Summarize long-form text into 17 output formats using recursive map-reduce chunking.
npx skills add https://github.com/swyxio/skills --skill summarize-anything
Please help me install this Agent Skill. Skill: summarize-anything Source: https://github.com/swyxio/skills/tree/main/summarize-anything Command: npx skills add https://github.com/swyxio/skills --skill summarize-anything
Manually summarizing long-form content like transcripts, articles, and documents is tedious, and standard LLMs fail when input exceeds their context window. This Skill eliminates that bottleneck by handling text of any length (1k to 1M+ words) and repurposing it into dozens of usable formats without manual copy-pasting between tools.
Use the summarize-anything skill to turn the attached 2-hour podcast transcript into a YouTube description, chapter markers, and a tweet thread, emphasizing the guest's AI cancer treatment research.
High-intent search queries and answers about installing and using this skill.
To summarize long-form text exceeding standard LLM context windows, this tool uses recursive map-reduce chunking to break down inputs up to 1M+ words, process each segment, and synthesize the results into a cohesive output.
Yes, you can generate social media posts and YouTube metadata from a single podcast transcript by processing the text once to produce 17 distinct output formats, including tweet threads, video descriptions, and chapter markers.
Yes, this summarization tool supports local LLM backends like Ollama, alongside OpenAI, Anthropic, Gemini, and OpenRouter, with automatic backend selection based on input size.
You can steer a summary to emphasize specific topics like technical architecture by applying focus directives, which highlight chosen angles and guide the LLM to extract targeted information from the long-form text.
The maximum document length supported for map-reduce summarization is 1M+ words, automatically chunking the input on paragraph boundaries with overlap to ensure context preservation across large transcripts or codebases.
zjykzkIngest raw text data into an Obsidian wiki as searchable knowledge.
Marky-TeamSchedule and publish social media posts with captions and media via the Marky API.
lfnovoExtract and normalize text from URLs, PDFs, documents, and media.
hung-phanOptimize prompts for LLM applications with in-context learning and attack defenses.
