ocr-locally[macOS only] Use this skill when the user requests OCR (Optical Character Recognition), image/PDF text extraction. Uses macOS native Vision/PDFKit frameworks...
Install via ClawdBot CLI:
clawdbot install ltryee/ocr-locallyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://developer.apple.com/documentation/visionAudited May 10, 2026 · audit v1.0
Generated May 12, 2026
Users need to extract text from scanned PDF files for editing or analysis. This skill reads PDFs locally using macOS PDFKit and Vision frameworks, outputting text or JSON with confidence scores and bounding boxes.
Users have images containing text in languages like Chinese, English, Japanese, or Korean and need accurate extraction. The skill supports multiple languages, outputting text or structured JSON, and can be set to fast or precise mode.
Professionals can extract text from screenshots of documents, forms, or receipts to automate data entry. The OCR skill outputs text directly to console or file, reducing manual typing errors.
Visually impaired users can use this skill to extract on-screen text from images and have it read aloud via screen readers. The JSON mode provides text with confidence to assist in understanding context.
Researchers or analysts extract text from specific pages of PDF reports for sentiment analysis or keyword extraction. The skill allows page range selection and outputs text or JSON for further processing.
Provide the basic OCR feature for free with a daily page/image limit. Monetize by offering unlimited usage or advanced features like JSON output and batch processing via subscription.
Offer the OCR skill as a pay-per-call API for enterprises integrating text extraction into their workflows. Charge per image or PDF page processed, with volume discounts.
Bundle this OCR skill as a premium feature within a larger macOS productivity suite (e.g., note-taking or document management app). Charge a one-time purchase or subscription for the suite.
💬 Integration Tip
To integrate, ensure the Swift scripts are executable and placed in the 'scripts' directory. For JSON output, parse the stdout JSON programmatically.
Scored May 12, 2026
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Collaborative thinking partner for exploring complex problems through questioning