Agent Skills
› opensquilla/opensquilla
› awesome-webpage-image-download
awesome-webpage-image-download
GitHub用于从网页搜索结果中确定性下载图片。接收标准输入中的候选URL，通过Python HTTP API下载并验证MIME类型和文件头，按槽位ID保存文件，并输出下载完成或未完成状态记录。
Trigger Scenarios
需要批量下载指定URL的图片
AwesomeWebpageMetaSkill搜索后的资源获取阶段
Install
npx skills add opensquilla/opensquilla --skill awesome-webpage-image-download -g -y
SKILL.md
Frontmatter
{
"name": "awesome-webpage-image-download",
"homepage": "",
"metadata": {
"opensquilla": {
"risk": "high",
"requires": {
"bins": [
"python3"
],
"config": [
"awesome_webpage.output_dir"
]
},
"capabilities": [
"network-read",
"filesystem-write"
]
}
},
"entrypoint": {
"args": [
"--output-dir",
"{{ with.output_dir }}",
"--local-path-prefix",
"{{ with.local_path_prefix | default('project\/assets\/images') }}"
],
"parse": "text",
"stdin": "{{ with.payload }}",
"command": "python {baseDir}\/scripts\/image_download.py",
"timeout": 120
},
"provenance": {
"origin": "opensquilla-original",
"license": "Apache-2.0",
"maintained_by": "OpenSquilla"
},
"description": "Deterministic image downloader for AwesomeWebpageMetaSkill search results. Use as skill_exec to fetch candidate image URLs into the configured local project tree without sandboxed shell curl.",
"description_zh": "为AwesomeWebpageMetaSkill搜索结果提供确定性的图片下载器。作为skill_exec使用，将候选图片URL抓取到配置的本地项目目录，无需沙箱内的shell curl。",
"user-invocable": false,
"disable-model-invocation": true
}
AwesomeWebpage Image Download
Internal deterministic downloader used by AwesomeWebpageMetaSkill after the
bounded web-search step has produced candidate image URLs.
It receives normalized media slots and search output on stdin, downloads direct
image URLs with Python HTTP APIs, validates the response MIME/magic bytes, saves
files by slot_id, and emits IMAGE_READY: records plus
IMAGE_DOWNLOAD_INCOMPLETE: when any requested image slot remains unfilled.
Version History
- f662be3 Current 2026-07-31 11:47
- 7f72a32 2026-07-05 18:38
