triage — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited triage (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.
Batch intake for the Chief of Staff: turn a chaotic pile into a sorted, owned, prioritized list — the front-door /structure does for one fuzzy input, /triage does for many.
/daily — fold the triaged items into today.## Triage — <date> (<N> items)
| # | Item (1 line) | Type | Owner | Next step | Priority | Route |
|---|---------------|------|-------|-----------|----------|-------|
| 1 | … | ask/FYI/decision/task | <who> | <action> | P1/P2/P3 | /structure · /decide · /draft · done |
**Needs your decision** — the short list only the user can resolve (with the framed choice).
**Delegated** — items routed to the team (with owner + next step).
**Drop / FYI** — no action needed (so they're off the list)./structure (needs framing), /decide (needs a call), /draft (needs a reply). Simple ones get a one-line next step.decision-type item into "Needs your decision" with the choice framed for a fast yes/no./structure on the flagged items, /draft the replies (internal may send; external = draft), and/or feed the result into /daily.L2 — sorts and routes; the human decides and sends. Triage never auto-replies.
references/voice.md register; internal-to-team may send.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.