Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deliver artifacts (files/images/voice) to current IM chat via gateway, returning a receipt. Use this as the only delivery proof for attachments. Text replies are sent automatically - only use this for file/image/voice attachments.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -3% | 0% |
| case-15 | ✓→✗ | ▼ Worse | -16% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -44% | 0% |
| case-17 | ✓→✗ | ▼ Worse | -16% | 0% |
通过网关向当前 IM 聊天交付附件（文件/图片/语音），并返回结构化回执。
| 参数 | 类型 | 必填 | 说明 | |-----|------|-----|------| | artifacts | array | 是 | 要交付的附件清单 | | mode | string | 否 | send 或 preview（默认 send） |
| 字段 | 类型 | 必填 | 说明 | |-----|------|-----|------| | type | string | 是 | file / image / voice | | path | string | 是 | 本地文件路径 | | caption | string | 否 | 说明文字 |
发送截图:
json{ "artifacts": [{"type": "image", "path": "data/temp/screenshot.png", "caption": "页面截图"}] }
发送文件:
json{ "artifacts": [{"type": "file", "path": "data/out/report.md"}] }
browser-screenshot: 网页截图desktop-screenshot: 桌面截图get-voice-file: 获取语音文件Other measured skills in the registry, with their headline benchmark lift.