notification — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited notification (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.
Send messages to mobile / desktop devices. Use this skill for any notification-related request.
Activate when the user:
/notification or asks to send/test a notification| Field | Description |
|---|---|
--title | The task or notification name in the user's own words (e.g. "Run test suite", "Test notification") |
--message | Concise outcome summary (max 200 chars). On failure, state what failed and why. |
--urgent | Add this flag when the user says "urgent", "important", "high priority", or "asap". Omit otherwise. |
--successed | Add this flag when the task succeeded. Omit on failure. |
node "<skill-directory>/scripts/send.mjs" \
--title "<title>" \
--message "<message>" \
[--urgent] \
[--successed]--successed so the user knows to check back. A failure notification is as valuable as a success one — the user may be AFK.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.