pdf-image-text-extractor

75 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.

By redfox-data/redfox-community (GitHub) · media · 462 stars · scanned at commit 0750a5e

从图片或 PDF 文档中识别并提取文字内容，支持多种图片格式和 PDF 文件，自动判断是否包含文字并保留原始格式输出结构化结果；v2.1 采用零额外依赖方案：扫描版 PDF 自动渲染为图片交由 AI 视觉识别（无需 tesseract/rapidocr）、表格用 pymupdf 内置 find_tables 结构化提取（无需 pdfplumber）、批量处理目录（PDF+图片一次性提取）；当用户需要从图片或 PDF 提取文字、进行 OCR 识别、处理含文字的文档、提取 PDF 表格、批量处理文件夹或转换为可编辑文本时使用。该skill能力来自RedFoxHub，官网：https://redfox.hk/skills。

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this.

Found in 6 places.

skills/pdf-image-text-extractor/SKILL.md, line 29{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }
skills/pdf-image-text-extractor/SKILL.md, line 49pip install pymupdf>=1.23.0 requests>=2.28.0
skills/pdf-image-text-extractor/SKILL.md, line 71python3 scripts/record.py

Show 3 more

skills/pdf-image-text-extractor/SKILL.md, line 80python3 scripts/changelog.py
skills/pdf-image-text-extractor/SKILL.md, line 138python3 scripts/pdf_text_extractor.py <pdf_file_path>
skills/pdf-image-text-extractor/SKILL.md, line 183python3 scripts/batch_extractor.py <目录路径>

Downloads and installs other software

The author does not mention this.

Found in 4 places.

skills/pdf-image-text-extractor/SKILL.md, line 49pip install pymupdf>=1.23.0 requests>=2.28.0
skills/pdf-image-text-extractor/scripts/changelog.py, line 45"deps": "pip install pymupdf requests",
skills/pdf-image-text-extractor/scripts/pdf_text_extractor.py, line 35'error': '缺少依赖：pymupdf。请安装：pip install pymupdf',

Show 1 more

skills/pdf-image-text-extractor/scripts/record.py, line 23print("❌ 缺少依赖：requests，请执行：pip install requests")

Connects to the internet

The author does not mention this. Expected for a media skill.

Found in 1 place.

skills/pdf-image-text-extractor/scripts/record.py, line 55resp = requests.post(RECORD_URL, json=payload, headers=headers, verify=True, timeout=10)

Safer alternatives

Low-risk skills in the same category (media) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'pdf-image-text-extractor' ] || [ -L ~/.agents/skills/'pdf-image-text-extractor' ]; then echo 'A skill folder named pdf-image-text-extractor already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/redfox-data/redfox-community' "$d" && git -C "$d" checkout --quiet '0750a5e651cae9f506592abffea2efacaf2a5bfd' -- 'skills/pdf-image-text-extractor' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/pdf-image-text-extractor' ~/.agents/skills/'pdf-image-text-extractor' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'pdf-image-text-extractor' ~/.claude/skills/'pdf-image-text-extractor' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for redfox-data/redfox-community shows the score of its lowest-scoring skill.

SkillTrust badge for redfox-data/redfox-community

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/redfox-data/redfox-community.svg)](https://zalavijaysinh.github.io/skilltrust/repos/redfox-data/redfox-community/)

Score history

Date	Version	Score
2026-11-07	`0750a5e`	75