Skip to main content
squirrelscan is built for autonomous AI workflows. This guide shows you how to integrate squirrelscan with AI coding agents to audit websites and implement fixes automatically.

​
Three Ways to Use squirrelscan

CLI for Humans

Run audits directly from your terminal with human-readable output.

Pipe to Agent

Pipe audit reports to Claude or other AI assistants using squirrel report --format llm.

Skill Integration

Install the squirrelscan skill so agents can run audits autonomously.

​
Install the Skill

The squirrelscan skill enables AI agents to run audits, analyze results, and implement fixes without manual intervention.

​
Installation

npx skills install squirrelscan/skills
This installs the audit-website skill for:
  • Claude Code - Desktop and CLI
  • Cursor - AI-first code editor
  • Any agent supporting Claude Code skills
The skill is a thin wrapper that calls the squirrelscan CLI. Install both the CLI and skill for full functionality.

​
Verify Installation

After installing, verify the skill is available: 
npx skills list
You should see audit-website in the output.

​
Using with Claude Code

​
Basic Audit Workflow

Simply prompt Claude to audit a website: 
Use the audit-website skill to audit squirrelscan.com
Claude will:
  1. Run the audit using squirrelscan CLI
  2. Parse the results
  3. Summarize issues by severity
  4. Suggest next steps

​
Example Prompts

Use the audit-website skill to audit example.com and summarize
the top 5 most critical issues

Use the audit-website skill to audit mysite.com focusing on
accessibility and performance issues

Use the audit-website skill to audit this website and fix
all errors and warnings

Use the audit-website skill to audit http://localhost:3000
and create a prioritized fix list

​
Plan Mode for Comprehensive Fixes

For larger fix efforts, use Claude’s plan mode to create an implementation strategy:
1

Trigger plan mode

Ask Claude to enter plan mode before starting work:
Enter plan mode. Use the audit-website skill to audit example.com,
then create a comprehensive plan to fix all high and medium severity issues.
2

Review the plan

Claude will:
  • Run the audit
  • Analyze all issues
  • Group fixes by category
  • Create an ordered implementation plan
  • Identify dependencies between fixes
Review and approve the plan.
3

Execute the plan

Once approved, Claude will implement fixes systematically, checking off completed items.

​
Using Subagents for Parallel Fixes

For complex sites with many issues, prompt Claude to use subagents: 
Use the audit-website skill to audit example.com.
Then spawn subagents to fix issues in parallel:
- Subagent 1: Fix all accessibility issues
- Subagent 2: Fix all SEO meta tag issues
- Subagent 3: Fix all performance issues
This parallelizes work across independent issue categories.

​
Piping to Claude (Alternative Method)

If you prefer not to use skills, pipe audit output directly to Claude:

​
Using Report Formats

After running an audit, export results in LLM-optimized formats: 
# Step 1: Run audit
squirrel audit example.com

# Step 2: Export and pipe to Claude
squirrel report <audit-id> --format llm | claude
LLM Format Benefits:
  • Compact structured XML/text hybrid (40% smaller than verbose XML)
  • Token-optimized for API costs and context limits
  • Includes actionable fix suggestions
  • Works with any LLM (Claude, GPT, etc.)

​
Example Workflows

# Audit and ask Claude to prioritize fixes
AUDIT_ID=$(squirrel audit example.com | tail -1)
squirrel report $AUDIT_ID --format llm | claude "Prioritize these issues and create a fix plan"

# Audit and implement high-severity fixes
squirrel report <audit-id> --format llm | claude "Fix all high-severity issues"

# Audit and explain issues to non-technical stakeholder
squirrel report <audit-id> --format text | claude "Explain these issues in simple terms"

​
Other Formats for AI

FormatFlagBest For
llm--format llmCompact structured XML for AI agents (40% smaller, token-optimized)
text--format textPlain text output for simple piping
json--format jsonCustom AI processing scripts
markdown--format markdownAI agents that prefer markdown
xml--format xmlVerbose structured XML for enterprise integration
Note: These formats are only available via squirrel report <audit-id> --format <format>, not the audit command directly.

​
Using with Other AI Coding Assistants

​
Cursor

Cursor supports Claude Code skills natively:
  1. Install the skill: 
    npx skills install squirrelscan/skills
  2. Use in Cursor chat: 
    @audit-website example.com
  3. Or use composer mode for multi-file fixes: 
    Use audit-website skill to audit this site, then fix all issues across the codebase

​
Windsurf / Aider / Other Agents

For agents without skill support, use piping: 
# Windsurf (Cascade)
squirrel report <audit-id> --format llm | windsurf

# Aider
squirrel report <audit-id> --format llm | aider

# Generic LLM API - save to file then send
squirrel report <audit-id> --format llm > audit.xml
# Then send audit.xml content to your LLM

​
Advanced Agent Patterns

​
Continuous Monitoring

Set up Claude to run periodic audits: 
Every week, use audit-website skill to audit example.com,
compare results to last week's audit, and report any new
issues or regressions.

​
Pre-Deploy Audits

In your deployment workflow: 
Before I deploy, use audit-website skill to audit
http://localhost:3000 and ensure there are no high-severity
issues introduced since the last deployment.

​
Automated Regression Detection

After making changes: 
I just updated the homepage. Use audit-website skill to audit
the site and verify I didn't introduce any SEO or accessibility
regressions.

​
Configuration for Agents

​
Project-Scoped Config

Create .squirrel/config.json in your project so agents use consistent settings: 
{
  "crawl": {
    "maxPages": 50,
    "respectRobotsTxt": true
  },
  "rules": {
    "disabled": ["word-count", "reading-level"]
  }
}
Now when agents run audits, they’ll use these settings automatically. See Configuration Reference for all options.

​
Limiting Crawl Scope

For large sites, configure agents to audit specific sections: 
{
  "crawl": {
    "maxPages": 20,
    "allowedDomains": ["example.com"],
    "urlPatterns": ["^/blog/.*"]
  }
}

​
Skill vs Piping: Which to Use?

  • Working in Claude Code, Cursor, or skill-compatible editors
  • You want agents to discover and use squirrelscan autonomously
  • Building multi-step workflows where the agent decides when to audit
  • The agent needs to run audits as part of a larger task
  • Working with agents that don’t support skills
  • You want explicit control over when audits run
  • Integrating into shell scripts or automation
  • Using squirrelscan with non-coding LLMs

​
Troubleshooting

Verify installation:
npx skills list | grep audit-website
Reinstall if missing:
npx skills install squirrelscan/skills --force
Ensure squirrelscan CLI is installed:
squirrel --version
The skill requires the CLI to be in PATH.
Check the export format:
squirrel report <audit-id> --format llm
Ensure you’re using the report command with --format llm for LLM-optimized output.

​
Next Steps

Configuration

Customize audit behavior and rules

CLI Reference

Full command-line options

Rules Reference

Explore all 140+ audit rules

GitHub Skills Repo

View skill source code