150 tagged ocr, measured the same way as everything else here.
Browse within: obsidian 37knowledge-management 30digital-humanities 21vision 21alchemy 20ancient-texts 20manuscripts 20nextjs 20Multimodal 19agent-skill 18GLM 17document-parsing 17claude-skill 16document-processing 16
Skill Claude CodeCodex
Use when you need to find, list, or read-and-summarize Obsidian vault notes mechanically — e.g., "find all NPC notes tied to faction X", "list all session N scene files", "read frontmatter of these 12 notes and return a table", "grep all Locations/ notes for wikilinks to [[NPC Name]]". Dispatches a Haiku subagent to…
Skill Claude CodeCodex
Use when creating or expanding worldbuilding content — locations, NPCs, factions, lore entries, quests, or items for a TTRPG campaign managed in an Obsidian vault. Triggers on any request to create, describe, detail, or flesh out campaign world elements, even if the user doesn't explicitly say "worldbuilding". Also…
Embassy-of-the-Free-Mind/sourcelibrary-v2
Skill Claude CodeCodex
Batch process books through the complete pipeline - generate cropped images for split pages, OCR all pages, then translate with context. Use when asked to process, OCR, translate, or batch process one or more books.
Embassy-of-the-Free-Mind/sourcelibrary-v2
Skill Claude CodeCodex
Check pipeline processing progress — all phases including OCR, translation, image extraction, enrichment, and more. Shows real page-level verification, not just job counters. Use when asked "how's it going?", "progress?", "status?", "now?", or any progress check.
Embassy-of-the-Free-Mind/sourcelibrary-v2
Skill Claude CodeCodex
Quality auditor for Source Library. Prioritizes verifying original language texts (not modern translations), auditing metadata accuracy against title pages, USTC alignment, and translation quality. Use for systematic quality control or to identify modern translations that should be replaced with originals.
Skill Claude CodeCodex
A PDF and image text-recognition tool for scanned documents. OCR, or optical character recognition, converts text visible in scans or pictures into machine-readable text, including Chinese and English.
Skill Claude CodeCodex
Axum server design for document extraction endpoints, middleware, async processing, and Model Context Protocol integration for AI agents.
Skill Claude CodeCodex
Kreuzberg's format detection -> extraction -> fallback orchestration for 75+ file formats.
Skill Claude CodeCodex
Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output…
Skill Claude CodeCodex
High-accuracy PDF content extraction using MinerU (Shanghai AI Lab). Use this whenever the user needs to extract text, formulas, tables, or images from a complex PDF — especially academic papers, multi-column layouts, scanned documents, or any PDF where pypdf produces garbled /Cxx formula output. Trigger on: "MinerU"…
Skill Claude CodeCodex
Instructions for extracting text, formulas, tables, and images from difficult PDF files with MinerU, a document-reading tool. It is intended for papers, multi-column layouts, and scanned documents where basic PDF readers may produce poor results.
runyuan-wang/book-to-skill-distillation
Skill Claude CodeCodex
End-to-end workflow for rewriting a book, long PDF, EPUB, manual, course, guideline library, same-domain multi-book source pack, large database, or methodology into an agent-native LingTai / Agent Skill structure. Use when the task is not a summary, but a reusable skill/knowledge system: source triage…
Skill Claude CodeCodex
Use when an AI agent invokes TranscreveAI as a nested video-to-knowledge capability and must return a durable handoff to the caller.
Skill Claude CodeCodex
Use to turn video URLs or media files into evidence-backed knowledge dossiers with TranscreveAI. Trigger on Reels, YouTube, TikTok, Loom, Vimeo, X/Twitter video links, local media files, video summaries, dossier requests, RAG over video runs, or requests to use TranscreveAI.
Skill Claude CodeCodex
A workflow for turning tables in PDF files into Excel workbooks, with one sheet per table and supporting images and quality notes. It uses MinerU, a tool that extracts content from PDFs, and needs an image-reading model to check the results.
Aidenwu0209/dsh-PaddleOCR-Skills
Skill Claude CodeCodex
Install and configure the native PaddleOCR plugin for DeepSeek Harness (DSH) from the Settings → PaddleOCR GUI. Use for OCR and image-to-text from screenshots, scans, and PDFs; Chinese/CJK text; PDF-to-Markdown; structured document parsing with tables, formulas, layout, and reading order; or DSH endpoint, credential…
Aidenwu0209/dsh-PaddleOCR-Skills
Skill Claude CodeCodex
Use the native DeepSeek Harness PaddleOCR tool to parse document layout and Markdown.
Aidenwu0209/dsh-PaddleOCR-Skills
Skill Claude CodeCodex
Use the native DeepSeek Harness PaddleOCR tool to extract text from an image or PDF.
Skill Claude CodeCodex
Multi-platform Chinese OCR text recognition via PaddleOCR/Baidu/Tencent/Alibaba/EasyOCR — 5 backends, all work in China.
Skill Claude CodeCodex
A workflow for turning supplied material—such as a web page, PDF, document, Markdown, text, screenshot, or pasted content—into a single offline HTML article.
Skill Claude CodeCodex
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, or Claude Code, apply an…
Skill Claude CodeCodex
A structured research workflow for studying companies and markets in mainland China and Hong Kong. It covers industry selection, supply-chain research, financial-report checks, and investor sentiment.
Skill Claude CodeCodex
A local-image analysis skill that identifies what is shown in pictures, screenshots, and error images.
liusencomic-cyber/douyin-agent-kit
Skill Claude CodeCodex
A batch workflow for archiving Douyin favorites or all posts from selected creators into Obsidian. It uses account cookies, rate limits, downloading, transcription, deduplication, and optional scheduled synchronization.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: