/extract

Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with source-location trace. Single tool. Reusable standalone.

BOOST

s0912758806p@s0912758806p

GitHub

From plugin

agentic-sop-to-work

20911 skills4 commands

Install

$ npx -y skills add s0912758806p/agentic-sop-to-work --skill extract --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/extract

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with source-location trace. Single tool. Reusable standalone.

SKILL.md

extract.SKILL.md

name: extract
description: Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with source-location trace. Single tool. Reusable standalone.

Skill A — extract（抽取讀數）

SOP 流程的第 1 步。把文字輸入中的 `key: number`（或 `key = number`）抽成結構化 readings。

綁定的單一工具

`python3`（標準庫；正規表示式 `re`）。**本 skill 只宣告/使用這一個工具。**

依賴（完整宣告；缺項由 `kit.require_deps` 明確報錯，非靜默失敗）

`python` >= 3.8

參數化（無硬編碼專案值）

輸入：`--in <text 檔>`（任意路徑，由編排層/呼叫端提供）
輸出：`--out <artifact.json>`

介面（與上下游 skill 的資料格式）

**輸入**：純文字（每行 `key: number`）。
**輸出 artifact**：`{"schema":"readings@1","produced_by":"extract","data":{"readings":[{"key","value"}]},"trace":[{"value","source","locator"}]}`
下游（compute）讀 `data.readings`。