Agent Skill

Squirrelscan skill

squirrelscansquirrelscan/skillsskills/squirrelscan/SKILL.md

squirrelscan audits websites for SEO, performance, security, accessibility, content, and structured data issues (300+ rules) and scores site health, via the squirrel CLI. Use when the user wants to check, audit, or improve a website's SEO, ranking, speed, or health, and for anything squirrelscan itself, installing or updating the CLI, login and API keys, running audits, publishing and sharing reports, cloud credits, MCP server setup, configuration, or troubleshooting. Also covers the entity map: the site-wide graph of the entities a site declares in its JSON-LD, and fixing structured data identity problems such as an organization declared separately on every page.

102MIT

always on

138 tokname + description

once used

7,047 tokSKILL.md body

bundled files

413 KB

repo stars

102GitHub

Install the Squirrelscan skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/squirrelscan/skills --skill squirrelscan

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/squirrelscan/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -R /tmp/skills/skills/squirrelscan ~/.claude/skills/squirrelscan

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	138 tok
When the agent uses it	The SKILL.md instructions	7,047 tok
Only if opened	4 bundled files (13 KB)	varies

Until it is used, squirrelscan costs about 9.9× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 2 skills from squirrelscan/skills would load 232 tokens of descriptions. Skills vs MCP study

Checks

Tells the agent to pipe a download into a shell (curl … | sh). That runs whatever the URL serves at that moment, with your permissions.
The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.

Pre-approved tools (allowed-tools): Bash(squirrel:*), Read. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

squirrelscan CLI
Links
Install
Command overview
Quickstart
Audit levels
Probing intensity
Authentication and accounts
Reports
Publishing
Regression diffs
What a published report holds
Structured data: the entity map
Proving a fix landed
Cloud features and credits
MCP server
Entity tools
Channel events
Agent feedback
Configuration
Custom request headers
Maintenance
Keeping these skills current
Reclaiming disk space

More skills from squirrelscan/skills

All skills in this repo

audit-websitesquirrelscan/skills
Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 16 other rule categories (300+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, and re-auditing until the site scores well. Use to discover and assess website or webapp issues and drive them to fixed.
74k94 tok idle · 1,246 in use