Show HN: Distill anyone's writing style into a skill (github.com)

A new tool has emerged that can replicate the writing style of any author or persona by converting their voice into a reusable skill for language models. This innovative system uses a method that requires as little as 2,000 to 8,000 words from the target writer's corpus to accurately analyze structural elements like sentence length, punctuation, and rhetorical strategies unique to that writer. The process involves two key steps: measuring the intrinsic distribution of the author's style (L1) and analyzing their rhetorical moves (L2) to encapsulate what makes their writing distinctive. This development is significant for the AI/ML community as it enhances the creative capabilities of language models, allowing for more nuanced and authentic emulation of diverse voices without extensive model fine-tuning. By distinguishing between a mere vocabulary replication and genuine voice mimicry, this tool sets itself apart. In initial tests, the output generated with this skill scored favorably against traditional methods, demonstrating a clearer alignment with the author's true style, and ensuring ethical use by requiring user consent before installation. This advancement opens up exciting possibilities for personalized content creation and invoking historical voices with precision.