proof — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited proof (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.
Proofread and lightly copy edit text while preserving wording, order, tone, and meaning.
proof.Never reply with the corrected file contents inline as a substitute for editing the file.
proof vs good-proseUse proof when the request is about correctness without stylistic change.
Use good-prose when the request asks for writing-quality changes or substantial edits.
If intent is ambiguous:
good-prose rewrite.Before editing, identify what to proofread, in this order:
<ide_selection> tag with content → treat the selection as the target.If the selection is from a file, edit the file at those lines; otherwise reply inline.
<ide_opened_file> tag is present → treat the opened file as the target.State the inferred file in your first message (e.g., "Proofreading TODO.md — the file open in your IDE.") and proceed.
No major rewrite-needed issues found. or a Flagged issues list.No major rewrite-needed issues found. or a Flagged issues list.Flagged issues format: original snippet, reason it was not directly edited, and suggested revision.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.