Back to Details

cargo-gtm

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Cargo GTM — Meta Skill

Cargo GTM — Meta Skill

Use this skill for prospecting, account research, contact enrichment, verification, lead scoring, personalization, signal monitoring, and campaign activation.
使用该技能进行客户开发、账户调研、联系人信息补全、验证、线索评分、个性化触达、信号监控和营销活动激活。

1) What this skill governs

1) 本技能的管理范围

  • Route GTM decisions, safety gates, and provider/quality defaults before execution.
  • Keep long command chains and tooling nuance in sub-docs; provider-specific implementation detail in 
    provider-playbooks/*.md
    .
  • Anchor recipes in credits-based actions (the high-value action calls). Free CRUD (createLead, getLead, deleteRecords) doesn't need this skill — agents can compose those ad hoc.
  • 在执行操作之前，管控GTM决策、安全门槛以及供应商/质量默认设置。
  • 将冗长的命令链和工具细节放在子文档中；供应商专属的实现细节放在
    provider-playbooks/*.md
    中。
  • 以基于积分的操作（高价值操作调用）为核心制定操作手册。免费的CRUD操作（createLead、getLead、deleteRecords）无需使用本技能——Agent可自行组合这些操作。

Process / goal

流程/目标

The user is generally trying to go from "I have an ICP" to "Here's a list of prospects with verified emails and personalized signals." They may be anywhere in this process — guide them along.
Discovery order: companies first, then people. When the task requires finding contacts at companies matching criteria (portfolio, ICP, hiring signal), discover the company set first, then find people at each company. Don't start with broad people-search queries.
用户通常希望从“我有ICP”推进到“这是一份包含已验证邮箱和个性化信号的潜在客户列表”。他们可能处于该流程的任意阶段——引导他们完成整个流程。
**探索顺序：先公司，再个人。**当任务需要在符合条件（投资组合、ICP、招聘信号）的公司中查找联系人时，先确定目标公司集合，再在每家公司中查找对应人员。不要从宽泛的人员搜索查询开始。

Documentation hierarchy

文档层级

  • Level 1 — 
    SKILL.md
    (this file): decision model, guardrails, routing table, links to sub-docs.
  • Level 2 — Phase docs: 
    guides/finding-companies-and-contacts.md
    , 
    guides/enriching-and-researching.md
    , 
    guides/writing-outreach.md
    .
  • Level 2.5 — Recipes: 
    recipes/*.md
     — step-by-step playbooks for specific scenarios.
  • Level 3 — Provider playbooks: 
    provider-playbooks/<slug>.md
     — provider-specific quirks, costs, and fallback behavior.
  • Level 1 — 
    SKILL.md
    （本文档）：决策模型、管控规则、路由表、子文档链接。
  • Level 2 — 阶段文档：
    guides/finding-companies-and-contacts.md
    、
    guides/enriching-and-researching.md
    、
    guides/writing-outreach.md
    。
  • Level 2.5 — 操作手册：
    recipes/*.md
     — 针对特定场景的分步指南。
  • Level 3 — 供应商指南：
    provider-playbooks/<slug>.md
     — 供应商专属特性、成本及 fallback 机制。

2) Read behavior — MANDATORY before any execution

2) 阅读规则 — 执行前必须遵守

STOP. Do not call any provider, run any 
cargo-ai orchestration action execute
command, or write any search query until you have opened the correct sub-doc for your task.
These docs encode what works, what fails, and why. They contain validated parameter schemas, cheapest-provider mappings, parallel execution patterns, sample payloads, and known pitfalls. Reading the right doc for 10 seconds saves 10 failed action calls, wasted credits, and garbage output.
暂停。在打开对应任务的子文档之前，请勿调用任何供应商、运行任何
cargo-ai orchestration action execute
命令或编写任何搜索查询。
这些文档记录了可行方案、失败案例及原因，包含经过验证的参数 schema、低成本供应商映射、并行执行模式、示例 payload 以及已知陷阱。花10秒阅读正确的文档，可避免10次失败的操作调用、浪费积分以及无效输出。

Routing rules — match your task to a doc and READ IT

路由规则 — 匹配任务并阅读对应文档

When the task involves…You MUST read this doc firstWhat it gives you
Finding companies, finding people, building lead lists, prospecting, portfolio/VC sourcing, contact finding at known companies
guides/finding-companies-and-contacts.md
Provider filter schemas, cheapest-source decision tree, parallel patterns, role-based search rules, portfolio/VC shortcuts, contact-finding patterns.
Enriching companies or contacts, finding emails/phones/LinkedIn, waterfall enrichment, signal lookup (job change, funding, tech stack), coalescing data
guides/enriching-and-researching.md
Waterfall patterns with fallback chains, when to use cargo-native vs waterfall vs FullEnrich vs peopleDataLabs, email/phone/LinkedIn fallback orders, signal segments, output retrieval via 
run download-outputs
.
Writing cold emails, personalizing outreach, lead scoring, qualification, sequence design, campaign copy
guides/writing-outreach.md
LLM provider routing (openAi/anthropic/perplexity/gemini), prompt templates, scoring rubrics, email length/tone rules, personalization patterns.
Building or modifying a recurring workflow (cron / webhook / scheduled tool / play), designing step sequences, triggers, deploy/verify cycles
../cargo-orchestration/SKILL.md
 (capability) + apply-patterns from this skill's recipes		Schema for tool/play workflows, node graph syntax, polling strategies, output retrieval.
当任务涉及…必须先阅读此文档文档提供内容
查找公司、查找人员、构建线索列表、客户开发、投资组合/VC挖掘、已知公司的联系人查找
guides/finding-companies-and-contacts.md
供应商过滤schema、低成本来源决策树、并行模式、基于角色的搜索规则、投资组合/VC快捷方式、联系人查找模式。
补全公司或联系人信息、查找邮箱/电话/LinkedIn、瀑布式信息补全、信号查询（职位变动、融资、技术栈）、数据合并
guides/enriching-and-researching.md
带 fallback 链的瀑布模式、何时使用cargo原生功能 vs 瀑布式 vs FullEnrich vs peopleDataLabs、邮箱/电话/LinkedIn的 fallback 顺序、信号细分、通过
run download-outputs
获取输出。
撰写冷邮件、个性化触达、线索评分、资格审核、序列设计、营销文案
guides/writing-outreach.md
LLM供应商路由（openAi/anthropic/perplexity/gemini）、提示词模板、评分标准、邮件长度/语气规则、个性化模式。
构建或修改 recurring workflow（cron / webhook / 定时工具 / play）、设计步骤序列、触发器、部署/验证周期
../cargo-orchestration/SKILL.md
（功能） + 应用本技能操作手册中的模式		工具/play工作流的schema、节点图语法、轮询策略、输出获取方式。

Recipes: step-by-step playbooks (check before executing)

操作手册：分步指南（执行前查看）

Scan this list and read the recipe matching your task. When a recipe matches: follow it step-by-step as your execution plan.
RecipeUse when…
recipes/prospecting.md
End-to-end find → enrich → verify → sync (P1/P2/P3 variants)
recipes/build-tam.md
Building a Total Addressable Market list at scale (100–10,000 companies)
recipes/linkedin-url-lookup.md
Resolving a person's LinkedIn profile URL from name + company with strict identity validation
recipes/portfolio-prospecting.md
Investor / accelerator → portfolio companies → contacts
recipes/job-change-monitoring.md
waterfall.detectJobChange
(cargo-unique) on a contact segment
recipes/funding-watch.md
Tracking companies that recently raised funding
recipes/tech-intent.md
Finding companies by tech-stack or hiring-intent signals
recipes/icp-discovery.md
Diffing Closed-Won vs Closed-Lost segments to surface ICP signals
If none match, scan the phase docs above for the closest pattern and adapt — or invoke 
agents/execution-plan-creator.md
 to compose a custom chain with provider/action slugs and cost estimates.
浏览以下列表，阅读与任务匹配的操作手册。当有匹配的操作手册时：严格按照步骤作为执行计划。
操作手册使用场景…
recipes/prospecting.md
端到端的查找→补全→验证→同步（P1/P2/P3变体）
recipes/build-tam.md
大规模构建总可寻址市场（TAM）列表（100–10,000家公司）
recipes/linkedin-url-lookup.md
通过姓名+公司解析人员的LinkedIn个人主页URL，并进行严格身份验证
recipes/portfolio-prospecting.md
投资者/加速器→投资组合公司→联系人
recipes/job-change-monitoring.md
对联系人细分群体执行
waterfall.detectJobChange
（Cargo专属功能）
recipes/funding-watch.md
追踪近期完成融资的公司
recipes/tech-intent.md
通过技术栈或招聘意向信号查找公司
recipes/icp-discovery.md
对比成交与流失客户细分群体，挖掘ICP信号
如果没有匹配的操作手册，浏览上述阶段文档找到最接近的模式并调整——或调用
agents/execution-plan-creator.md
，结合供应商/操作slug和成本估算构建自定义流程链。

3) Priority provider stack (recipes lead with these 6)

3) 优先供应商栈（操作手册以这6个为主）

These six credits-based providers cover the full prospecting → enrichment → verification → signal pipeline at the lowest credit cost in the catalog. Every recipe in this skill's 
recipes/
leads with this stack:
ProviderRoleKey actions (cost in credits)
salesNavigatorSourcing
searchLeads
(0.02), 
searchAccounts
(0.05), 
findCompanyInsights/Metrics/EmployeesCount/Distribution
(0.25 each)
cargo (native)Firmographic + signal intelligence
enrichBusinessFirmographics
(0.5), 
…Technographics
(1), 
…FundingAndAcquisitions
(0.5), 
enrichProspectDetails/LinkedinProfile/LinkedinPosts
(2), 
matchBusiness/matchProspect
(0.5), 13 more
waterfallMulti-source enrichment + signal
enrichContact
(2), 
enrichCompany
(1), 
verifyEmail
(0.1), 
detectJobChange
(3), 
searchProspects
(3), 
findPhone
(7)
FullEnrichPremium contact lookup
findEmail
(1), 
findPhone
(6), 
findPhoneAndEmail
(7), 
reverseEmailLookup
(2)
theirStackTech-stack + hiring intent
searchTechnologies
(0.5), 
searchJobs
(0.5), 
searchCompanies
(0.5)
peopleDataLabsHeavyweight backfill
enrichPerson
(3), 
enrichCompany
(3), 
searchPeople
(3), 
searchCompanies
(3), 
queryPeople/Companies
(3)
See 
provider-playbooks/
 for per-provider deep dives. See 
references/stage-action-map.md
 for the complete cheapest-action-per-stage table across the full 120-integration catalog.
这6个基于积分的供应商覆盖了从客户开发→信息补全→验证→信号的完整流程，且在目录中积分成本最低。本技能
recipes/
下的所有操作手册均以该栈为核心：
供应商角色核心操作（积分成本）
salesNavigator客户挖掘
searchLeads
（0.02）、
searchAccounts
（0.05）、
findCompanyInsights/Metrics/EmployeesCount/Distribution
（每项0.25）
cargo（原生）企业信息+信号智能
enrichBusinessFirmographics
（0.5）、
…Technographics
（1）、
…FundingAndAcquisitions
（0.5）、
enrichProspectDetails/LinkedinProfile/LinkedinPosts
（2）、
matchBusiness/matchProspect
（0.5）、另有13项操作
waterfall多源信息补全+信号
enrichContact
（2）、
enrichCompany
（1）、
verifyEmail
（0.1）、
detectJobChange
（3）、
searchProspects
（3）、
findPhone
（7）
FullEnrich高级联系人查询
findEmail
（1）、
findPhone
（6）、
findPhoneAndEmail
（7）、
reverseEmailLookup
（2）
theirStack技术栈+招聘意向
searchTechnologies
（0.5）、
searchJobs
（0.5）、
searchCompanies
（0.5）
peopleDataLabs重量级数据补充
enrichPerson
（3）、
enrichCompany
（3）、
searchPeople
（3）、
searchCompanies
（3）、
queryPeople/Companies
（3）
查看
provider-playbooks/
获取供应商深度解读。查看
references/stage-action-map.md
获取全120个集成目录中各阶段最低成本操作的完整对照表。

4) Recipe spine (default chain)

4) 操作手册核心流程（默认链）

1. SOURCE   → salesNavigator.searchLeads / searchAccounts            (0.02–0.05/record)
2. DEDUPE   → cargo.matchProspect / cargo.matchBusiness              (0.5/record)
3. ENRICH   → cargo.enrichBusinessFirmographics / Technographics
              + waterfall.enrichContact / enrichCompany              (0.5–2/record)
4. SIGNAL   → cargo.enrichBusinessFundingAndAcquisitions
              + theirStack.searchJobs
              + waterfall.detectJobChange                            (0.5–3/record)
5. CONTACT  → FullEnrich.findEmail (fallback peopleDataLabs)         (1–3/record)
6. VERIFY   → waterfall.verifyEmail                                  (0.1/record)
7. BACKFILL → peopleDataLabs.enrichPerson (only if step 5 missed)    (3/record)
Adapt by phase: drop steps that aren't relevant to the user's goal. For pure sourcing, run step 1 only. For "enrich a list I already have," run steps 2–7.
1. SOURCE   → salesNavigator.searchLeads / searchAccounts            (0.02–0.05/record)
2. DEDUPE   → cargo.matchProspect / cargo.matchBusiness              (0.5/record)
3. ENRICH   → cargo.enrichBusinessFirmographics / Technographics
              + waterfall.enrichContact / enrichCompany              (0.5–2/record)
4. SIGNAL   → cargo.enrichBusinessFundingAndAcquisitions
              + theirStack.searchJobs
              + waterfall.detectJobChange                            (0.5–3/record)
5. CONTACT  → FullEnrich.findEmail (fallback peopleDataLabs)         (1–3/record)
6. VERIFY   → waterfall.verifyEmail                                  (0.1/record)
7. BACKFILL → peopleDataLabs.enrichPerson (only if step 5 missed)    (3/record)
根据阶段调整：移除与用户目标无关的步骤。若仅需客户挖掘，仅运行步骤1。若需“补全我已有的列表”，运行步骤2–7。

5) Output retrieval — use 
run download-outputs
, not 
run download

5) 输出获取 — 使用
run download-outputs
，而非
run download

When the agent needs the actual data produced by an action (enriched fields, found emails, search results), use:
bash
cargo-ai orchestration run download-outputs \
  --workflow-uuid <uuid> \
  --output-node-slug <slug> \
  --format json \
  --is-finished
Returns 
{"url": "..."}
— a signed URL to a CSV/JSON containing only the output node's data. Faster and cheaper than 
run download
(which pulls full run records). See 
references/output-retrieval.md
 and 
../cargo-analytics/SKILL.md
.
当Agent需要获取操作产生的实际数据（补全字段、找到的邮箱、搜索结果）时，使用：
bash
cargo-ai orchestration run download-outputs \
  --workflow-uuid <uuid> \
  --output-node-slug <slug> \
  --format json \
  --is-finished
返回
{"url": "..."}
— 一个指向仅包含输出节点数据的CSV/JSON文件的签名URL。比
run download
（拉取完整运行记录）更快、成本更低。查看
references/output-retrieval.md
和
../cargo-analytics/SKILL.md
。

6) Action shape rules (every recipe)

6) 操作格式规则（所有操作手册）

Every action JSON in this skill follows the rules in 
../cargo-orchestration/references/actions.md
:
  • kind: "connector"
    action shape: 
    {"kind":"connector","integrationSlug":"<slug>","actionSlug":"<slug>","config":{}}
    . 
    connectorUuid
    is NOT in 
    config
     — the platform resolves the workspace's authenticated connector from 
    integrationSlug
    automatically.
  • For multi-step node graphs: 
    connectorUuid
    lives at the top level of the node, not in 
    config
    . Cross-node interpolation uses 
    {{nodes.<slug>.<field>}}
    . Agent node outputs wrap under 
    .answer
    (read as 
    {{nodes.<slug>.answer.<field>}}
    ).
本技能中的所有操作JSON均遵循
../cargo-orchestration/references/actions.md
中的规则：
  • kind: "connector"
    操作格式：
    {"kind":"connector","integrationSlug":"<slug>","actionSlug":"<slug>","config":{}}
    。
    connectorUuid
    不在
    config
    中    ——平台会自动从
    integrationSlug
    解析工作区已认证的连接器。
  • 对于多步骤节点图：
    connectorUuid
    位于节点顶层，而非
    config
    中。跨节点插值使用
    {{nodes.<slug>.<field>}}
    。Agent节点输出包裹在
    .answer
    下（读取方式为
    {{nodes.<slug>.answer.<field>}}
    ）。

7) When stuck — file a workspace report

7) 遇到问题时 — 提交工作区报告

If a recipe fails repeatedly and the cause isn't obvious, escalate via 
cargo-ai workspaceManagement report create
. See 
../cargo-workspace-management/SKILL.md
 (Reports section).
若操作手册反复失败且原因不明，通过
cargo-ai workspaceManagement report create
升级问题。查看
../cargo-workspace-management/SKILL.md
（报告章节）。

8) Provider playbooks

8) 供应商指南

Per-provider deep dives for the priority stack. Long-tail providers don't have dedicated playbooks yet — fall back to 
references/alternatives.md
 and 
references/stage-action-map.md
.
Priority stack:
  • provider-playbooks/salesNavigator.md
     — cheapest sourcing in the catalog (0.02–0.05/record).
  • provider-playbooks/cargo.md
     — 22 native enrichment + signal actions; the 
    match*
    actions are key for dedup.
  • provider-playbooks/waterfall.md
     — swiss-army-knife: enrichment, verification, and the cargo-unique 
    detectJobChange
    signal.
  • provider-playbooks/FullEnrich.md
     — premium contact lookup; 
    reverseEmailLookup
    is unique.
  • provider-playbooks/theirStack.md
     — tech-stack + hiring-intent signals.
  • provider-playbooks/peopleDataLabs.md
     — heavyweight backfill at flat 3-credit tier.
优先供应商栈的深度解读。长尾供应商暂无专属指南——可参考
references/alternatives.md
和
references/stage-action-map.md
。
优先供应商栈：
  • provider-playbooks/salesNavigator.md
     — 目录中成本最低的客户挖掘工具（0.02–0.05/条记录）。
  • provider-playbooks/cargo.md
     — 22项原生信息补全+信号操作；
    match*
    操作是去重的关键。
  • provider-playbooks/waterfall.md
     — 多功能工具：信息补全、验证，以及Cargo专属的
    detectJobChange
    信号。
  • provider-playbooks/FullEnrich.md
     — 高级联系人查询；
    reverseEmailLookup
    是专属功能。
  • provider-playbooks/theirStack.md
     — 技术栈+招聘意向信号。
  • provider-playbooks/peopleDataLabs.md
     — 重量级数据补充，统一3积分层级。

9) References

9) 参考文档

  • references/stage-action-map.md
     — cheapest credits-based action per stage across the full 120-integration catalog.
  • references/credits-cost-table.md
     — auto-generated cost table for all 141 credits-based actions.
  • references/waterfall-strategy.md
     — canonical waterfall chains by enrichment goal (every recipe's "fallback" follows these).
  • references/alternatives.md
     — provider swap-ins from the long tail when the priority stack can't serve.
  • references/output-retrieval.md
     — 
    run download-outputs
    patterns for fetching action data.
  • references/stage-action-map.md
     — 全120个集成目录中各阶段最低成本的基于积分操作对照表。
  • references/credits-cost-table.md
     — 所有141项基于积分操作的自动生成成本表。
  • references/waterfall-strategy.md
     — 按信息补全目标划分的标准瀑布链（所有操作手册的“fallback”均遵循此规则）。
  • references/alternatives.md
     — 当优先供应商栈无法满足需求时，可替换的长尾供应商。
  • references/output-retrieval.md
     — 使用
    run download-outputs
    获取操作数据的模式。