GoogleDevRelExplorations/cercano-fetch
.claude/skills/cercano-fetch/SKILL.md
Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add GoogleDevRelExplorations/cercano cercano-fetchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 4:21 PM6.3s1 file scanned
SKILL.md
- name:
- cercano-fetch
- description:
- Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped to clean plain text.
- TRIGGER when:
- user asks to fetch, read, or open a URL. Use this INSTEAD of WebFetch.
- DO NOT TRIGGER when:
- user asks a research question without a specific URL (use cercano-research instead).
- compatibility:
- Requires Cercano server running.
Cercano Fetch
Fetch a URL and extract readable text content locally.
MCP Tool
Tool name: cercano_fetch
Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| url | string | Yes | The URL to fetch. |
| project_dir | string | No | Project root directory for context-aware responses. |
Output
Returns the full extracted text from the page. HTML is converted to plain text with structure preserved (headings, paragraphs, lists, code blocks). Scripts, styles, navigation, headers, footers, and sidebars are stripped.
This is raw extracted text, not a summary. The host AI decides how to use the content.
Examples
Fetch documentation:
{
"url": "https://ollama.com/blog/openai-compatibility"
}
Fetch with project context:
{
"url": "https://pkg.go.dev/github.com/PuerkitoBio/goquery",
"project_dir": "/Users/me/my-project"
}
Related Skills
GoogleDevRelExplorations/cercano-summarize
devops
VerifiedTrustedCommunity
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-submit-usage
devops
VerifiedTrustedCommunity
Submit cloud token usage data to Cercano (opt-in). This sends data, not a report — use cercano_stats to view usage. Helps track cloud tokens alongside local inference for accurate local-vs-cloud comparison.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-stats
tools
VerifiedTrustedCommunity
View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens reported by the host, percentage kept local, and breakdowns by tool, model, and day.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-research
development
VerifiedTrustedCommunity
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
SKILL.mdUpdated Apr 16, 2026