// Use when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends. Triggers on "sentry 监控", "sentry 日报", "查看 sentry", "sentry report", "sentry monitor".
Use when the user wants to fix a Sentry issue, auto-repair a bug from Sentry, or create a fix PR for a Sentry error. Triggers on "修复 sentry", "fix sentry issue", "sentry 修复", "sentry fix".
Create a workspace role that follows the ROLE.md specification. Use when the user wants to create a new role, refine a role definition, or turn repeated responsibilities into a reusable routed role.
Control Windows desktop applications: open/operate apps, click controls, type text, scroll, keyboard shortcuts, window management, toggle options, lists and combos, etc. Note: NEVER invoke this skill for opening web pages/visiting websites — use browser-related tools instead. Trigger words: open app, operate app, control computer, click, type, scroll, switch, dropdown, select, modify, change to, set, check, uncheck, app-control, toggle.
List all AI API keys for the current team. Shows key aliases, masked key values, and spend per key. Use when a team member asks about their API key or wants to see who has access.
Manage AI API keys and budget for the current team. Owner-only operations include adding/removing member keys and setting budget limits. Use when the team owner wants to manage AI access.
Check AI usage and spend for the current team or individual member. Shows total spend, per-member breakdown, or personal usage. Use when someone asks about costs, budget, or how much has been used.
| name | sentry-monitor |
| description | Use when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends. Triggers on "sentry 监控", "sentry 日报", "查看 sentry", "sentry report", "sentry monitor". |
Scan both TeamClaw Sentry projects for unresolved fatal/high issues, analyze root causes, and push a summary report to WeCom.
| Project | Sentry Slug | Platform |
|---|---|---|
| Rust backend | ucar-inc/teamclaw | Rust |
| React frontend | ucar-inc/teamclaw-react | JavaScript React |
Run these two commands in parallel:
sentry issue list ucar-inc/teamclaw --query "is:unresolved" --json --fields shortId,title,priority,level,status --limit 20
sentry issue list ucar-inc/teamclaw-react --query "is:unresolved" --json --fields shortId,title,priority,level,status --limit 20
Filter results: keep only issues where level is fatal OR priority is high.
If no issues match, skip to step 4 with "全部正常" message.
For each filtered issue (max 10 total), perform local root cause analysis:
sentry issue view <shortId> --json
From the stack trace / error message, identify the relevant source files and functions in the codebase.
Read those source files to understand the code context around the crash/error site.
Produce a one-sentence root cause summary based on the stack trace + source code analysis.
Run analyses in parallel where possible (use Agent tool with parallel subagents). Each subagent should:
sentry issue view <shortId> --jsonIf analysis cannot determine a root cause, use the error title as-is.
Build a report in this exact format:
Sentry 日报 <YYYY-MM-DD>
【Rust 后端】N 个高优 issue
• <shortId> [<level>] <title> — 根因：<root cause summary>
• ...
【React 前端】N 个高优 issue
• <shortId> [<level>] <title> — 根因：<root cause summary>
• ...
修复命令：/sentry-fix <top-issue-id>
If a project has zero matching issues, omit that section entirely.
Send the formatted report to the TeamClaw group chat:
wecom-cli msg send_message '{"chat_type": 2, "chatid": "wrOOClYgAA5gMJijxEUfWC6M0RAjwlWQ", "msgtype": "text", "text": {"content": "<report text>"}}'
If no fatal/high issues exist across both projects, send:
Sentry 日报 <YYYY-MM-DD> — 全部正常，无高优 issue
/sentry-monitor/loop 24h /sentry-monitorsentry CLI is not authenticated, prompt the user to run sentry auth login.