text▌

Transcribe audio and video to text with speaker identification, word-level timestamps, and 90+ language support. \n \n Two models available: scribe_v2 for batch transcription with high accuracy, and scribe_v2_realtime for live transcription with ~150ms latency \n Speaker diarization labels each word with speaker ID; keyterm prompting helps recognize domain-specific vocabulary and proper nouns \n Word-level timestamps include type classification (word, spacing, audio event) for precise timing and

Reduces token count in prompts and docs by 20–40% using 41 research-backed optimization rules. \n \n Applies rules across six categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension \n Three optimization modes: light (text cleanup only), medium (balanced restructuring, default), and deep (aggressive compression and rephrasing) \n Processes single files or entire directories of markdown files, with built-in quality checks for reference vali

Extractive summarization from long documents with flexible length control and batch processing. \n \n Supports three algorithms (TextRank, LSA, frequency-based) with configurable language support \n Control summary length by ratio, sentence count, or word count; optionally preserve original sentence order \n Extract key points as bullet-point summaries alongside full-text summaries \n Batch process multiple documents or entire directories with consistent parameters \n Available as Python API or

Extract cognitive patterns and thinking fingerprints from any text to analyze reasoning and decision-making styles.

This skill provides a workflow for transforming data into structured narrative text visualizations using T8 Syntax - a declarative Markdown-like language for creating data narratives with semantic entity annotations.

File Organization: Split structure. See references/ for detailed implementations.

Invoke this skill in the following situations:

Generate professional, optimized prompts for AI image generation tools with primary support for Google Gemini (Nano Banana), plus Midjourney, Stable Diffusion, DALL-E, Leonardo.ai, and others.

Transcribe audio to text via inference.sh CLI.

This skill provides tools and guidance for extracting text from PDFs in formats suitable for language model consumption.