follow-up — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited follow-up (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.
Find emails that need follow-up and draft contextual responses.
Find emails you sent that received no reply after N days:
messages(action="search", query="SINCE 2026-03-16 BEFORE 2026-03-20", folder="Sent", account="...")Re: prefix):messages(action="search", query="SUBJECT \"Re: <original subject>\" FROM <recipient>")
No reply after 5 days:
1. "API Integration Proposal" to [email protected] (sent Mar 18)
Original: Asked about timeline for API access
2. "Invoice #2024-003" to [email protected] (sent Mar 16)
Original: Sent invoice, requested payment confirmationFind received emails you flagged/starred but never responded to:
messages(action="search", query="FLAGGED", account="...")Then for each flagged email, check Sent folder for a reply with matching subject. If none found, it needs attention.
For each follow-up candidate:
send(action="reply", message_id="<original_msg_id>", body="<follow-up text>")Only use send(action="send") for new conversations.
Check all accounts, same as inbox-review:
messages(action="list_accounts")
# Iterate each account's Sent folder~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.