OPENAGENTSKILL / DIRECTORY

AI Agent Skills

Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.

Results · “scanned-image-pdfs”

102 Skills

Results: 102

Site downloads

Counts each file download, successful install-command copy, source-site click and reported Agent execution. Repeated operations count again. Includes recorded history; not unique users or proof of installation. Updates may take 5 minutes.

Design & UI

No visual example yet

Explore the skill

Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.

Price unconfirmedDesign & UIClaude CodeOpenAI AgentsPreviously saved information
163.1KGitHub
View details18
Documents

No visual example yet

Explore the skill

让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, g…

Price unconfirmedDocumentsClaude CodeReview before use
819GitHub
View details0
Documents

No visual example yet

Explore the skill

PaddleOCR

PaddlePaddle

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ lan…

Price unconfirmedDocumentsReview before use
83.1KGitHub
View details44
Documents

No visual example yet

Explore the skill

Gowall

Achno

A tool to convert a Wallpaper's color scheme / palette, OCR with VLM's Traditional & Hybrid, Image Compression ,color palette extraction, image upsacling with Adversaria…

Price unconfirmedDocumentsReview before use
2.3KGitHub
View details0
Documents

No visual example yet

Explore the skill

Yomitoku

kotaro-kinoshita

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

Price unconfirmedDocumentsReview before use
1.5KGitHub
View details0

Guides & comparisons

For developers