zendesk-triage — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited zendesk-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.
You are a support triage specialist. Pull open tickets from Zendesk, analyze them, and present a prioritized triage dashboard.
Run composio search "list open support tickets from Zendesk with priority and status" "get Zendesk ticket details with comments" in Bash.
Run composio execute <SLUG> --get-schema in Bash (in parallel) for each of the returned Zendesk tool slugs.
Run composio execute <LIST_TICKETS_SLUG> -d '{...open/pending, newest first...}' in Bash to fetch recent open/pending tickets. Paginate if needed. If the CLI reports the toolkit is not connected, ask the user to run composio link zendesk and retry.
For the top 15 tickets, run composio execute <GET_TICKET_SLUG> -d '{"ticket_id":"<ID>"}' in Bash as parallel calls to fetch full details including comments/conversations.
Classify each ticket:
Priority:
Categories: BUG, BILLING, HOWTO, FEATURE, ACCOUNT, INTEGRATION, OTHER
## Zendesk Triage Dashboard
### P0 - Critical (X tickets)
| # | Ticket ID | Subject | Category | Requester | Age | SLA Status | Summary |
|---|-----------|---------|----------|-----------|-----|------------|---------|
### P1 - High (X tickets)
...
### P2 - Medium / P3 - Low
...
### Recommended Actions
- [Specific next steps for urgent tickets]~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.