Back to Details

client-packet-engine

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Client Packet Engine

客户数据包引擎

Batch pipeline that takes a list of companies and produces finished GTM pitch packets — intelligence packages, growth strategies, and executed sample work (lead lists, content drafts, email sequences). Designed for prospective client pitches, not live campaign execution.
这是一个批量处理流水线，接收公司列表并生成完整的GTM提案数据包——包括情报包、增长策略，以及已执行的样本成果（线索列表、内容草稿、邮件序列）。专为潜在客户提案设计，不用于实时营销活动执行。

When to Use

使用场景

  • "Build pitch packets for [company list]"
  • "Create client packets for these companies"
  • "Run the full pitch pipeline for [companies]"
  • "Prepare GTM packets for prospective clients"
  • 为[公司列表]生成提案数据包
  • 为这些公司创建客户数据包
  • 为[公司]运行完整的提案流水线
  • 为潜在客户准备GTM数据包

Key Constraints

核心约束

  • Pitch-packet mode: Generates sample leads, content, and outreach drafts but does NOT launch live campaigns, send real emails, or spend on paid Apollo enrichment. The goal is demonstrating value.
  • Cost budget: Default $5/company. Warn at 80% ($4). Hard stop at limit.
  • Parallelization: Up to 3 companies concurrent (Phase 1), up to 5 strategy executions concurrent (Phase 3).
  • Human checkpoints: (1) After cost estimate, (2) Strategy selection per company, (3) Before any single API call >$2.
  • 提案数据包模式：生成样本线索、内容和开发信草稿，但不会启动实时营销活动、发送真实邮件，也不会使用付费Apollo数据增强服务。核心目标是展示服务价值。
  • 成本预算：默认每家公司5美元。当花费达到预算的80%（4美元）时发出警告，达到预算上限时强制停止。
  • 并行处理：第一阶段最多同时处理3家公司，第三阶段最多同时执行5项策略。
  • 人工检查点：(1) 成本估算后；(2) 每家公司的策略选择环节；(3) 任何单次API调用费用超过2美元前。

Input

输入

companies:
  - name: "Company Name"
    url: "https://company.com"
  - name: "Another Company"
    url: "https://another.com"
Minimum: 1 company. No hard maximum, but warn if >10 (long runtime, high cost).
companies:
  - name: "Company Name"
    url: "https://company.com"
  - name: "Another Company"
    url: "https://another.com"
最低要求：1家公司。无硬性上限，但如果超过10家会发出警告（运行时间长、成本高）。

Phase 0: Intake & Validation

阶段0：接收与验证

Steps

步骤

  1. Parse input: Extract company names and URLs from the user's request. Normalize URLs (add https:// if missing, strip trailing slashes).
  2. Validate websites: For each URL, do a quick web fetch to confirm:
    • Site is reachable (not 404/500)
    • It's the correct company (page title or content matches company name)
    • Flag any mismatches for user confirmation
  3. Estimate costs: Calculate per-company estimate based on typical skill costs:
    • Phase 1 (research + audits): ~$1.50/company (Apify credits for SEO, ads, content scraping)
    • Phase 3 (strategy execution): ~$1.00-3.00/company depending on strategy count and types
    • Total estimate: $2.50-4.50/company typical
  4. Present summary for approval:
    Batch Summary:
┌──────────────────┬─────────────────────────┬──────────┐
│ Company          │ URL                     │ Est Cost │
├──────────────────┼─────────────────────────┼──────────┤
│ Acme Corp        │ https://acme.com        │ ~$3.50   │
│ Beta Inc         │ https://beta.io         │ ~$3.50   │
└──────────────────┴─────────────────────────┴──────────┘
Total estimated cost: ~$7.00
Budget limit: $5.00/company ($10.00 total)
  5. Get user approval before proceeding.
  1. 解析输入：从用户请求中提取公司名称和网址，统一网址格式（缺失https://则自动添加，移除末尾斜杠）。
  2. 验证网站：对每个网址执行快速网络请求，确认：
    • 网站可访问（无404/500错误）
    • 网站属于目标公司（页面标题或内容与公司名称匹配）
    • 若发现不匹配，标记后请求用户确认
  3. 估算成本：根据典型技能成本计算每家公司的预估费用：
    • 阶段1（调研+审计）：约每家1.5美元（用于SEO、广告、内容爬取的Apify credits）
    • 阶段3（策略执行）：每家约1.0-3.0美元，具体取决于策略数量和类型
    • 总预估：每家公司通常2.50-4.50美元
  4. 呈现汇总信息供用户审批：
    批量处理汇总:
┌──────────────────┬─────────────────────────┬──────────┐
│ 公司名称         │ 网址                     │ 预估费用 │
├──────────────────┼─────────────────────────┼──────────┤
│ Acme Corp        │ https://acme.com        │ ~$3.50   │
│ Beta Inc         │ https://beta.io         │ ~$3.50   │
└──────────────────┴─────────────────────────┴──────────┘
总预估费用: ~$7.00
预算上限: 每家公司$5.00（总计$10.00）
  5. 获取用户审批后再继续。

Output

输出

  • Validated company list with confirmed URLs
  • Cost estimate acknowledged by user
  • 已验证的公司列表（含确认后的网址）
  • 用户已确认的成本估算

Phase 1: Research & Strategy Generation

阶段1：调研与策略生成

Run the client-onboarding playbook (Phases 1-3) for each company.
为每家公司运行客户入职剧本（阶段1-3）。

Execution

执行方式

  • Process up to 3 companies in parallel using Task agents
  • Each company gets the full client-onboarding treatment:
    • Phase 1: Intelligence Gathering (company research, competitor research, founder research, SEO audit, AEO visibility, ads review, industry scan, GTM analysis)
    • Phase 2: Synthesis into Client Intelligence Package
    • Phase 3: Strategy Generation with execution tags (see Structured Execution Tags in client-onboarding)
  • 使用Task agents最多同时处理3家公司
  • 每家公司均接受完整的客户入职流程：
    • 阶段1：情报收集（公司调研、竞品调研、创始人调研、SEO审计、AEO可见性分析、广告审核、行业扫描、GTM分析）
    • 阶段2：合成为客户情报包
    • 阶段3：生成带执行标签的策略（详见客户入职流程中的结构化执行标签）

Cost Tracking

成本跟踪

After each company completes:
  • Log actual Apify/API costs
  • Compare against per-company budget
  • If at 80% of budget, warn before continuing
  • If at limit, stop and report what was completed
每家公司完成后：
  • 记录实际Apify/API费用
  • 与每家公司的预算进行对比
  • 若花费达到预算的80%，继续前发出警告
  • 若达到预算上限，停止处理并报告已完成的内容

Output per Company

每家公司的输出

  • clients/<company>/intelligence-package.md
  • clients/<company>/growth-strategies.md
    (with 
    <!-- execution -->
    tags on each strategy)
  • All Phase 1 research files in 
    clients/<company>/intelligence/
  • clients/<company>/intelligence-package.md
  • clients/<company>/growth-strategies.md
    （每个策略带有
    <!-- execution -->
    标签）
  • 所有阶段1的调研文件存储于
    clients/<company>/intelligence/

Phase 2: Strategy Selection (Human Checkpoint)

阶段2：策略选择（人工检查点）

Present all generated strategies across all companies for user selection.
展示所有公司生成的策略，供用户选择。

Presentation Format

展示格式

For each company, show a summary table:
undefined
针对每家公司，展示汇总表格：
undefined

Acme Corp — 7 strategies generated

Acme Corp — 生成7项策略

#StrategyPatternPriorityICEEst LeadsEst Cost
1Hiring signal outbound (DevOps roles)signal-outboundP08.2~50$0.80
2Competitor displacement (vs BigCo)competitive-displacementP07.5~30$1.20
3Conference speaker prospectingevent-prospectingP16.8~20$0.50
4SEO comparison contentcontent-lead-genP16.5~40$0.60
5Quarterly business review timinglifecycle-timingP25.0~15$0.30
6LinkedIn thought leadershipmanualP24.5——
7Partner co-marketingmanualP23.8——
Select strategies to execute: [e.g., "1-4", "all P0", "top 3 by ICE"]
undefined
序号策略模式优先级ICE预估线索量预估费用
1招聘信号开发信（DevOps岗位）signal-outboundP08.2~50$0.80
2竞品客户转化（针对BigCo）competitive-displacementP07.5~30$1.20
3会议演讲者挖掘event-prospectingP16.8~20$0.50
4SEO对比内容content-lead-genP16.5~40$0.60
5季度业务回顾时机lifecycle-timingP25.0~15$0.30
6LinkedIn思想领导力manualP24.5——
7合作伙伴联合营销manualP23.8——
请选择要执行的策略：[例如："1-4", "所有P0", "ICE得分前三"]
undefined

Selection Options

选择方式

Accept flexible input:
  • Specific numbers: "1, 3, 5"
  • Ranges: "1-4"
  • Priority-based: "all P0", "P0 and P1"
  • Score-based: "top 3 by ICE"
  • All executable: "all" (skips 
    manual
    pattern strategies)
  • Per-company overrides: "Acme: 1-3, Beta: all P0"
接受灵活的输入形式：
  • 具体序号："1, 3, 5"
  • 范围："1-4"
  • 基于优先级："所有P0", "P0和P1"
  • 基于得分："ICE得分前三"
  • 所有可执行策略："all"（跳过标记为
    manual
    的策略）
  • 按公司单独指定："Acme: 1-3, Beta: 所有P0"

Validation

验证

  • Warn if selected strategies exceed remaining per-company budget
  • Flag any strategies tagged 
    manual
    (these produce a plan document but no automated execution)
  • Confirm final selection before proceeding
  • 若所选策略超出该公司剩余预算，发出警告
  • 标记所有标记为
    manual
    的策略（这些策略仅生成计划文档，不执行自动化操作）
  • 继续前确认最终选择

Phase 3: Strategy Execution (Pitch-Packet Mode)

阶段3：策略执行（提案数据包模式）

Execute selected strategies using the execution pattern routing system.
使用执行模式路由系统执行选定策略。

Execution Pattern Router

执行模式路由器

Read the 
<!-- execution -->
tag from each selected strategy and route to the appropriate skill chain.
读取每个选定策略中的
<!-- execution -->
标签，将其路由至对应的技能链。

Pattern: 
signal-outbound

模式：
signal-outbound

Detect buying signal → find contacts → draft outreach.
StepSkillPitch-Packet Behavior
1. Detect signals
job-posting-intent
/ 
linkedin-post-research
/ 
review-scraper
(based on 
signal_type
)		Run normally — free or low-cost scraping
2. Find contacts
company-contact-finder
Run normally — uses Gooseworks MCP (free)
3. Draft outreach
email-drafting
Draft sequences but do NOT send or set up campaigns
Output: Signal report + lead CSV + draft email sequences
检测购买信号 → 查找联系人 → 撰写开发信。
步骤技能提案数据包模式行为
1. 检测信号
job-posting-intent
/ 
linkedin-post-research
/ 
review-scraper
（基于
signal_type
）		正常运行——免费或低成本爬取
2. 查找联系人
company-contact-finder
正常运行——使用Gooseworks MCP（免费）
3. 撰写开发信
email-drafting
撰写邮件序列，但不发送或设置营销活动
输出：信号报告 + 线索CSV文件 + 邮件序列草稿

Pattern: 
content-lead-gen

模式：
content-lead-gen

Create content asset + find leads who'd care.
StepSkillPitch-Packet Behavior
1. Create content
content-asset-creator
Generate the asset (HTML report, comparison page, etc.)
2. Find leads
apollo-lead-finder
Free search only — no paid enrichment. Show lead count + titles
Output: Content asset (HTML) + lead list (names/titles/companies, no emails)
创建内容资产 → 定位对其感兴趣的线索。
步骤技能提案数据包模式行为
1. 创建内容
content-asset-creator
生成内容资产（HTML报告、对比页面等）
2. 查找线索
apollo-lead-finder
仅免费搜索——不使用付费数据增强。展示线索数量和职位头衔
输出：内容资产（HTML） + 线索列表（姓名/职位/公司，不含邮箱）

Pattern: 
competitive-displacement

模式：
competitive-displacement

Target competitor's unhappy customers.
StepSkillPitch-Packet Behavior
1. Mine competitor intel
web-archive-scraper
+ 
review-scraper
Scrape archived customer lists + negative reviews
2. Find contacts
company-contact-finder
Find decision-makers at identified companies
3. Draft outreach
email-drafting
Draft displacement-themed sequences
4. Create comparison content
content-asset-creator
Build comparison page (client vs competitor)
Output: Competitor intel report + lead CSV + email sequences + comparison page
定位竞品的不满意客户。
步骤技能提案数据包模式行为
1. 挖掘竞品情报
web-archive-scraper
+ 
review-scraper
爬取归档客户列表 + 负面评价
2. 查找联系人
company-contact-finder
定位目标公司的决策者
3. 撰写开发信
email-drafting
撰写针对竞品转化的邮件序列
4. 创建对比内容
content-asset-creator
构建对比页面（我方vs竞品）
输出：竞品情报报告 + 线索CSV文件 + 邮件序列 + 对比页面

Pattern: 
event-prospecting

模式：
event-prospecting

Find event attendees/speakers matching ICP.
StepSkillPitch-Packet Behavior
1. Find events/people
luma-event-attendees
/ 
conference-speaker-scraper
Scrape relevant events
2. Qualify leads
lead-qualification
Score against ICP
3. Find contacts
company-contact-finder
Enrich qualified leads
Output: Event attendee list + qualified leads CSV
查找符合理想客户画像（ICP）的会议参与者/演讲者。
步骤技能提案数据包模式行为
1. 查找活动/人员
luma-event-attendees
/ 
conference-speaker-scraper
爬取相关活动信息
2. 线索资质审核
lead-qualification
根据ICP打分
3. 查找联系人
company-contact-finder
补充合格线索的信息
输出：会议参与者列表 + 合格线索CSV文件

Pattern: 
lifecycle-timing

模式：
lifecycle-timing

Timed outreach based on trigger events.
StepSkillPitch-Packet Behavior
1. Research triggersWeb researchIdentify timing triggers (fiscal year, renewal cycles, etc.)
2. Find contacts
company-contact-finder
Find decision-makers at target companies
3. Draft timed sequences
email-drafting
Draft timing-aware email sequences with send-date recommendations
Output: Trigger research document + lead CSV + timing-aware email sequences
基于触发事件的定时开发信。
步骤技能提案数据包模式行为
1. 调研触发事件网络调研识别时间触发因素（财年、续约周期等）
2. 查找联系人
company-contact-finder
定位目标公司的决策者
3. 撰写定时序列邮件
email-drafting
撰写含发送日期建议的定时邮件序列
输出：触发事件调研文档 + 线索CSV文件 + 定时邮件序列

Pattern: 
manual

模式：
manual

Strategy requires human execution or tools not yet automated.
StepOutput
1. Generate execution planDetailed step-by-step plan with recommended tools, timelines, and KPIs
Output: Strategy execution plan document (no automated work)
该策略需要人工执行或使用尚未自动化的工具。
步骤输出
1. 生成执行计划详细的分步计划，含推荐工具、时间线和关键绩效指标（KPI）
输出：策略执行计划文档（无自动化操作）

Parallelization

并行处理

  • Run up to 5 strategy executions concurrently across all companies
  • Track cost per execution against remaining company budget
  • If a single API call would exceed $2, pause and confirm with user
  • 所有公司最多同时执行5项策略
  • 跟踪每项执行的成本，确保不超过该公司的剩余预算
  • 若单次API调用费用超过2美元，暂停并向用户确认

Cost Tracking

成本跟踪

Maintain a running cost log:
Cost Tracker:
┌──────────────┬─────────────┬───────┬──────────┬───────────┐
│ Company      │ Strategy    │ Spent │ Budget   │ Remaining │
├──────────────┼─────────────┼───────┼──────────┼───────────┤
│ Acme Corp    │ Phase 1     │ $1.40 │ $5.00    │ $3.60     │
│ Acme Corp    │ Strategy 1  │ $0.70 │          │ $2.90     │
│ Acme Corp    │ Strategy 2  │ $1.10 │          │ $1.80     │
└──────────────┴─────────────┴───────┴──────────┴───────────┘
维护实时成本日志：
成本跟踪器:
┌──────────────┬─────────────┬───────┬──────────┬───────────┐
│ 公司名称      │ 策略         │ 已花费 │ 预算      │ 剩余预算   │
├──────────────┼─────────────┼───────┼──────────┼───────────┤
│ Acme Corp    │ Phase 1     │ $1.40 │ $5.00    │ $3.60     │
│ Acme Corp    │ Strategy 1  │ $0.70 │          │ $2.90     │
│ Acme Corp    │ Strategy 2  │ $1.10 │          │ $1.80     │
└──────────────┴─────────────┴───────┴──────────┴───────────┘

Output per Strategy

每项策略的输出

All outputs go to 
clients/<company>/
in the appropriate subdirectory:
  • Lead CSVs → 
    clients/<company>/leads/
  • Content assets → 
    clients/<company>/content/
  • Email sequences → 
    clients/<company>/campaigns/
  • Strategy plans → 
    clients/<company>/strategies/
  • Signal/research reports → 
    clients/<company>/intelligence/
所有输出均存储于
clients/<company>/
的对应子目录中：
  • 线索CSV文件 → 
    clients/<company>/leads/
  • 内容资产 → 
    clients/<company>/content/
  • 邮件序列 → 
    clients/<company>/campaigns/
  • 策略计划 → 
    clients/<company>/strategies/
  • 信号/调研报告 → 
    clients/<company>/intelligence/

Phase 4: Packaging

阶段4：打包

Run client-package-local for each company to produce the final deliverable.
为每家公司运行client-package-local剧本，生成最终交付物。

Steps

步骤

  1. For each company, run the 
    client-package-local
    playbook
  2. This produces a dated package directory:
    clients/<company>/client-package/<YYYY-MM-DD>/
├── intelligence-package.md
├── growth-strategies.md
├── executed-strategies/
│   ├── strategy-1-signal-outbound/
│   │   ├── signal-report.md
│   │   ├── leads.csv
│   │   └── email-sequences.md
│   ├── strategy-2-competitive-displacement/
│   │   ├── competitor-intel.md
│   │   ├── leads.csv
│   │   ├── email-sequences.md
│   │   └── comparison-page.html
│   └── ...
└── summary.md
  3. Generate a 
    summary.md
    for each packet that includes:
    • Company overview (from intelligence package)
    • Strategies generated and which were executed
    • Key metrics: total leads found, content assets created, email sequences drafted
    • Recommended next steps (what to do if the client signs)
  1. 为每家公司运行
    client-package-local
    剧本
  2. 生成带日期的包目录：
    clients/<company>/client-package/<YYYY-MM-DD>/
├── intelligence-package.md
├── growth-strategies.md
├── executed-strategies/
│   ├── strategy-1-signal-outbound/
│   │   ├── signal-report.md
│   │   ├── leads.csv
│   │   └── email-sequences.md
│   ├── strategy-2-competitive-displacement/
│   │   ├── competitor-intel.md
│   │   ├── leads.csv
│   │   ├── email-sequences.md
│   │   └── comparison-page.html
│   └── ...
└── summary.md
  3. 为每个数据包生成
    summary.md
    ，内容包括：
    • 公司概况（来自情报包）
    • 已生成的策略及已执行的策略
    • 核心指标：找到的线索总数、创建的内容资产数量、撰写的邮件序列数量
    • 后续建议（若客户签约后的操作步骤）

Final Report

最终报告

After all companies are packaged, present a batch summary:
Batch Complete: 3/3 companies processed

┌──────────────┬────────────┬───────────┬────────┬──────────┬───────────┐
│ Company      │ Strategies │ Executed  │ Leads  │ Content  │ Total Cost│
├──────────────┼────────────┼───────────┼────────┼──────────┼───────────┤
│ Acme Corp    │ 7          │ 4         │ 142    │ 3 assets │ $4.20     │
│ Beta Inc     │ 5          │ 3         │ 89     │ 2 assets │ $3.80     │
│ Gamma Labs   │ 6          │ 4         │ 115    │ 3 assets │ $4.50     │
└──────────────┴────────────┴───────────┴────────┴──────────┴───────────┘

Total cost: $12.50 / $15.00 budget
Packets saved to: clients/<company>/client-package/<date>/
所有公司打包完成后，呈现批量处理汇总：
批量处理完成：3/3家公司已处理

┌──────────────┬────────────┬───────────┬────────┬──────────┬───────────┐
│ 公司名称      │ 策略总数    │ 已执行策略 │ 线索数  │ 内容资产  │ 总费用    │
├──────────────┼────────────┼───────────┼────────┼──────────┼───────────┤
│ Acme Corp    │ 7          │ 4         │ 142    │ 3项资产   │ $4.20     │
│ Beta Inc     │ 5          │ 3         │ 89     │ 2项资产   │ $3.80     │
│ Gamma Labs   │ 6          │ 4         │ 115    │ 3项资产   │ $4.50     │
└──────────────┴────────────┴───────────┴────────┴──────────┴───────────┘

总费用：$12.50 / 预算$15.00
数据包已保存至：clients/<company>/client-package/<date>/

Error Handling

错误处理

  • Website unreachable: Skip company, flag in report, continue with others
  • Skill failure: Retry once. If still fails, log error, skip that strategy execution, continue with others
  • Budget exceeded: Stop execution for that company, package whatever was completed
  • Rate limiting: Back off and retry with exponential delay (max 3 retries)
  • No strategies tagged executable: Generate all strategies but flag that manual selection will be needed for execution
  • 网站无法访问：跳过该公司，在报告中标记，继续处理其他公司
  • 技能执行失败：重试一次。若仍失败，记录错误，跳过该策略执行，继续处理其他策略
  • 预算超支：停止该公司的执行，打包已完成的内容
  • 速率限制：退避并重试，采用指数退避策略（最多重试3次）
  • 无标记为可执行的策略：生成所有策略，但标记需人工选择后才能执行

Configuration Overrides

配置覆盖

Users can override defaults at invocation:
Override options:
  budget_per_company: $10      # Default $5
  max_parallel_companies: 5    # Default 3
  max_parallel_strategies: 8   # Default 5
  skip_phases: [4]             # Skip packaging
  strategy_filter: "P0 only"  # Pre-filter strategies
  pitch_packet_mode: false     # Enable live campaign mode (CAREFUL)
WARNING: Setting 
pitch_packet_mode: false
enables live campaign execution — emails will be sent, Apollo credits will be spent. Only do this with explicit user confirmation.
用户可在调用时覆盖默认配置：
覆盖选项:
  budget_per_company: $10      # 默认$5
  max_parallel_companies: 5    # 默认3
  max_parallel_strategies: 8   # 默认5
  skip_phases: [4]             # 跳过打包阶段
  strategy_filter: "P0 only"  # 预过滤策略
  pitch_packet_mode: false     # 启用实时营销活动模式（注意风险）
警告：设置
pitch_packet_mode: false
将启用实时营销活动执行——邮件会被发送，Apollo credits会被消耗。仅在获得用户明确确认后操作。