Voice-Matched Content System
ReviewAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill is coherent, but it is designed to mimic another person’s writing voice and make AI-written content sound non-AI without clear consent or disclosure guardrails.
Install or use this only if you intend to analyze your own writing or have clear permission from the person whose voice is being modeled. Do not use it to impersonate someone, hide AI authorship where disclosure matters, or process private messages without consent.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A user could use the skill to create messages or posts that appear to be written by another person, which could harm trust or reputation.
The skill is explicitly designed to imitate a person’s writing and reduce signs that the content was AI-generated. Without visible consent or disclosure boundaries, this can mislead readers about who authored the content.
Extract someone's authentic writing voice from samples, build a complete Voice DNA profile, then generate content that sounds like them — not AI.
Use only with samples you own or have permission to use, and disclose AI assistance where authorship or identity could matter.
Private writing samples or personal style details could be retained in a reusable profile if the user or agent saves it.
The skill creates a reusable profile from writing samples. While user-directed and purpose-aligned, the profile may contain durable inferences about a person’s communication style and may be reused in later tasks.
After extraction, generate a structured Voice DNA document. This becomes the permanent reference for all future content.
Avoid sharing sensitive samples, remove private details before analysis, and store or reuse the Voice DNA Profile only with the subject’s permission.