By varunr89
Extract text from images, PDFs, and videos using Apple Vision, tesseract, and MLX OCR
npx claudepluginhub varunr89/claude-marketplace --plugin ocr-toolkitExtract text from a directory of JPG/JPEG images into a single Markdown file using Apple Vision, tesseract, or MLX OCR
Extract text from PDF files using Apple Vision OCR, optimized for Apple Silicon
Extract text from video files by sampling frames and running Apple Vision OCR, with optional perceptual deduplication
Claude Code plugins for OCR, scheduling, flight search, transcription, and developer workflows.
claude plugin marketplace add varunr89/claude-marketplace
Then install individual plugins:
claude plugin install <plugin-name>
| Plugin | Description |
|---|---|
| codex-collab | Automated Codex CLI reviews during design and implementation |
| ocr-toolkit | Extract text from images, PDFs, and videos |
| when2meet | Create When2Meet events and pre-fill availability |
| safari-archiver | Archive Safari pages to Obsidian as clean markdown |
| transcription | Fast audio transcription using MLX Whisper |
| flight-optimizer | Multi-leg flight search with scoring |
| scenario-test | Azure infrastructure scenario testing |
| config-sync | Sync ~/.claude/ config via git |
| phone-a-friend | Consult other AI models for second opinions |
| resume-tailoring | Tailored resumes with branching experience discovery |
| devlog | Auto-generate dev log blog posts |
CI (every PR): Static validation + fresh install E2E on macos-14 ($0 API cost)
# Run locally
bash ci/test-fresh-install.sh "$PWD"
plugins/.claude-plugin/plugin.json with name, version, descriptionskills/*/SKILL.md with YAML frontmattertests/platform.json if plugin has OS/arch requirements.claude-plugin/marketplace.json to register the pluginUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Humanise text and remove AI writing patterns. Detects and fixes 24 AI tell-tales including inflated language, promotional tone, AI vocabulary, filler phrases, sycophantic tone, and formulaic structure.
Frontend design skill for UI/UX implementation
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents: true, providing patterns for 'use cache' directive, cacheLife(), cacheTag(), cache invalidation, and parameter permutation rendering.
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.