Install
$ agentstack add skill-cuteweather-agent-image-search ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Pexels 图片检索与下载
目标
- 按关键词从 Pexels 检索真实图片并下载到本地目录。
- 输出图片来源追溯信息:
id、photographer、url。 - 严禁返回或使用任何 placeholder/dummy 图片链接。
API 配置
- Base URL:
https://api.pexels.com/v1/search - 环境变量:
PEXELS_API_KEY
检索规范
- 必须传
query(如landscape、nature mountain)。 - 可选参数优先按需求设置:
--per-page、orientation、size、color、locale。 --per-page取值范围为1-80,默认80。- 脚本会自动翻页直到达到
limit或无更多结果,不需要手工传page。 - 收到结果后,优先使用
photos[].src.large2x,若不存在再用photos[].src.original。 - 如果
photos为空,直接返回“无可用真实图片”,并建议更换 query 或过滤参数。
禁止占位符规则(硬约束)
- 禁止输出或下载任何占位图链接,包括但不限于:
placeholderdummy imagevia.placeholder.complacehold.co- 当无结果时,只能返回失败原因与改进建议,不能自动替换为占位图。
输出约定
- 默认输出目录由调用方给定(例如
./assets/pexels)。 - 命名建议:
__.jpg - 结果说明中包含:
- 下载文件路径
- Pexels
id photographer- 原始页面
url
工具脚本(独立文件)
- 仓库内脚本路径:
image-search/scripts/pexels_search_download.py - 作用:检索 + 过滤占位符链接 + 下载 + 输出来源信息(JSON 行)
SCRIPT="./image-search/scripts/pexels_search_download.py"
[ -f "$SCRIPT" ] || { echo "pexels_search_download.py not found"; exit 1; }
可执行示例(调用独立脚本)
示例 1:检索 landscape 并下载第一张
SCRIPT="./image-search/scripts/pexels_search_download.py"
python "$SCRIPT" \
--query "landscape" \
--output-dir "./assets/pexels" \
--limit 1
示例 2:带过滤条件检索并下载(横图 + 大图)
SCRIPT="./image-search/scripts/pexels_search_download.py"
python "$SCRIPT" \
--query "nature" \
--output-dir "./assets/pexels" \
--orientation landscape \
--size large \
--limit 1
示例 3:批量下载 5 张并按序号命名(去重)
SCRIPT="./image-search/scripts/pexels_search_download.py"
python "$SCRIPT" \
--query "city skyline" \
--output-dir "./assets/pexels" \
--per-page 15 \
--limit 5 \
--metadata-file "./assets/pexels/city_skyline.metadata.jsonl"
示例 4:下载 100 张(自动翻页,默认只打印汇总)
SCRIPT="./image-search/scripts/pexels_search_download.py"
python "$SCRIPT" \
--query "landscape" \
--output-dir "./assets/pexels" \
--per-page 15 \
--limit 100 \
--metadata-file "./assets/pexels/landscape.metadata.jsonl"
执行策略(给模型)
- 用户要求“找某类图片”时,优先执行本技能,不要返回示例 URL 或占位符。
- 失败时提供可执行修正建议(换 query、调
orientation/size/color、翻页)。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cuteweather
- Source: cuteweather/agent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.