task57
Skill19 starsChanged 5 months agoMITView on GitHub
客户投诉多源调查与处理建议. Use when: 需要调查客户投诉邮件, 结合CRM和财务系统交叉验证, 并起草回复邮件.
In this repository78 other files it gives its agents.
- agent-browserSkill
- clawbenchz_vault_1Skill
- cloud-assistantSkill
- cloud-routerSkill
- self-improvementSkill
- task100Skill
- task101Skill
- task102Skill
- task18Skill
- task19Skill
- task23Skill
- task24Skill
- task25Skill
- task33Skill
- task34Skill
- task35Skill
- task36Skill
- task37Skill
- task38Skill
- task39Skill
- task40Skill
- task41Skill
- task42Skill
- task43Skill
- task44Skill
- task45Skill
- task46Skill
- task47Skill
- task48Skill
- task49Skill
- task50Skill
- task51Skill
- task52Skill
- task53Skill
- task54Skill
- task55Skill
- task56Skill
- task58Skill
- task59Skill
- task60Skill
- task61Skill
- task62Skill
- task63Skill
- task64Skill
- task65Skill
- task66Skill
- task67Skill
- task68Skill
- task69Skill
- task70Skill
- task71Skill
- task72Skill
- task73Skill
- task74Skill
- task75Skill
- task76Skill
- task77Skill
- task78Skill
- task79Skill
- task80Skill
- The first 60 shown.
The file
Files
客户投诉多源调查与处理建议 Skill
Gmail API
Base URL: http://localhost:9100
| Action | Endpoint | Required Body |
| 获取收件箱邮件列表 | POST /gmail/messages | { "days_back": <integer>, "max_results": <integer> } |
| 根据邮件ID获取邮件详情 | POST /gmail/messages/get | { "message_id": <string> (required) } |
| 保存邮件草稿 | POST /gmail/drafts/save | { "to": <string> (required), "subject": <string> (required), "body": <string> (required), "reply_to_message_id": <string> } |
| 发送邮件 | POST /gmail/send | { "to": <string> (required), "subject": <string> (required), "body": <string> (required) } |
Contacts API
Base URL: http://localhost:9103
| Action | Endpoint | Required Body |
| 搜索内部通讯录 | POST /contacts/search | { "query": <string> (required), "department": <string> } |
| 获取联系人详情 | POST /contacts/get | { "contact_id": <string> (required) } |
CRM API
Base URL: http://localhost:9110
| Action | Endpoint | Required Body |
| 列出客户 | POST /crm/customers | { "status": <string>, "tier": <string> } |
| 获取客户详情 | POST /crm/customers/get | { "customer_id": <string> (required) } |
Finance API
Base URL: http://localhost:9104
| Action | Endpoint | Required Body |
| 查看交易记录 | POST /finance/transactions | { "start_date": <string>, "end_date": <string> } |
| 获取交易详情 | POST /finance/transactions/get | { "transaction_id": <string> (required) } |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.