Results for “ocr”

Adds a searchable text layer to a scanned PDF with ocrmypdf. Installs the toolchain at runtime in ~18s. Use when a PDF's pages are images and the deliverable is a file to keep, grep, or hand to another tool: 'make this PDF searchable', 'OCR this scan', 'I can't select the text in this PDF', 'search across these scanned pages', 'the pdf skill returned nothing'. Handles non-English scans via tesseract language packs. NOT for charts, diagrams, handwriting, or slide layouts. Route those to transcribing-images.

The English summary is being prepared. Showing the original description.

Recognize and extract text from scanned PDFs and images with ComPDF OCR workflows. Use for OCR, searchable PDF generation, text recognition, table recognition, and scanned-document extraction requests.

The English summary is being prepared. Showing the original description.

Generate a Socratic questioning sequence that develops conceptual understanding through guided inquiry. Use when facilitating philosophical discussions, concept exploration, or critical examination.

The English summary is being prepared. Showing the original description.

Socratic questioning partner named Gadfly for deep learning through dialogue. Use this skill when the user wants to learn, understand, or explore a topic through questions rather than explanations. Trigger when the user says "teach me about...", "help me understand...", "I want to learn...", "ask me questions about...", "quiz me", "Socratic method", "Gadfly", or wants to deeply understand something through dialogue rather than passive reading. Also trigger when the user provides a text or document and wants to be questioned about it, or wants to check their own understanding of a concept.

The English summary is being prepared. Showing the original description.

OCR scanned or image-only corpora with vision-language models in four phases: `triage` inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints; `evaluate` picks a system by measured CER/WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance; `run` builds the production pipeline; and `clean` removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and LLM passes, and records provenance. Born-digital documents with a text layer go to $doc-to-markdown; runs on Leiden's ALICE cluster add $vlm-ocr-alice.

The English summary is being prepared. Showing the original description.

Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.

The English summary is being prepared. Showing the original description.

docling CLIを使用したドキュメント変換スキル。PDF、DOCX、PPTX、HTML、画像、Excel等のあらゆるドキュメントをMarkdown、JSON、YAML、HTML、テキストに変換。OCR対応で画像内テキストも抽出可能。Use when converting documents to Markdown or other formats, extracting text from PDFs, processing scanned documents with OCR, or converting office documents. Argument hint: [file_path] [--to md|json|yaml|html|text] [--ocr-lang ja] [--output output_dir]

The English summary is being prepared. Showing the original description.

Expert en AudioCraft avancé (MusicGen text-to-music, AudioGen text-to-sound, fine-tuning)

The English summary is being prepared. Showing the original description.

画像ファイルからテキストを抽出しクリップボードにコピー。「文字起こし」「OCR」などで使用。

The English summary is being prepared. Showing the original description.

Break a stuck or complex problem into the smallest sub-question that, if answered, unlocks the next step — then answer it and repeat until the path forward is clear. Load when a problem feels genuinely stuck, when reasoning keeps circling, or when deep-thinking diagnoses a Socratic frame. Also triggers on "I keep going in circles", "what is the real question here", "help me reason through this step by step", "unstick my thinking", "recursive questioning", "what is the root question". Based on the recursive Socratic questioning method (EMNLP 2023) which outperforms CoT and Tree-of-Thought on complex reasoning tasks.

The English summary is being prepared. Showing the original description.

Extract text from PDFs, inspect page counts and document metadata, merge files, or split them into individual pages. Create PDFs from Markdown, HTML, or Python code, using the tools suited to each task.

• Extracting text from a PDF
• Combining several PDFs into one
• Splitting a PDF into individual pages

Convert PDF, Office, and other documents into Markdown that preserves useful text structure. Use batch conversion and literature organization to prepare files for search, text analysis, or AI systems that retrieve information from documents.

• Convert PDF and Office files to Markdown
• Batch-convert a document folder
• Organize research papers with source metadata

Develop a research question, search and verify literature, and combine findings into an academic report. Modes also support guided research discussions, claim checking, paper comparisons, and systematic reviews with optional meta-analysis, which statistically combines study results.

• Clarify a research direction through guided questions
• Search literature and compare findings across sources
• Check specific claims against supporting sources

Help junior developers and AI newcomers understand code through guided questions and progressive hints. Support debugging, concept learning, and critical review of AI-generated code so learners can explain their reasoning and work toward solutions themselves.

• Understand errors through guided questions
• Explain AI-generated code in your own words
• Learn with pseudocode and progressive hints

Build a screening pipeline for web pages, PDFs, and images before an AI agent reads them. Extract hidden text, check for malicious instructions with detection models, and record decisions to block or allow content.

• Screening external content before an agent reads it
• Checking uploaded PDFs and images for hidden instructions
• Scanning documents before adding them to a knowledge base

Route articles, meeting notes, videos, documents, and conversations to specialized workflows for saving in GBrain. Preserve sources, add citations, and update related people, companies, concepts, and timelines with links back to the saved material.

• Save an article with its sources and related concepts
• Update attendee pages from meeting notes
• Organize video and podcast transcripts

Develop applications with the Claude API using examples from Anthropic's official cookbooks. Explore document summarization, image analysis, document retrieval, external tool calls, and prompt caching through practical Python code and implementation guidance.

• Learning basic Claude API integration
• Building an assistant that searches documents
• Extracting text and information from images

Convert office documents, spreadsheets, presentations, ebooks, and PDFs into Markdown text that an agent can read. Save large conversions to a file and use hosted text recognition for scanned PDF pages when needed.

• Prepare Word documents for an agent to read
• Convert spreadsheets and slides into Markdown
• Extract content from PDFs and ebooks

Extract PDF text when the usual file reader returns errors or unusable output. Choose command-line tools or Python libraries for plain text, metadata, tables, and complex layouts, with checks for scanned or copy-protected documents.

• Recovering text when PDF reading fails
• Extracting tables and structured data from PDFs
• Inspecting PDF metadata

Extract PDF text using a sequence of tools when one method fails. Validate downloaded files, check whether the extracted text is substantial, record the successful method, and investigate alternative sources if extraction remains unsuccessful.

• Extracting text from regulatory documents and handbooks
• Checking whether a PDF download returned an error page
• Trying another tool after empty or garbled text extraction

Find arXiv papers by topic, author, category, or ID and retrieve abstracts and publication details. Create BibTeX citation entries, then use Semantic Scholar to explore citation counts, references, related papers, and author profiles.

• Find recent papers on a research topic
• Look up papers by author or arXiv ID
• Explore citations and related research

Develop a research question, search and verify literature, combine findings, and produce a structured report. Seven modes cover guided research discussions, briefs, literature reviews, fact-checking, and systematic reviews, with statistical pooling of study results when appropriate.

• Clarify a research topic through guided questions
• Build an annotated bibliography and synthesize findings
• Check claims against verified sources

Create resumes, reports, papers, and other documents with LaTeX, a document typesetting system, then produce PDFs and page previews. Also convert document formats and handle PDF tasks such as merging files and filling forms.

• Creating reports and papers with charts and citations
• Preparing resumes and cover letters
• Converting handwritten PDFs into LaTeX

Run Apache Tika as a Docker container when you need guaranteed OCR (scanned PDFs, images) or geospatial raster support with zero local install — `apache/tika:<version>-full` bundles Tesseract, GDAL, ImageMagick, and fonts. Also covers the minimal image, port/volume/memory conventions, the path-identity mount gotcha, and how to confirm OCR actually ran rather than silently returning no text. Powered by Apache Tika. Use when a local `tika-app`/`tika-server` doesn't have Tesseract installed, or you want a disposable, self-contained parsing environment. Companion to the `file-to-markdown` skill, which covers the parsing calls themselves once a server is up.

The English summary is being prepared. Showing the original description.