image-collector for Openclaw

A professional image procurement tool designed to automatically collect, verify, and optimize news-related images from official sources.

lunadelo
v1.0.0
Apr 1, 2026
0
816
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install image-collector

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install image-collector using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is image-collector?

The image-collector skill is a specialized utility for the Openclaw Skills ecosystem designed to automate the visual asset gathering process for AI tech news. It solves the common problem of low-quality or irrelevant imagery by prioritizing official press releases and authoritative media outlets while strictly filtering out watermarked or low-resolution content.

By leveraging automated verification pipelines, this skill ensures that every image collected is contextually relevant to the news topic. It moves beyond simple scraping by implementing resolution thresholds and metadata keyword matching, providing a polished, professional look for any automated content generation workflow.

image-collector Use Cases

  • Automating image sourcing for daily AI technology news reports.
  • Filtering out watermarked images from web search results to maintain brand professionalism.
  • Ensuring high-resolution standards for media assets in automated publishing pipelines.
  • Verifying the relevance of scraped images against specific news headlines and keywords.

How image-collector Works

  1. Source Validation: The skill checks potential image URLs against a whitelist of high-priority official domains.
  2. Watermark Detection: Scans the corners and bottom of images to detect and filter out logos or copyright text.
  3. Quality Inspection: Validates that the image meets minimum resolution requirements (800x600) and checks for compression artifacts.
  4. Relevance Verification: Performs keyword matching between the news metadata and the image metadata/filename.
  5. Final Output: Exports optimized, verified images ready for immediate use in news articles.

image-collector Setup

To get started with image-collector in your Openclaw Skills environment, first verify your local dependencies:

bash ~/.openclaw/workspace/skills/image-collector/scripts/check-deps.sh

Ensure you have Python 3.8+ and the necessary imaging libraries installed:

pip install Pillow requests

image-collector Data Schema & Taxonomy

The skill organizes collected assets and validation logs using the following structure:

Feature Requirement / Logic
Resolution Minimum 800x600 pixels
Priority P0: Official Sites (Apple, OpenAI) > P1: Authority Media (Reuters)
Forbidden Unsplash, Pixabay, or WeChat (mmbiz) sources
Match Score Keyword matching between news title and image filename

image-collector Advanced Features

  • Multi-stage source prioritization (P0-P3) to ensure maximum asset authority.
  • Integration with web-access skill for manual screenshot optimization when automated collection fails.
  • Automatic metadata scoring for context-aware image selection.
  • Built-in optimization routine for existing local images via the --optimize flag.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Github Stars: 0
forks: 0

Featured*