Install any skill in seconds. Free to start, no credit card required.
Get Started Free →op7418/feishu-fetch-doc
获取飞书云文档内容。返回文档的 Markdown 内容,支持处理文档中的图片、文件和画板(需配合 feishu_doc_media 工具)。
Passed 5 of 12 test cases with the skill, and 3 of 12 without it.
and 8 more in the full report
6 fixed4 passed either way11 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When saving embedded images or attachments extracted from Feishu document HTML tags using the media downloader tool, what resource_type value should be specified?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies media as the value for resource_type in feishu_doc_media. | Missed | Passed |
The instructions your model reads when the skill loads.
获取飞书云文档的 Markdown 内容(Lark-flavored 格式)。
文档中的图片、文件、画板需要通过 feishu_doc_media(action: download)工具单独获取!
返回的 Markdown 中,媒体文件以 HTML 标签形式出现:
图片:
<image token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc" width="1833" height="2491" align="center"/>
文件:
<view type="1">
<file token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc" name="skills.zip"/>
</view>
画板:
<whiteboard token="Z1FjxxxxxxxxxxxxxxxxxxxtnAc"/>
token 属性值feishu_doc_media 下载:
{
"action": "download",
"resource_token": "提取的token",
"resource_type": "media",
"output_path": "/path/to/save/file"
}
test cases passed, vs 3 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.