Token导航 LogoToken导航TokenDH.com
图像处理敏感数据github未标认证来源可访问许可证需确认审计提醒

stock-images库存图片

Agent Skill

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

总安装

703

周安装

29

GitHub Stars

406

下载量

230
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:stock-images(库存图片)
来源仓库:https://github.com/openclaudia/openclaudia-skills
仓库路径:skills/stock-images
安装命令:
npx skills add https://github.com/openclaudia/openclaudia-skills --skill stock-images
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/openclaudia/openclaudia-skills --skill stock-images

简介

stock-images 用于辅助图像生成、图片编辑或视觉素材处理,适合让 Agent 根据文本生成图片或调用图像模型工作流。

  • 适用于图像处理与视觉内容创作场景,支持提示词整理与版权合规检查。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,具体用法需结合原始 README 进一步确认。
  • 使用时需确认输入图片、版权来源及模型限制,涉及人物或品牌素材时应额外核对授权与真实性。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Stock Images from Unsplash

Search Unsplash for images, download them, and optionally add text overlay.

Prerequisites

  • Unsplash API key in UNSPLASH_CLIENT_ID environment variable (register at unsplash.com/developers)
  • Python 3 with requests and Pillow (for text overlay)

Usage

Search and Download

import os, requests, random

def search_unsplash(query, orientation=None, count=30):
    """Search Unsplash and return photo results."""
    params = {
        "query": query,
        "per_page": count,
        "client_id": os.environ["UNSPLASH_CLIENT_ID"],
    }
    if orientation:
        params["orientation"] = orientation  # landscape, portrait, squarish
    resp = requests.get("https://api.unsplash.com/search/photos", params=params)
    resp.raise_for_status()
    return resp.json()["results"]

def download_photo(photo, output_path):
    """Download a photo's regular-size image."""
    url = photo["urls"]["regular"]
    resp = requests.get(url)
    resp.raise_for_status()
    with open(output_path, "wb") as f:
        f.write(resp.content)
    # Trigger download tracking (required by Unsplash API terms)
    requests.get(photo["links"]["download_location"],
                 params={"client_id": os.environ["UNSPLASH_CLIENT_ID"]})
    print(f"Photo by {photo['user']['name']} on Unsplash")

# Example: search and download a random matching photo
results = search_unsplash("nature landscape", orientation="landscape")
photo = random.choice(results)
download_photo(photo, "./image.jpg")

With Text Overlay

from PIL import Image, ImageDraw, ImageFont

def add_text_overlay(image_path, title, subtitle=None, output_path=None):
    """Add title/subtitle overlay to an image."""
    img = Image.open(image_path)
    draw = ImageDraw.Draw(img)
    width, height = img.size

    # Semi-transparent overlay at bottom
    overlay_height = height // 4
    overlay = Image.new("RGBA", (width, overlay_height), (0, 0, 0, 128))
    img.paste(overlay, (0, height - overlay_height), overlay)

    # Title text
    try:
        font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", 48)
        small_font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 28)
    except OSError:
        font = ImageFont.load_default()
        small_font = font

    title_y = height - overlay_height + 20
    draw.text((40, title_y), title, fill="white", font=font)

    if subtitle:
        draw.text((40, title_y + 60), subtitle, fill=(200, 200, 200), font=small_font)

    out = output_path or image_path
    img.save(out)

add_text_overlay("./image.jpg", "My Blog Post Title", "A short description")

CLI Options to Support

When building a script, support these options:

OptionDescription
--querySearch query string (required)
--outputOutput file path (required unless listing)
--orientationFilter: landscape, portrait, or squarish
--colorColor filter (e.g., blue, green, black_and_white)
--pickSelection mode: random (default) or first
--titleTitle text to overlay on the image
--subtitleSubtitle text (only used with --title)
--listList results without downloading
--countNumber of results to fetch, max 30 (default: 30)

Important Notes

  • Attribution required: Unsplash requires crediting the photographer. Always include Photo by {name} on Unsplash in your output.
  • Download tracking: Trigger the download endpoint as required by Unsplash API terms.
  • Rate limits: 50 requests/hour for demo apps, 5000/hour for production apps.
  • Image sizes: raw (original), full (high-res), regular (1080px wide), small (400px), thumb (200px).

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.91%
按下载量换算85

Claude

29.85%
按下载量换算69

Cursor

19.62%
按下载量换算45

Gemini CLI

9.59%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills