用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/kmavrodis/kratos-agent --skill ticket-triage命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Read the plant-floor Azure IoT surface — device twins (spindles, conveyors, robotic arms, vision systems), time-series telemetry with pre-annotated alarms, downtime events with cause codes and lot ids, and per-line OEE rollups (Availability × Performance × Quality).
Share generated files (PDFs, charts, CSVs) with Frank by writing them to /tmp and referencing the absolute path. The frontend auto-converts /tmp paths into download links.
Build the downloadable incident brief PDF — cover + KPI strip + OEE chart + downtime timeline + root-cause narrative + supplier/material signals + recommended actions + sign-off, per SOP §7.1. Renders via the inline HTML template + Playwright.
基于 SOC 职业分类
正在显示 SKILL.md
| name | ticket-triage |
| description | Triage one ticket end-to-end — gather context, search the KB for known fixes, propose the next action |
| enabled | true |
Use this skill when the user asks you to triage, brief on, look at, or "tell me about" a specific ticket (e.g. "Triage INC-7001", "What's happening on INC-7002?", "Walk me through that VIP ticket").
This is a read-heavy skill. No writes happen automatically — if a fix is obvious, propose it as a next step and let the user decide whether to execute it via the appropriate write skill.
In parallel where possible:
servicenow_get_ticket(ticket_id) — the ticket itselfservicenow_list_work_notes(ticket_id) — the conversation historyservicenow_get_user(caller_id) — who raised it (note VIP flag)servicenow_get_ci(ci_id) if the ticket has one — what's the impacted systemUse the ticket's tags and short_description keywords to query servicenow_search_kb. If the ticket has kb_article_ids already linked, fetch those via servicenow_get_kb_article and lead with them.
# {Ticket Number} — Triage
## Snapshot
- **Title**: Cannot log in to Workday — MFA loop
- **Priority**: P3 · Medium urgency · Low impact
- **State**: In Progress · Assigned to Aaron Cole (AGT-301), Endpoint
- **Opened**: 2 hours ago (08:14 UTC) · SLA: on track
- **Caller**: Jamal Carter (USR-2102) — Field Sales — Americas
## What's known
- Last work note (AGT-301, 9 minutes ago): "Time skew on the device — MFA TOTP off by 90s. Asked user to enable automatic time sync."
- Prior public reply from user: tried token reset, still looping.
- CI: Olympus Identity Platform (CI-IDP-01) — currently Operational.
## Likely fix (from KB-200)
> Most common cause is device time skew (TOTP off by >30s). KB-200 documents the auto-time-sync remediation and includes a Powershell snippet if the user is on Windows.
This matches the agent's last work note exactly — looks like the right path.
## Recommended next action
1. Wait 5 minutes for the user to enable time sync, then ask them to retry.
2. If still failing, escalate to Identity & Access (queue) and consider clearing the cached MFA token in Entra per KB-200 step 4.
3. Update ticket state → Resolved once the user confirms sign-in works.
If you'd like me to add a public note nudging the user to retry, just say so.