Agent Skills › superlinked/sie › extract-entities

extract-entities

GitHub

通过 Superlinked MCP 工具从文档中零样本提取实体，避免将全文载入上下文。支持多种格式，输出紧凑表格并保存至指定路径，适用于用户请求列表或提取文件中特定信息时。

packages/sie_mcp/plugin/claude-code/extract-entities/SKILL.md superlinked/sie

Trigger Scenarios

用户要求从文件中列出实体用户要求提取文件中的组织、日期等信息用户要求将文档内容整理为表格

Install

npx skills add superlinked/sie --skill extract-entities -g -y

More Options

Non-standard path

npx skills add https://github.com/superlinked/sie/tree/main/packages/sie_mcp/plugin/claude-code/extract-entities -g -y

Use without installing

npx skills use superlinked/sie@extract-entities

指定 Agent (Claude Code)

npx skills add superlinked/sie --skill extract-entities -a claude-code -g -y

安装 repo 全部 skill

npx skills add superlinked/sie --all -g -y

预览 repo 内 skill

npx skills add superlinked/sie --list

SKILL.md

Frontmatter

{
    "name": "extract-entities",
    "description": "Extract people, organizations, dates, amounts, or custom labels from a document through the connected Superlinked MCP edge, returning a compact table instead of reading the full document into context. Use when the user asks to list, extract, or tabulate entities from a file."
}

Extract Entities with Superlinked MCP

Use the connected Superlinked MCP server to run zero-shot entity extraction on the SIE cluster through the MCP extract_entities tool.

Steps

Pick labels from the user's request. Lowercase nouns work best, for example: person, organization, date, amount, contract term.
Do not open, view, attach, or read the whole source document into context.
Call the Superlinked MCP extract_entities tool:
- Pass labels as a list of label strings.
- For PDF, scan, image-of-text, DOCX, PPTX, XLSX, or HTML inputs, read raw bytes only, base64-encode them, and pass document_base64 plus filename.
- For text or markdown inputs, read raw bytes only, base64-encode them, and pass content_base64.
- Leave engine as auto unless the user explicitly asks to force a conversion engine.
Write the returned markdown_table to processed/<source-stem>.entities.md. Create processed/ if it does not exist.
Your next message must begin with a short receipt:
```
Extracted <entity_count> entities from <source> -> processed/<source-stem>.entities.md
```
Then present the entity table or the subset the user asked for.

Errors

If the MCP call fails, relay the tool error and do not retry blindly. For auth or connector errors, tell the user to reinstall the generated MCP plugin pack or rerun the generated claude mcp add ... --header 'Authorization: Bearer ...' command from INSTALL.md.