bymassimodeluisa· 1 skill
Based on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.
$npx -y skills add massimodeluisa/recursive-decomposition-skill --skill recursive-decompositionInstalls into the current project.
Run `npx skills use "https://github.com/massimodeluisa/recursive-decomposition-skill" --skill "massimodeluisa/recursive-decomposition-skill/recursive-decomposition"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/massimodeluisa/recursive-decomposition-skill" that are relevant to the current task. Run `npx skills add "https://github.com/massimodeluisa/recursive-decomposition-skill"` and select the relevant skills, then follow their instructions.