text▌

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

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

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

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

Natural speech synthesis from text across 70+ languages with multiple quality and latency models. \n \n Six models available ranging from highest-quality eleven_v3 to ultra-low-latency eleven_flash_v2_5 (~75ms), with language and speed tradeoffs documented \n Supports 13+ output formats including MP3, PCM, WAV, Opus, and telephony codecs (μ-law, A-law) for web, streaming, and real-time applications \n Fine-tune voice characteristics via stability, similarity boost, style, speaker boost, and spee

Remove signs of AI-generated writing to enhance text's natural flow.

Convert text to natural speech via inference.sh CLI.

Generate speech audio from text using HeyGen's Starfish TTS model with voice, speed, and pitch control. \n \n List available TTS voices by language and gender, then generate audio files with customizable speed (0.5–1.5) and pitch (−50 to 50) \n Supports multilingual voices with locale selection (e.g., pt-BR ) and SSML-style break tags for pauses within text \n Returns audio URL, duration, request ID, and word-level timestamps for caption syncing or timed overlays \n Requires HEYGEN_API_KEY envir

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