Smart Image Finder

Smart image search and download tool for AI agents. Three methods: news website extraction, Brave image search, AI generation. Use cases: article illustratio...

Security Scan

The skill's instructions and scripts largely match its stated purpose (finding/downloading images), but there's an important incoherence: the SKILL.md requires a Brave API key in examples while the skill metadata does not declare any required environment variables or credentials — users should confirm the missing credential declaration and be cautious about network scraping and copyright.

Purpose & Capability

The name/description (image search/download via news extraction, Brave search, AI generation) align with the included README, SKILL.md examples, and two shell scripts. The provided patterns and download/verify workflows are consistent with the stated purpose.

Instruction Scope

SKILL.md instructs the agent to fetch arbitrary webpages and call external image APIs (Brave, Pollinations) and to download files via curl. Those actions are within the skill's scope, but the docs explicitly show using an environment variable BRAVE_API_KEY (and rely on CLI tools like jq/file/identify) even though no env var is declared in the registry metadata. The instructions also suggest scraping many news sites directly; while functional, that can hit sites requiring JS/cookie/signatures (which the docs acknowledge) and may have legal/copyright implications.

Install Mechanism

No install spec; the skill is instruction-only plus two small shell scripts. There are no downloads from untrusted URLs or package installs. The scripts are plain Bash using curl/file/jq/identify — low install risk.

Credentials

Registry metadata lists no required environment variables, but SKILL.md and README examples use BRAVE_API_KEY for Brave image search. This mismatch is an incoherence: if users intend to use the Brave method they must provide a secret not declared by the skill. No other secrets are requested, which is proportionate to purpose, but the missing declaration reduces transparency.

Persistence & Privilege

The skill is not always-enabled and does not request persistent privileges or system-wide configuration changes. It merely runs CLI commands and downloads images; autonomous invocation is allowed by default (platform normal) but not combined with other high-risk flags.

What to consider before installing

Things to consider before installing: - Transparency: SKILL.md shows using a BRAVE_API_KEY for the Brave image-search examples, but the registry metadata does not declare this required env var — ask the publisher to add BRAVE_API_KEY to requires.env so it’s explicit. - Network & secrets: the skill performs arbitrary HTTP requests (curl) and will download remote files. Only provide the Brave API key if you trust the skill and the agent environment; do not reuse high-privilege credentials. - Legal/copyright: the skill scrapes news sites and downloads images. Confirm you have the right to use downloaded images for your intended purpose. - Operational: the scripts require curl, grep, jq, file, and optionally ImageMagick (identify). Ensure those tools are available in the agent runtime. - If you need higher assurance: ask for the publisher contact or source repo, request that required env vars be declared, and review any agent logs for unexpected outbound requests when the skill runs. Given the single clear incoherence (undeclared BRAVE_API_KEY) and otherwise straightforward scripts, the skill may be legitimate but warrants caution and clarification before trusting with credentials or production use.

A complete solution for AI agents to find high-quality images for articles, dashboards, and content creation.

No browser required — all methods work via command line in the background.

Core Methods

Method	Best For	Pros	Cons
News Site Extraction	Specific news events	Authentic, high-res, authoritative	Need to know source
Brave Image Search	General keywords	Fast, free, good relevance	Variable quality
AI Generation	Concept art, custom visuals	Fully customizable	Requires good prompts

---

Method 1: News Website High-Res Extraction (No Browser)

Workflow: curl + grep (Recommended)

Extract image URLs directly from HTML without opening a browser:

# Step 1: Fetch page HTML and extract image URLs
curl -sL "https://www.reuters.com/world/article-slug/" | \
  grep -oE 'https://www\.reuters\.com/resizer/v2/[^"]+\.jpg[^"]*' | head -3

# Step 2: Download with HD parameters
curl -sL -o photo.jpg "https://www.reuters.com/resizer/v2/xxx.jpg?width=3000&quality=100"

# Step 3: Verify it's actually an image
file photo.jpg  # Should show: JPEG image data

Source-Specific Extraction Patterns

# Reuters
curl -sL "$URL" | grep -oE 'https://www\.reuters\.com/resizer/v2/[^"]+\.jpg[^"]*' | head -3

# TechCrunch
curl -sL "$URL" | grep -oE 'https://techcrunch\.com/wp-content/uploads/[^"]+\.(jpg|png)' | head -3

# Bloomberg
curl -sL "$URL" | grep -oE 'https://assets\.bwbx\.io/images/[^"]+\.(jpg|webp)' | head -3

# BBC
curl -sL "$URL" | grep -oE 'https://ichef\.bbci\.co\.uk/news/[0-9]+/[^"]+\.jpg' | head -3

# France24
curl -sL "$URL" | grep -oE 'https://s\.france24\.com/media/display/[^"]+\.jpg' | head -3

# Spaceflight Now (WordPress)
curl -sL "$URL" | grep -oE 'https://spaceflightnow\.com/wp-content/uploads/[^"]+\.jpg' | head -3

# ThePaper (澎湃)
curl -sL "$URL" | grep -oE 'https://imagepphcloud\.thepaper\.cn/pph/image/[^"]+\.jpg' | head -3

Verified Sources (Direct Download Works)

Tech/AI Category

Source	CDN Pattern	HD Parameters	Notes
TechCrunch	techcrunch.com/wp-content/uploads/	?w=2048	Most stable ✅
Bloomberg	assets.bwbx.io/images/	Direct HD	WebP format

Politics/International Category

Source	CDN Pattern	HD Parameters	Notes
Reuters	reuters.com/resizer/v2/	?width=3000&quality=100	Most stable ✅
BBC	ichef.bbci.co.uk/news/1024/	/1024/ max	Limited to 1024px
NBC News	media-cldnry.s-nbcnews.com/image/	Direct download	Medium size
France24	s.france24.com/media/display/	w:1920	Adjustable ✅

Space/Science Category

Source	CDN Pattern	HD Parameters	Notes
Spaceflight Now	spaceflightnow.com/wp-content/uploads/	Remove size suffix	WordPress standard

Chinese Sources

Source	CDN Pattern	Notes
ThePaper (澎湃)	imagepphcloud.thepaper.cn/pph/image/	Direct download ✅

Sources Requiring Manual Save

Source	Issue	Workaround
Guardian	URL signature validation	Right-click save
The Verge	Complex CDN format	Use Brave search instead
Wired	Page protection	Manual save
CNN	URL extraction difficult	Use Brave search instead
AP News	Parameter adjustment fails	Save original manually

HD Parameter Quick Reference

# Reuters
?width=3000&quality=100

# TechCrunch
?w=2048

# BBC (replace number in URL)
/1024/  # Max available

# France24
w:1920

# NBC News (URL parameter)
t_fit-1500w

---

Method 2: Brave Image Search (No Browser)

Best for: Quick general-purpose images, automated workflows.

Basic Usage

# Set API Key (first time)
export BRAVE_API_KEY="your_api_key"

# Search images
curl -s "https://api.search.brave.com/res/v1/images/search?q=keyword&count=10" \
  -H "X-Subscription-Token: $BRAVE_API_KEY" | jq '.results[] | {title, url: .properties.url, width: .properties.width}'

# Get first image URL directly
curl -s "https://api.search.brave.com/res/v1/images/search?q=SpaceX%20Starship&count=1" \
  -H "X-Subscription-Token: $BRAVE_API_KEY" | jq -r '.results[0].properties.url'

Rate Limiting ⚠️

Brave API has rate limits. When making multiple searches:

# Add delay between requests (1-2 seconds recommended)
for query in "query1" "query2" "query3"; do
  curl -s "https://api.search.brave.com/res/v1/images/search?q=$query&count=1" \
    -H "X-Subscription-Token: $BRAVE_API_KEY" | jq -r '.results[0].properties.url'
  sleep 2  # Wait 2 seconds between requests
done

Best practices:

• Free tier: ~1 request/second max
• Add sleep 1 or sleep 2 between batch requests
• If you get 429 (rate limited), wait 60 seconds before retrying

Search Tips

1. Add year: SpaceX Starship 2025 is more precise than SpaceX Starship
2. Add event terms: Keir Starmer Xi Jinping Beijing handshake beats UK China meeting
3. Site restriction: site:reuters.com Trump tariff limits to specific source

One-liner: Search and Download

# Search, get first result URL, download
IMG_URL=$(curl -s "https://api.search.brave.com/res/v1/images/search?q=SpaceX%20launch%202025&count=1" \
  -H "X-Subscription-Token: $BRAVE_API_KEY" | jq -r '.results[0].properties.url')
curl -sL -o spacex.jpg "$IMG_URL"
file spacex.jpg

Verify Image Accessibility

# Check if URL returns 200
curl -sI "$IMAGE_URL" | head -1
# Should return: HTTP/2 200

# Check content type
curl -sI "$IMAGE_URL" | grep -i content-type
# Should return: content-type: image/jpeg or image/png

---

Method 3: AI Image Generation (No Browser)

Best for: Concept images, creative illustrations, when real photos unavailable.

Free Option: Pollinations

# Generate image (completely free, no API key needed)
curl -sL -o output.jpg "https://image.pollinations.ai/prompt/description?width=1920&height=1080&nologo=true"

# Example: Tech-style AI concept image
curl -sL -o ai-concept.jpg "https://image.pollinations.ai/prompt/futuristic%20AI%20chip%20glowing%20blue%20on%20dark%20background%20minimalist%20tech%20style?width=1920&height=1080&nologo=true"

Prompt Best Practices

# Good prompt structure
{subject} + {style} + {color tone} + {composition} + {exclusions}

# Example
"Sam Altman speaking at conference, professional photo, warm lighting, 
 shallow depth of field, high resolution, no text no watermark"

# 16:9 cover image
"... 16:9 aspect ratio, horizontal composition, clean space on right for text overlay"

# Avoid garbled text
"... no text, no letters, no words, no watermarks"

Platform Comparison

Platform	Prompt Language	Size Params	Notes
Pollinations	English	width/height	Free unlimited
Jimeng (即梦)	Chinese	16:9/1:1	Best for Chinese scenes
DALL-E	English	1792x1024	Highest quality

---

Complete Workflow Example (All CLI, No Browser)

Scenario: Find image for "UK PM visits China" article

# Option A: Extract from Reuters (no browser)
# 1. Find article URL via web search or known URL
# 2. Extract image URL from HTML
IMG_URL=$(curl -sL "https://www.reuters.com/world/uk-pm-china-visit/" | \
  grep -oE 'https://www\.reuters\.com/resizer/v2/[^"]+\.jpg' | head -1)
# 3. Download with HD params
curl -sL -o starmer-xi.jpg "${IMG_URL}?width=3000&quality=100"

# Option B: Brave search (no browser)
IMG_URL=$(curl -s "https://api.search.brave.com/res/v1/images/search?q=Keir%20Starmer%20Xi%20Jinping%202025&count=1" \
  -H "X-Subscription-Token: $BRAVE_API_KEY" | jq -r '.results[0].properties.url')
curl -sL -o starmer-xi.jpg "$IMG_URL"

# Option C: AI generate (no browser)
curl -sL -o uk-china.jpg "https://image.pollinations.ai/prompt/British%20and%20Chinese%20flags%20diplomatic%20meeting%20minimalist?width=1920&height=1080&nologo=true"

# Verify result
file starmer-xi.jpg
ls -lh starmer-xi.jpg

---

Quick Reference Card

Choose Method by Scenario

Need	Recommended Method	Reason
Specific news event	News site extraction	Authentic, authoritative
General concept image	Brave search	Fast, free
No suitable real photo	AI generation	Fully customizable
Article cover	AI generation	Controllable text space
Dashboard news	Brave search	Automation-friendly

Image Quality Checklist

• Resolution ≥ 1200px width
• File size > 50KB (smaller likely thumbnail)
• file command confirms image (not HTML)
• No watermarks
• No copyright issues (news images for commentary/citation)

---

Troubleshooting

Problem	Cause	Solution
curl returns HTML	Hotlink protection/signature	Try different source or Brave search
Image 403	URL expired	Re-fetch URL
Blurry image	Downloaded thumbnail	Adjust HD parameters
Brave no results	Keywords too specific	Simplify keywords
grep returns empty	Page uses JavaScript rendering	Use Brave search instead