Back to Details

table-creation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Create Table

创建表格

End-to-end workflow: parse company data → create/reuse Extruct table → upload rows → add columns → run enrichment.
端到端工作流：解析公司数据 → 创建/复用Extruct表格 → 上传行数据 → 添加列 → 运行enrichment。

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 table creation, row uploads, column creation, and enrichment runs are handled by the extruct-api skill. This skill focuses on parsing input data and orchestrating the flow — the extruct-api skill handles the API execution.
本技能将所有Extruct API调用委托给
extruct-api
技能。
对于所有Extruct API操作，请阅读并遵循
skills/extruct-api/SKILL.md
中的说明。
所有表格创建、行数据上传、列创建和enrichment运行均由extruct-api技能处理。本技能专注于解析输入数据和编排工作流——extruct-api技能负责API执行。

Workflow

工作流

1. Parse input data

1. 解析输入数据

Accept data in any of these formats:
Pasted list (most common): User pastes company names, URLs, and metadata as freeform text. Parse into structured records. Extract domains by stripping protocol, 
www.
, and trailing slashes.
CSV file: Read CSV, map columns to find the URL/domain column.
Extruct table URL: Use the extruct-api skill to fetch data from existing table.
Key rules:
  • Skip entries with no URL (e.g., "Stealth" companies)
  • Deduplicate by domain
  • Ask which metadata fields to preserve (country, stage, industry, etc.)
接受以下任意格式的数据：
粘贴列表（最常用）：用户以自由文本形式粘贴公司名称、URL和元数据。将其解析为结构化记录。通过去除协议、
www.
和末尾斜杠来提取域名。
CSV文件：读取CSV，映射列以找到URL/域名列。
Extruct表格URL：使用extruct-api技能从现有表格中获取数据。
关键规则：
  • 跳过无URL的条目（例如“Stealth”企业）
  • 按域名去重
  • 询问用户需要保留哪些元数据字段（国家、阶段、行业等）

2. Decide: create new table or add to existing

2. 决策：创建新表格或添加至现有表格

Ask the user:
  • New table: Delegate to the extruct-api skill to create a company table
  • Existing table: User provides table ID or URL (
    https://app.extruct.ai/tables/{id}
    )
询问用户：
  • 新表格：委托extruct-api技能创建公司表格
  • 现有表格：用户提供表格ID或URL（
    https://app.extruct.ai/tables/{id}
    ）

3. Upload rows

3. 上传行数据

Delegate row upload to the extruct-api skill with the parsed domains.
Report progress to the user.
将行数据上传任务委托给extruct-api技能，传入解析后的域名。
向用户汇报进度。

4. Add agent columns (optional)

4. 添加Agent列（可选）

If the user wants enrichment columns (industry, funding, etc.), delegate column creation to the extruct-api skill.
Column types by use case:
User saysAgent typeOutput formatNotes
"add industry"
llm
select
with labels		Classification from profile, no web research needed
"add funding"
research_pro
text
Needs web research
"classify by vertical"
llm
select
with labels		Classification
"find their tech stack"
research_pro
text
Needs web research
"score fit 1-5"
llm
or 
research_reasoning
grade
Assessment
"tag multiple categories"
llm
multiselect
with labels		Multiple tags
See the list-enrichment skill for full column types and output formats.
若用户需要enrichment列（行业、融资情况等），将列创建任务委托给extruct-api技能。
按使用场景划分的列类型：
用户需求Agent类型输出格式说明
"添加行业信息"
llm
带标签的
select
基于企业档案分类，无需网络调研
"添加融资信息"
research_pro
text
需要网络调研
"按垂直领域分类"
llm
带标签的
select
分类任务
"查找技术栈"
research_pro
text
需要网络调研
"适配度评分1-5"
llm
或
research_reasoning
grade
评估任务
"添加多类别标签"
llm
带标签的
multiselect
多标签任务
完整的列类型和输出格式请查看list-enrichment技能。

5. Trigger enrichment

5. 触发enrichment

Delegate the enrichment run to the extruct-api skill, scoped to only the newly added agent columns.
If no agent columns were added, skip this step.
将enrichment运行任务委托给extruct-api技能，仅针对新增的Agent列执行。
若未添加Agent列，则跳过此步骤。

6. Report to user

6. 向用户汇报结果

Provide:
  • Table URL: 
    https://app.extruct.ai/tables/{table_id}
  • Row count uploaded
  • Columns added
  • Cells queued for enrichment
  • Any rows skipped (stealth, duplicates, invalid URLs)
提供以下信息：
  • 表格URL：
    https://app.extruct.ai/tables/{table_id}
  • 已上传的行数据数量
  • 已添加的列
  • 待enrichment的单元格数量
  • 已跳过的行数据（Stealth企业、重复项、无效URL）

Input Parsing Patterns

输入解析规则

Freeform pasted list (5-line groups)

自由格式粘贴列表（5行一组）

Company Name
URL (or "Stealth")
Country
Industry
Funding Stage
Parse by splitting into 5-line chunks. Filter where URL == "Stealth".
Company Name
URL (or "Stealth")
Country
Industry
Funding Stage
按5行一组拆分解析。过滤掉URL为“Stealth”的条目。

CSV

CSV

Map columns: look for "website", "url", "domain", "Company Website". Extract domain from whichever column contains URLs.
映射列：查找包含“website”、“url”、“domain”、“Company Website”的列。从包含URL的列中提取域名。

Single-column domain list

单列域名列表

example.com
startup.io
company.ai
Direct upload — each line is a domain.
example.com
startup.io
company.ai
直接上传——每行对应一个域名。

Common Pitfalls

常见注意事项

  • Domain format: Strip protocol and trailing slash. 
    https://www.example.com/
    → 
    example.com
  • Stealth companies: Skip — no domain to enrich
  • Duplicates: Deduplicate by domain before upload
  • Column labels: For 
    select
    /
    multiselect
    , collect unique values from user data to build the label list
  • 域名格式：去除协议和末尾斜杠。
    https://www.example.com/
    → 
    example.com
  • Stealth企业：跳过——无域名可进行enrichment
  • 重复项：上传前按域名去重
  • 列标签：对于
    select
    /
    multiselect
    类型，从用户数据中收集唯一值以构建标签列表