image-to-text-pdf
Convert a finished raster image, especially a generated poster or visual resume, into an image-based PDF with an additional selectable, copyable, searchable text layer. Use when the image is the final visual layout, when recreating that layout in PPT, HTML, or LaTeX would be fragile, and when the user needs both a final invisible-text PDF and a visible inspection PDF for checking OCR or text-layer placement.
What this skill does
# Image to Text PDF Turn a finished raster image into a PDF while preserving the image exactly and adding a transparent text layer for selection, copying, and search. ## Workflow 1. Get the complete image. - Treat the image as the visual source of truth. - Keep the original image dimensions; the layout coordinates should use the same pixel coordinate space whenever possible. 2. Build a text-layer layout JSON. - Prefer OCR or a vision model that returns text boxes over trying to infer positions manually. - Use the user's source text to correct OCR transcription. OCR boxes determine position; the source text determines final copyable content. - Read `references/ocr-alignment.md` when you need guidance for extracting, correcting, or prompting for box-level text. - Read `references/layout-json.md` for the exact JSON schema. 3. Generate both PDFs. ```bash python scripts/compose_image_text_pdf.py \ --image /path/to/image.png \ --layout /path/to/layout.json \ --output /path/to/image-text.pdf \ --debug-output /path/to/image-text-check.pdf ``` For CJK or other non-Latin text, pass a Unicode font: ```bash python scripts/compose_image_text_pdf.py \ --image /path/to/image.png \ --layout /path/to/layout.json \ --output /path/to/image-text.pdf \ --debug-output /path/to/image-text-check.pdf \ --font-file /path/to/NotoSansCJK-Regular.ttc ``` 4. Inspect the debug PDF before delivering. - The final PDF should look like the image-only source. - The debug PDF should show highlighted text boxes and visible text where the hidden layer will be placed. - If a highlighted box is shifted, fix the layout JSON, not the image. - If copy/paste text is wrong, fix the `text` field in layout JSON, not the OCR image. ## OCR Word Conversion When an OCR tool returns word-level boxes, convert them to line-level layout items: ```bash python scripts/ocr_words_to_layout.py \ --ocr /path/to/ocr.json \ --output /path/to/layout.json \ --image-width 1536 \ --image-height 2048 \ --source-text /path/to/source.txt ``` The converter accepts common JSON shapes containing `words`, `items`, `textAnnotations`, or nested page/line/word objects. It groups nearby words into lines and can replace OCR text with the closest line from the source text when the match is strong. ## Practical Rules - Keep text boxes line-level unless a paragraph must be selected as one unit. Line-level boxes are easier to position and debug. - Do not try to match the rasterized font exactly. The hidden layer only needs close geometry and correct text. - Use the visible inspection PDF as the validation artifact. It should make every embedded text span obvious. - For generated images, ask the image-generation step to keep text in large, separated blocks. Dense tiny text is harder for OCR and manual correction. - Preserve the image as the background instead of rebuilding the layout in presentation or web formats.
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ 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.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.