
Icon Retrieval
This skill lets Claude search for icons via an HTTP API and fetch the SVG content directly using curl. You give it a keyword like "security" or "document" and it pulls back up to 20 matching icon URLs, then retrieves the actual SVG strings you can drop into pages or diagrams. It's straightforward if you're building infographics, dashboards, or any project where you need quick visual elements without hunting through icon libraries manually. The API is hosted at a third-party endpoint, so reliability depends on that service being up. Works best when you need programmatic icon access during prototyping or content generation rather than curated design work.
- skills.sh installs
- 1.7K
- GitHub stars
- 530
- last updated
- Aug 21, 2026
Install
$ npx -y skills add antvis/chart-visualization-skills --skill icon-retrieval --agent claude-codeInstalls into .claude/skills of the current project.
Files
Icon Search
Use the icon HTTP API directly with curl.
API
Search Endpoint
- Method:
GET - URL:
https://www.weavefox.cn/api/v1/infographic/icon - Query params:
text(required): search keyword, e.g."data analysis"topK(optional): number of icons to fetch (1-20), default5
Example:
curl -sS -L --max-time 20 "https://www.weavefox.cn/api/v1/infographic/icon?text=document&topK=5"
Typical response:
{
"success": true,
"data": [
"https://example.com/icon1.svg",
"https://example.com/icon2.svg"
]
}
Retrieve SVG Content
curl -sS -L --max-time 20 "https://example.com/icon1.svg"
Workflow
- Determine the icon concept keyword (for example:
security,document,data). - Search icon URLs using the API endpoint.
- Use
curlto fetch the SVG content of selected URLs. - Use SVG directly in pages, diagrams, or infographic materials.
Notes
- Use URL encoding for special characters in
text. topKrange is 1–20; if omitted, the service returns up to 5 results.- For network issues, retry with a smaller
topKor verify endpoint accessibility.
Sponsors
Details
- Repository
- github.com/antvis/chart-visualization-skills
- Categories
- Backend & APIs, Data Science & ML
- First seen
- May 16, 2026