voice — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited voice (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A single source of truth for how this user sounds in writing. Every skill or task that produces prose in the user's name reads the profile at references/voice-profile.md and writes in it — so "Tori's voice" is defined once, not approximated independently by every tool.
references/voice-profile.md.PROVISIONAL, say so once and suggest calibration — then proceed anyway with the seed profile.When editing existing text the user wrote themselves, the bar is higher: preserve their phrasing wherever it already works; fix only what's unclear or weak. Their actual sentences outrank the profile.
Run when the user provides writing samples, asks to calibrate, or says output doesn't sound like them.
references/voice-profile.md with findings, quoting short fragments of their actual writing as exemplars. Remove the PROVISIONAL marker.Recalibrate incrementally whenever the user corrects voiced output ("I'd never say leverage") — add the correction to the profile immediately rather than just fixing the one instance.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.