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/composio-community/support-skills --skill weekly-digest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。
Automatically analyze and tag untagged [Gorgias](https://composio.dev/toolkits/gorgias) tickets based on content.
Extract a structured bug report from a support ticket and create a [Linear](https://composio.dev/toolkits/linear) issue.
Summarize customer support/sales calls from [Dialpad](https://composio.dev/toolkits/dialpad) or [Leexi](https://composio.dev/toolkits/leexi) call logs
基于 SOC 职业分类
正在显示 SKILL.md
| name | weekly-digest |
| description | Generate a weekly support digest and post it to [Slack](https://composio.dev/toolkits/slack) |
| disable-model-invocation | true |
You are a support reporting analyst. Generate a comprehensive weekly support digest covering ticket volume, trends, top issues, and team performance, then post it to Slack.
Run composio search "list support tickets from Gorgias filtered by date range" "get ticket details from Gorgias" "send a formatted message to Slack channel" in Bash.
Run composio execute GORGIAS_LIST_TICKETS -d '{...past 7 days...}' in Bash to pull all tickets from the past 7 days. Paginate to get the complete set. If the CLI reports the toolkit is not connected, ask the user to run composio link gorgias and retry.
For a representative sample (up to 25 tickets), run composio execute GORGIAS_GET_TICKET -d '{"ticket_id":"<ID>"}' in Bash as parallel calls to get response time data and message details.
## Weekly Support Digest
**Week of:** [Monday date] - [Sunday date]
### At a Glance
- New tickets: X (+/-Y% vs last week)
- Resolved: X
- Still open: X
- Avg first response: Xh
- Avg resolution time: Xh
- CSAT: X% (if available)
### Top Issues This Week
1. [Issue category] - X tickets - [brief description of trend]
2. [Issue category] - X tickets
3. [Issue category] - X tickets
### Notable Tickets
- **Biggest fire:** #[ID] - [what happened and how it was resolved]
- **Longest open:** #[ID] - [status and why]
- **Best resolution:** #[ID] - [quick/creative resolution worth highlighting]
### Trends
- [Any emerging patterns]
- [Issues that are growing/shrinking]
- [Product areas generating the most tickets]
### Recommendations
- [Process improvements]
- [Product fixes that would reduce ticket volume]
- [Knowledge base articles to create/update]
Show the digest to the user for review. After confirmation:
composio execute SLACK_FIND_CHANNELS -d '{...}' in Bash to find the target Slack channel, parse the JSON output for the channel IDcomposio execute SLACK_SEND_MESSAGE -d '{"channel":"<channel id>","text":"<digest>"}' in Bash