Search for images using Google Custom Search API with intelligent scoring and LLM-based selection.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongoogle-image-searchExecute the skills CLI command in your project's root directory to begin installation:
Fetches google-image-search from glebis/claude-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate google-image-search. Access via /google-image-search in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
9
total installs
9
this week
90
GitHub stars
0
upvotes
Run in your terminal
9
installs
9
this week
90
stars
Search for images using Google Custom Search API with intelligent scoring and LLM-based selection.
/opt/homebrew/bin/llmStore credentials in .env:
Google-Custom-Search-JSON-API-KEY=your_key
Google-Custom-Search-CX=your_cx
OPENROUTER_API_KEY=your_openrouter_key
Search for a single term:
python3 ~/.claude/skills/google-image-search/scripts/google_image_search.py \
--query "neural interface wearable device" \
--output-dir ./images \
--num-results 5
Process multiple queries from JSON config:
python3 ~/.claude/skills/google-image-search/scripts/google_image_search.py \
--config image_queries.json \
--output-dir ./images \
--llm-select
Create JSON config from a list of terms using LLM:
python3 ~/.claude/skills/google-image-search/scripts/google_image_search.py \
--generate-config \
--terms "AlterEgo wearable" "sEMG electrodes" "BCI headset" \
--output my_queries.json
Extract visual terms from note, find images, and insert below headings:
python3 ~/.claude/skills/google-image-search/scripts/google_image_search.py \
--enrich-note ~/Brains/brain/Research/neural-interfaces.md
This mode:
| Option | Description |
|---|---|
--query TEXT |
Simple single query |
--config FILE |
JSON config for batch |
--generate-config |
Generate config from --terms |
--enrich-note FILE |
Enrich Obsidian note |
--output-dir DIR |
Where to save images |
--urls-only |
Return URLs only, no download |
--llm-select |
Use LLM to pick best image (default: on) |
--no-llm-select |
Disable LLM selection |
--num-results N |
Results per query (default: 5) |
--dry-run |
Show what would be done |
Each entry supports:
{
"id": "unique-id",
"heading": "Display Heading",
"description": "Context for what image to find",
"query": "Google search query",
"numResults": 5,
"selectionCriteria": "What makes a good image",
"requiredTerms": ["must", "have"],
"optionalTerms": ["bonus", "terms"],
"excludeTerms": ["stock", "clipart"],
"preferredHosts": ["official-site.com"],
"selectionCount": 2
}
See references/api_config_reference.md for full documentation.
Images are scored based on:
After scoring, LLM picks the best image from top candidates based on:
The LLM evaluates authenticity, clarity, and relevance for technical audiences.
When in an Obsidian vault:
.obsidian folderAttachments)![[image.png|alt text]]| File | Purpose |
|---|---|
google_image_search.py |
Main entry point |
api.py |
Google Custom Search API |
config.py |
Credentials and config handling |
download.py |
Image download with magic bytes |
evaluate.py |
Keyword-based scoring |
llm_select.py |
LLM selection and term extraction |
obsidian.py |
Vault detection and enrichment |
output.py |
Markdown output generation |
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
kostja94/marketing-skills
aaaaqwq/claude-code-skills
aradotso/trending-skills
agentbay-ai/agentbay-skills
Leonxlnx/taste-skill
jwynia/agent-skills
google-image-search has been reliable in day-to-day use. Documentation quality is above average for community skills.
We added google-image-search from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
google-image-search fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: google-image-search is the kind of skill you can hand to a new teammate without a long onboarding doc.
Solid pick for teams standardizing on skills: google-image-search is focused, and the summary matches what you get after install.
Useful defaults in google-image-search — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
google-image-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: google-image-search is focused, and the summary matches what you get after install.
google-image-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Registry listing for google-image-search matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 32