Back to Details

list-building

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

List Building

列表构建

Build company lists using Extruct, guided by a decision tree. Reads from the company context file for ICP and seed companies.
在决策树的指导下，使用Extruct构建公司列表。从公司上下文文件中读取ICP和种子公司信息。

Extruct API Operations

Extruct API 操作

This skill delegates all Extruct API calls to the 
extruct-api
skill.
For all Extruct API operations, read and follow the instructions in 
skills/extruct-api/SKILL.md
.
All company search, lookalike search, deep search, table creation, row uploads, and enrichment runs are handled by the extruct-api skill. This skill focuses on what to search for and why — the extruct-api skill handles the how.
本技能将所有Extruct API调用委托给
extruct-api
技能。
所有Extruct API操作，请阅读并遵循
skills/extruct-api/SKILL.md
中的说明。
所有公司搜索、lookalike search、深度搜索、表格创建、行上传和数据enrichment操作均由extruct-api技能处理。本技能专注于搜索内容和搜索原因，而extruct-api技能负责处理实现方式。

Decision Tree

决策树

Before running any queries, determine the right approach:
Have a seed company from win cases or context file?
  YES → Lookalike Search (pass seed domain)
  NO  ↓

New vertical, need broad exploration?
  YES → Semantic Search (3-5 queries from different angles)
  NO  ↓

Need qualification against specific criteria?
  YES → Deep Search (criteria-scored async research)
  NO  ↓

Need maximum coverage?
  YES → Combine Search + Deep Search (~15% overlap expected)
在运行任何查询之前，确定合适的方法：
Have a seed company from win cases or context file?
  YES → Lookalike Search (pass seed domain)
  NO  ↓

New vertical, need broad exploration?
  YES → Semantic Search (3-5 queries from different angles)
  NO  ↓

Need qualification against specific criteria?
  YES → Deep Search (criteria-scored async research)
  NO  ↓

Need maximum coverage?
  YES → Combine Search + Deep Search (~15% overlap expected)

Before You Start

开始之前

Read the company context file if it exists:
claude-code-gtm/context/{company}_context.md
Extract:
  • ICP profiles — for query design and filters
  • Win cases — for seed companies in lookalike mode
  • DNC list — domains to exclude from results. If no DNC list exists in the context file, ask the user: (1) run an Extruct search for competitors to auto-populate, (2) accept a CSV of existing customers/partners, or (3) skip for now
Also check for a hypothesis set at 
claude-code-gtm/context/{vertical-slug}/hypothesis_set.md
. If it exists, use the Search angle field from each hypothesis to design search queries — these are pre-defined query suggestions tailored to each pain point.
如果存在公司上下文文件，请阅读：
claude-code-gtm/context/{company}_context.md
提取以下信息：
  • ICP画像 — 用于查询设计和筛选
  • 成功案例 — 用于lookalike模式下的种子公司
  • DNC列表 — 需要从结果中排除的域名。如果上下文文件中没有DNC列表，请询问用户：(1) 运行Extruct搜索竞争对手以自动填充；(2) 接受现有客户/合作伙伴的CSV文件；(3) 暂时跳过
同时检查
claude-code-gtm/context/{vertical-slug}/hypothesis_set.md
中的假设集。如果存在，请使用每个假设中的Search angle字段设计搜索查询——这些是针对每个痛点预先定义的查询建议。

Method 1: Lookalike Search

方法一：Lookalike Search

Use when you have a seed company (from win cases, existing customers, or user input). Delegate to the extruct-api skill to run a lookalike search with the seed domain.
When to use:
  • You have a happy customer and want more like them
  • Context file has win cases with domains
  • User says "find companies similar to X"
Tips:
  • Run multiple lookalike searches with different seed companies for broader coverage
  • Combine with filters to constrain geography or size
  • Deduplicate across runs by domain
当你有种子公司（来自成功案例、现有客户或用户输入）时使用。委托extruct-api技能使用种子域名运行lookalike search。
适用场景：
  • 你有满意的客户，想要寻找更多类似客户
  • 上下文文件中包含带域名的成功案例
  • 用户提出"find companies similar to X"
提示：
  • 使用不同的种子公司运行多次lookalike search，以扩大覆盖范围
  • 结合筛选条件限制地域或公司规模
  • 按域名去重多次运行的结果

Method 2: Semantic Search — Fast, Broad

方法二：语义搜索——快速、广泛

Delegate to the extruct-api skill to run semantic company search queries.
Query strategy:
  • Write 3-5 queries per campaign, each from a different angle on the same ICP
  • Describe the product/use case, not the company type
  • Deduplicate across queries by domain — overlap is expected
  • Target 200-800 companies total across all queries
委托extruct-api技能运行公司语义搜索查询。
查询策略：
  • 每个活动编写3-5个查询，每个查询从同一ICP的不同角度出发
  • 描述产品/使用场景，而非公司类型
  • 按域名去重不同查询的结果——允许存在重叠
  • 所有查询的目标公司总数为200-800家

Method 3: Deep Search — Deep, Qualified

方法三：深度搜索——深入、精准

Delegate to the extruct-api skill to create and run deep search tasks.
Query strategy:
  • Write queries like a job description — 2-3 sentences describing the ideal company
  • Use criteria to auto-qualify — each company gets graded 1-5 per criterion
  • Default 50 results for first pass; expand after quality review
  • Use up to 5 criteria per task; keep criteria focused and non-overlapping
  • Run separate tasks for different ICP segments
委托extruct-api技能创建并运行深度搜索任务。
查询策略：
  • 像撰写职位描述一样编写查询——用2-3句话描述理想公司
  • 使用条件自动筛选——每家公司按每个条件获得1-5分的评分
  • 首次运行默认返回50条结果；经质量审核后可扩大结果数量
  • 每个任务最多使用5个条件；条件需聚焦且互不重叠
  • 针对不同ICP细分群体运行单独的任务

Upload to Table

上传至表格

After collecting results, delegate to the extruct-api skill to create a company table and upload domains. Extruct auto-enriches each domain with a Company Profile.
收集结果后，委托extruct-api技能创建公司表格并上传域名。Extruct会自动为每个域名补充Company Profile。

Re-run After Enrichment

数据增强后重新运行

After the 
list-enrichment
skill adds data points to this list, consider re-running list building using enrichment insights as Deep Search criteria. For example:
  • If enrichment reveals that "companies using legacy ERP" are the best fit, create a Deep Search task with that as a criterion
  • If enrichment shows a geographic cluster, run a Search with tighter geo filters
  • This creates a feedback loop: list → enrich → learn → refine list
当
list-enrichment
技能为该列表添加数据点后，可考虑将数据增强的洞察作为深度搜索条件，重新运行列表构建。例如：
  • 如果数据增强发现"使用传统ERP的公司"是最佳匹配对象，创建以此为条件的深度搜索任务
  • 如果数据增强显示存在地域集群，使用更严格的地域筛选条件运行搜索
  • 这将形成一个反馈循环：列表→增强→学习→优化列表

Result Size Guidance

结果规模指导

Campaign stageTarget list sizeMethod
Exploration50-100Search (2-3 queries)
First campaign200-500Search (5 queries) + Deep Search
Scaling500-2000Deep Search (high result count) + multiple Search
活动阶段目标列表规模方法
探索阶段50-100家搜索（2-3个查询）
首次活动200-500家搜索（5个查询）+深度搜索
规模化阶段500-2000家深度搜索（高结果数量）+多次搜索

Workflow

工作流程

  1. Read context file for ICP, seed companies, and DNC list
  2. Follow the decision tree to pick the right method
  3. Draft queries (3-5 for Search, 1-2 for Deep Search)
  4. Delegate to the extruct-api skill to run queries and collect results
  5. Deduplicate across all results by domain
  6. Remove DNC domains
  7. Delegate to the extruct-api skill to upload to a company table
  8. Add agent columns if user needs custom research
  9. Ask user for preferred output: Extruct table link, local CSV, or both
  1. 读取上下文文件获取ICP、种子公司和DNC列表
  2. 遵循决策树选择合适的方法
  3. 草拟查询（搜索用3-5个，深度搜索用1-2个）
  4. 委托extruct-api技能运行查询并收集结果
  5. 按域名对所有结果去重
  6. 移除DNC列表中的域名
  7. 委托extruct-api技能上传至公司表格
  8. 如果用户需要自定义调研，添加Agent列
  9. 询问用户偏好的输出形式：Extruct表格链接、本地CSV文件，或两者都要