SWSkillsWay.ai
View Repo ↗
Skillset · / squirrelscan / skills

squirrelscansquirrelscan/skills

PurposeA collection of two Agent Skills (`squirrelscan` and `audit-website`) plus a plugin/marketplace for Claude Code, Cursor, and Codex. It wraps the squirrelscan CLI to let AI agents audit websites across 260+ rules (SEO, performance, security, etc.), detect leaked secrets, and iteratively fix issues via a code-mapping loop. Used for automated site health checks, regression diffs, and CI/CD pipelines through standard Agent Skills or MCP server.
Skill Count
2
Required CLI
squirrel
Domains
BusinessCodingOthers
Forms
Cli ManualWorkflow
Skillset Analysis

Core Idea

Principles & Methodology

The author's design philosophy, what sets this apart from peer projects, and quick notes on the key workflows. Skill names mentioned in the text auto-link to their detail pages.

Core Idea

squirrelscan skills turn a website audit CLI into agent-native workflows, unlike all-in-one site builders it focuses on detection + fix loop for site health.

Principles

  • CLI-driven: both skills wrap the squirrel CLI (must be in PATH)
  • Audit-first: crawl + 260+ rules across 21 categories, LLM-native output
  • Iterative fixing: map findings to code, fix in batches, re-audit

Key Skills

  • squirrelscan: operate CLI — install, login, run audits, publish, MCP setup
  • audit-website: the fix loop — audit, map to source, fix, re-audit until score is good

Workflow

  1. User asks to audit/fix a site
  2. Agent uses squirrelscan to run audit
  3. audit-website drives batch fixes + re-audits Best in CI/CD and AI-assisted debugging.

Installation

One command to install the entire Skillset.

Copy and run in your terminal to add squirrelscan/skills to your Agent environment.

$npx skills add squirrelscan/skills
SkillsWay.ai · Heads-Up Agent Skills InspectorUnderstand Agent Skills before you install.

Skill Relationships

Usage Relationships Between Skills

Skill → Skill usage relationships, with cross-layer references. Same color blocks indicate the same skill form.

Relationship Count
2
Standalone Skills
0
Most Referencing
  • audit-website1 downstream skills
  • squirrelscan1 downstream skills
Most Referenced
  • squirrelscan1 upstream skills
  • audit-website1 upstream skills

Note: Each dependency line reads as "the current Skill depends on" the Skill it points to.

Skill Composition

How skills in this set are triggered

Each skill is designed for a specific kind of caller — some only fire when you name them, others load automatically when the model judges them relevant. The split below summarises both modes at a glance.

User-Invoked0

These skills only fire when you call them by name. The agent will not load them on its own — they stay inert until invoked.

No skill in this set is recommended for manual invocation.

Model-Invoked0

These skills are loaded automatically by the agent when it judges the context relevant. You usually don't need to call them yourself.

No skill in this set is model-invoked.

Skill List

2 Skills · Filter by name or domain

audit-website

Audits websites via the squirrel CLI across 20+ rule categories (260+ rules) and drives an iterative code fix loop. Maps issues to source, applies batched fixes, re-audits until score targets met. Delivers a healthy, fixed site with before/after proof.

→
Domain
CodingOthers
Form
Workflow
Location
skills/audit-website/SKILL.md

squirrelscan

squirrelscan skill operates the squirrel CLI to audit websites across 260+ rules in 21 categories (SEO, performance, security, etc.), producing health scores and LLM-optimized reports. It covers install, auth, audit, report publishing, cloud credits, and MCP setup. Value: quickly identifies fixable site issues to improve ranking, speed, and health.

→
Domain
CodingBusiness
Form
Cli Manual
Location
skills/squirrelscan/SKILL.md

Showing 2 / 2