaigns, account inventory, and warmup scores before proceeding.
询问用户以下问题：
  1. 你是已有Instantly账号需要审计现有推广活动，还是要从零开始搭建？
  2. 你是否有Instantly API密钥？（审计模式下必须提供）
如果用户提供了API密钥 → 先运行 
scripts/instantly-audit.py
拉取推广活动、账号清单和预热评分后再继续。

Phase 1: Discovery & Audit

第一阶段：调研与审计

1A — Infrastructure Check (if API key available)

1A — 基础设施检查（如果有可用API密钥）

Run 
python3 scripts/instantly-audit.py --api-key <KEY>
and report:
  • Active campaigns (name, status, reply rate, open rate)
  • Sending accounts (count, warmup score, daily limit)
  • Domain inventory
  • Warmup gaps: any account with score <80 or <14 days warmup → flag as NOT ready
运行 
python3 scripts/instantly-audit.py --api-key <KEY>
并输出以下报告内容：
  • 活跃推广活动（名称、状态、回复率、打开率）
  • 发件账号（数量、预热评分、每日发送限额）
  • 域名清单
  • 预热缺口：所有评分低于80分或预热时长不足14天的账号 → 标记为未就绪

1B — Performance Data

1B — 性能数据

  • Pull campaign analytics from Instantly
  • Ask: "Do you have a spreadsheet with historical outbound data?" If yes, request link.
  • 从Instantly拉取推广活动分析数据
  • 询问用户：「你是否有存储历史推广数据的电子表格？」如果有，请求获取文件链接。

1C — ICP Definition

1C — ICP定义

If no ICP defined, collect:
  • Titles: Who are you targeting? (e.g., VP Marketing, Head of Growth)
  • Industries: Which verticals?
  • Company size: Employee count or revenue range?
  • Revenue floor: Minimum ARR/revenue to qualify?
  • Anti-ICP: Who to explicitly exclude?
Use 
references/icp-template.md
as the collection template.
如果尚未定义ICP，收集以下信息：
  • 职位： 你的目标受众是谁？（例如：营销副总裁、增长负责人）
  • 行业： 哪些垂直领域？
  • 公司规模： 员工数量或营收范围？
  • 营收下限： 符合准入要求的最低ARR/营收额？
  • 反ICP： 需要明确排除的受众？
使用 
references/icp-template.md
作为信息收集模板。

1D — Business Context

1D — 业务背景

Collect:
  • What do you sell? (One sentence, no jargon)
  • What's the primary offer? (Free trial, audit, demo, consultation)
  • Real URLs to reference (pricing page, case studies, relevant content)
  • Any proof points? (Client results, stats, social proof)
收集以下信息：
  • 你销售的产品/服务是什么？（一句话描述，不要使用行业黑话）
  • 核心权益是什么？（免费试用、审计、演示、咨询）
  • 可供参考的真实URL（定价页、案例研究、相关内容）
  • 有没有可提供的佐证？（客户成果、数据、社会证明）

1E — Expert Panel Config

1E — 专家小组配置

Default: 10 experts (see 
references/expert-panel.md
). Ask: "Any industry-specific experts to add, or panelists to swap?" Confirm roster before scoring.
默认配置：10名专家（详见 
references/expert-panel.md
） 询问用户：「是否需要添加特定行业的专家，或者替换现有小组成员？」在评分前确认最终名单。

Phase 2: Expert Panel Recursive Scoring

第二阶段：专家小组递归评分

Target: 90/100. Non-negotiable. Iterate until reached.
目标：90/100，为硬性要求，迭代直到达到该分数为止。

Round Structure

轮次结构

Each round produces:
  1. Score table — all 10 panelists, individual score (0-100), one-line rationale
  2. Aggregate score — average of all 10
  3. Top weaknesses — ranked list of what's holding the copy back
  4. Changes made — specific edits addressing each weakness
  5. Updated copy — full revised sequence after changes
每一轮输出以下内容：
  1. 评分表 —— 10名专家各自的评分（0-100）及一句话评分理由
  2. 综合得分 —— 10名专家的平均分
  3. 核心短板 —— 按优先级排序的文案待优化点
  4. 调整内容 —— 针对每个短板做出的具体修改
  5. 更新后文案 —— 修改后的完整序列文案

Scoring Criteria (per panelist's lens — see 
references/expert-panel.md
)

评分标准（从每个专家的视角判断 —— 详见 
references/expert-panel.md
）

  • Subject line curiosity / open rate potential
  • First sentence pattern interrupt
  • Body clarity and brevity
  • CTA softness and specificity
  • Sequence flow and follow-up logic
  • Deliverability risk signals (spam words, link density)
  • Personalization believability
  • 主题线好奇心/打开率潜力
  • 首句注意力抓取效果
  • 正文清晰度和简洁度
  • CTA的柔和度和明确性
  • 序列流程和跟进逻辑
  • 送达率风险信号（垃圾词、链接密度）
  • 个性化内容可信度

Rules

规则

  • Scores must be brutally honest. No padding to 90 without earning it.
  • If round score < 90: identify top 3 weaknesses, revise copy, run next round.
  • If round score ≥ 90: finalize copy and proceed to deliverables.
  • Show every round in the final doc — the iteration trail is part of the value.
  • 评分必须完全客观真实，未达到要求不得刻意凑到90分。
  • 如果本轮得分 < 90：找出前3个核心短板，修改文案后开启下一轮评分。
  • 如果本轮得分 ≥ 90：定稿文案，进入交付阶段。
  • 最终文档中需要展示每一轮的评分结果 —— 迭代过程本身也是价值的一部分。

Phase 3: Deliverables

第三阶段：交付物

Strategy Doc

策略文档

Create a document (Google Doc, Notion, or markdown) with:
  1. Pre-Analysis / Brutal Truth — what the existing campaigns are doing wrong (or baseline if starting from scratch)
  2. ICP Summary — confirmed targeting parameters
  3. Infrastructure Status — account inventory, warmup readiness, capacity math
  4. Scoring Rounds — full panel vote tables for every round
  5. Final Email Copy — all steps for all campaigns, Instantly-ready format
  6. Implementation Plan — step-by-step setup instructions
  7. Capacity Math — accounts × daily send rate = pipeline projections
  8. Weekly Metrics Targets — open rate, reply rate, positive reply rate, meetings booked
  9. STOP List — what to kill immediately
  10. START List — what to launch first
创建一份文档（支持Google Doc、Notion或markdown格式），包含以下内容：
  1. 前期分析/客观结论 —— 现有推广活动存在的问题（如果从零开始则输出基线参考）
  2. ICP概要 —— 确认后的受众定向参数
  3. 基础设施状态 —— 账号清单、预热就绪状态、容量测算
  4. 评分轮次记录 —— 每一轮完整的专家评分表
  5. 最终邮件文案 —— 所有推广活动的全流程内容，适配Instantly格式
  6. 实施方案 —— 分步设置指引
  7. 容量测算 —— 账号数量 × 每日发送量 = 潜在客户流预测
  8. 每周指标目标 —— 打开率、回复率、正向回复率、预约会议数
  9. 停止清单 —— 需要立即停用的内容/操作
  10. 启动清单 —— 需要优先上线的内容/操作

Format Rules for Final Copy

最终文案格式规则

Follow all rules in 
references/instantly-rules.md
and 
references/copy-rules.md
.
遵循 
references/instantly-rules.md
和 
references/copy-rules.md
中的所有规则。

Human Review Gate

人工审核关口

Do NOT push anything to Instantly automatically. The doc is for human review. Get explicit approval before any API writes.
禁止自动向Instantly推送任何内容，生成的文档需先提交人工审核，在得到明确批准前不得调用API执行写入操作。

Iteration

迭代

After review, collect feedback and re-run scoring on revised copy if needed.
审核完成后收集反馈，如果需要可以对修改后的文案重新运行评分流程。

Capacity Math Formula

容量测算公式

Accounts ready (score ≥80, ≥14 days warmup) × 30 emails/day = conservative daily volume
Accounts ready × 50 emails/day = aggressive daily volume
Daily volume × 22 working days = monthly send capacity
Monthly sends × expected reply rate = expected replies
Expected replies × qualification rate = pipeline opportunities
Accounts ready (score ≥80, ≥14 days warmup) × 30 emails/day = conservative daily volume
Accounts ready × 50 emails/day = aggressive daily volume
Daily volume × 22 working days = monthly send capacity
Monthly sends × expected reply rate = expected replies
Expected replies × qualification rate = pipeline opportunities

Weekly Metrics Targets (Baselines)

每周指标目标（基线）

MetricGoodGreat
Open rate40%+60%+
Reply rate3%+7%+
Positive reply rate1%+3%+
Meeting rate0.5%+1.5%+
Adjust targets based on niche and offer. Cold traffic to a free audit converts differently than a paid trial.
指标良好优秀
打开率40%+60%+
回复率3%+7%+
正向回复率1%+3%+
会议预约率0.5%+1.5%+
根据所属细分领域和提供的权益调整目标，冷触引流到免费审计的转化率和付费试用的转化率存在差异。

Add-On Recommendations (mention but don't build)

附加功能推荐（仅提及无需实现）

  • LinkedIn automation: HeyReach or similar for multi-channel sequences. Separate workflow.
  • Lead enrichment: Clay or Apollo for personalization data before upload.
  • Lead pipeline: Use 
    scripts/lead-pipeline.py
    for Apollo → LeadMagic → Instantly automation.
  • LinkedIn自动化： 使用HeyReach或类似工具搭建多渠道推广序列，属于独立工作流。
  • 线索富集： 上传线索前使用Clay或Apollo获取个性化数据。
  • 线索流转： 使用 
    scripts/lead-pipeline.py
    实现Apollo → LeadMagic → Instantly的自动化流程。

Reference Files

参考文件

FilePurpose
references/instantly-rules.md
Variable syntax, sequence structure, deliverability rules
references/expert-panel.md
Default 10-expert roster with scoring lenses
references/copy-rules.md
Email copy rules (first sentence, CTA, stats framing)
references/icp-template.md
ICP data collection template
scripts/instantly-audit.py
Pulls campaigns, accounts, warmup scores via Instantly v2 API
scripts/lead-pipeline.py
End-to-end lead sourcing pipeline
scripts/competitive-monitor.py
Competitor tracking and intelligence
scripts/cross-signal-detector.py
Multi-source signal detection
scripts/cold-outbound-sender.py
Send approved outbound emails
文件用途
references/instantly-rules.md
变量语法、序列结构、送达率规则
references/expert-panel.md
默认10人专家小组名单及评分视角
references/copy-rules.md
邮件文案规则（首句、CTA、数据表述）
references/icp-template.md
ICP信息收集模板
scripts/instantly-audit.py
通过Instantly v2 API拉取推广活动、账号、预热评分
scripts/lead-pipeline.py
端到端线索获取流转管线
scripts/competitive-monitor.py
竞品追踪和情报收集
scripts/cross-signal-detector.py
多源信号检测
scripts/cold-outbound-sender.py
发送经审核的推广邮件