Menú
将本地 PDF、TXT、Word、PPT 文件分割为文本和图片chunk。
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Operate LinkMind Interaction menu features against the hosted LinkMind server with API-key identity: recommended/joined/owned channels, subscribe/unsubscribe, monitor/list/send messages, create/enable/disable/delete/translate channels. Use when the user asks to manage LinkMind interaction/social channels without installing the LinkMind client.
Operate social channels through LinkMind HTTP APIs: view the latest messages by channel name, browse new messages, or send text/questions/announcements to a specified channel. Use this when the user naturally asks to read or write messages in a channel.
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
| name | extract_content_with_image |
| description | 将本地 PDF、TXT、Word、PPT 文件分割为文本和图片chunk。 |
| version | 1.0.0 |
| author | lagi |
| tags | ["extract","pdf","chunks","images"] |
执行脚本前请先激活环境
scripts/extract_content_with_image.pyargv[1] 为待处理文件的本地绝对路径.pdf、.txt、.doc、.docx、.ppt、.pptxjson.loads / parseJsonObject{"status":"success","filepath":"...pdf","data":[...]}{"status":"failed","msg":"<具体异常信息>"}data 中每个元素形如：{"text":"...", "image":"<图片列表的 JSON 字符串或空串>"}PyMuPDF（fitz）和 Pillowsoffice，用于 .doc/.docx/.ppt/.pptx/.txt 转 PDF；可用环境变量 SOFFICE_PATH 指定soffice 时：
.txt 会直接用 fitz 生成 PDF，并基于原始文本做分块.doc/.docx/.ppt/.pptx 会返回失败 JSONtransformers + TOKENIZER_DIR 或 MODEL_DIR
CHUNK_SIZE=512SKILL_OUTPUT_DIR/extract_content_with_image/<run_id>/files/filepath 返回转换后的 PDF 路径image 字段中以绝对路径返回page_dir 会在结束时清理，保留裁剪后的图片文件